# AI Practice Signal Brief

*2026-08-30 02:00 UTC* | 560 collected | 440 kept (signal>=1) | Sources: {'hackernews': 287, 'github': 119, 'lobsters': 75, 'stackoverflow': 79}

> High-recall dump: grouped by source, sorted by signal (heuristic priority hint only). Sift downstream for value.

## hackernews (269)

1. **Show HN: Loom – A Markdown knowledge graph for better coding-agent execution** | signal 55.0 | tags: agent workflow, context engineering, claude code, coding agent | https://github.com/z3z1ma/agent-loom
2. **Launch HN: Bullet (YC S26) – A Faster Coding Agent** | signal 44.0 | tags: claude code, coding agent, benchmark | https://www.codewithbullet.com
3. **Launch HN: Extend (YC W23) – Turn your messiest documents into data** | signal 43.6 | tags: context engineering, prompt engineering, evals | https://www.extend.ai/
4. **Show HN: Claude Code skills that build complete Godot games** | signal 41 | tags: claude code, coding agent | https://github.com/htdt/godogen
5. **Launch HN: Relari (YC W24) – Identify the root cause of problems in LLM apps** | signal 40.3 | tags: coding agent, rag pipeline, tool use, retrieval | https://news.ycombinator.com/item?id=39641105
6. **Launch HN: Vellum (YC W23) – Dev Platform for LLM Apps** | signal 39.8 | tags: prompt engineering, llm ops, vector | https://news.ycombinator.com/item?id=35042836
7. **Launch HN: LlamaFarm (YC W22) – Open-source framework for distributed AI** | signal 39.3 | tags: rag pipeline, evals, retrieval, vector | https://github.com/llama-farm/llamafarm
8. **Show HN: Representing Agents as MCP Servers** | signal 38.1 | tags: agent workflow, mcp agent | https://github.com/lastmile-ai/mcp-agent/tree/main/examples/mcp_agent_server
9. **Show HN: Armalo AI – The Infrastructure for Agent Networks** | signal 37.8 | tags: agent workflow, langchain, evals, benchmark | https://news.ycombinator.com/item?id=47244042
10. **Show HN: Laminar – Open-Source DataDog + PostHog for LLM Apps, Built in Rust** | signal 37 | tags: rag pipeline, evals, vector | https://github.com/lmnr-ai/lmnr
11. **Context Rot: How increasing input tokens impacts LLM performance** | signal 36 | tags: context engineering | https://research.trychroma.com/context-rot
12. **Show HN: R2R – Open-source framework for production-grade RAG** | signal 36 | tags: rag pipeline, retrieval, vector | https://github.com/SciPhi-AI/R2R
13. **Show HN: I open-sourced my Go and Next B2B SaaS Starter (deploy anywhere, MIT)** | signal 35.1 | tags: claude code, retrieval, vector | https://github.com/moasq/production-saas-starter
14. **Show HN: Autofix Bot – Hybrid static analysis and AI code review agent** | signal 34.5 | tags: claude code, coding agent, benchmark | https://news.ycombinator.com/item?id=46237358
15. **Show HN: ClawMem – Open-source agent memory with SOTA local GPU retrieval** | signal 34.2 | tags: claude code, coding agent, retrieval, vector | https://github.com/yoloshii/ClawMem
16. **Why My Open-Source Project Hasn't Done Better** | signal 32.4 | tags: evaluation harness, coding agent, benchmark | https://news.ycombinator.com/item?id=49046999
17. **I looked at 1000s of RAG queries to figure out the problem with semantic search** | signal 31.9 | tags: rag pipeline, evals, benchmark, retrieval, vector | https://news.ycombinator.com/item?id=42299349
18. **Ask HN: What Agent should I build next? Looking for ideas** | signal 31.1 | tags: agent workflow, rag pipeline, langchain | https://news.ycombinator.com/item?id=44325301
19. **Launch HN: Captain (YC W26) – Automated RAG for Files** | signal 30.4 | tags: rag pipeline, retrieval, vector | https://www.runcaptain.com/
20. **How do you pick a Coding Agent HN?** | signal 30.2 | tags: claude code, coding agent, benchmark | https://news.ycombinator.com/item?id=46634773
21. **Show HN: Wegent –Open Source Cloud Coding Agent Platform** | signal 30.1 | tags: claude code, coding agent, retrieval | https://github.com/wecode-ai/Wegent
22. **Launch HN: Sonarly (YC W26) – AI agent to triage and fix your production alerts** | signal 29.9 | tags: claude code, coding agent | https://sonarly.com/
23. **Launch HN: Manufact (YC S25) – MCP Cloud** | signal 28.6 | tags: claude code | https://manufact.com
24. **Show HN: Interbase – Long-running AI goals and aliases for any model** | signal 28.1 | tags: agent workflow, code review workflow | https://github.com/agentsorchestrationcompany/interbase
25. **Show HN: Open-source EU AI Act compliance layer for AI agents (8/2026 deadline)** | signal 27.3 | tags: rag pipeline, langchain, autogen, retrieval | https://news.ycombinator.com/item?id=47141347
26. **Launch HN: Roe AI (YC W24) – AI-powered data warehouse to query multimodal data** | signal 27.0 | tags: prompt engineering, vector | https://news.ycombinator.com/item?id=41202694
27. **Show HN: Superlog (YC P26) – Observability that installs itself and fixes bugs** | signal 26.7 | tags: claude code | https://superlog.sh/
28. **Show HN: A library to convert+deploy existing agent projects as MCP servers** | signal 26.5 | tags: agent workflow, langgraph | https://github.com/NapthaAI/automcp
29. **Show HN: Single-agent long-horizon reasoning within one LLM run** | signal 26.4 | tags: context engineering, tool use | https://huggingface.co/papers/2507.16784
30. **Show HN: Typia (20,000x faster validator) challenges to Agentic AI with compiler** | signal 26.1 | tags: agent workflow, function calling | https://typia.io/articles/typia-challenges-to-agentic-ai-with-its-compiler-skill.html
31. **Evaluating AGENTS.md: are they helpful for coding agents?** | signal 26 | tags: coding agent | https://arxiv.org/abs/2602.11988
32. **Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training** | signal 26 | tags: benchmark | https://github.com/alainnothere/llm-circuit-finder
33. **DeepClaude – Claude Code agent loop with DeepSeek V4 Pro** | signal 26 | tags: claude code | https://github.com/aattaran/deepclaude
34. **Show HN: AgentLint – ESLint for your coding agents** | signal 25.8 | tags: claude code, coding agent | https://github.com/samilozturk/agentlint
35. **Show HN: Gentrace – connect to your LLM app code and run/eval it from a UI** | signal 25.8 | tags: llm ops, evals, retrieval | https://gentrace.ai/
36. **Show HN: Agents, run any coding agent on your subscription not API costs** | signal 25.7 | tags: claude code, coding agent | https://agents-cli.sh
37. **Show HN: HoneyHive – An unified evaluation and monitoring platform for LLM apps** | signal 25.6 | tags: rag pipeline, langchain, benchmark, vector | https://news.ycombinator.com/item?id=37777683
38. **Show HN: 20+ Claude Code agents coordinating on real work (open source)** | signal 25.4 | tags: claude code | https://github.com/mutable-state-inc/lean-collab
39. **Ask HN: Why do AI coding agents refuse to save their own observations?** | signal 25.3 | tags: claude code, coding agent | https://news.ycombinator.com/item?id=47170501
40. **Show HN: Devplan – Generate specs and coding prompts with deep context** | signal 25.3 | tags: claude code, coding agent | https://www.devplan.com/
41. **Show HN: Irpapers – Visual embeddings vs. OCR trade-offs in scientific PDFs** | signal 25.2 | tags: rag pipeline, benchmark, retrieval, vector | https://github.com/weaviate/query-agent-benchmarking
42. **Show HN: A policy gate that runs before your AI coding agent's tool calls** | signal 25.1 | tags: claude code, coding agent | https://sigmashake.com
43. **Show HN: Projekt [Free Alpha] – All-in-one workspace for building with agents** | signal 25.1 | tags: claude code, coding agent | https://www.getprojekt.com/
44. **Show HN: Burr – A framework for building and debugging GenAI apps faster** | signal 25.1 | tags: langchain, evals | https://github.com/DAGWorks-Inc/burr
45. **Show HN: GibRAM an in-memory ephemeral GraphRAG runtime for retrieval** | signal 24.8 | tags: rag pipeline, retrieval, vector | https://github.com/gibram-io/gibram
46. **Show HN: Open-Source Animal Crossing–Style UI for Claude Code Agents** | signal 24.6 | tags: claude code | https://github.com/outworked/outworked/releases/tag/v0.3.0
47. **Launch HN: Talc AI (YC S23) – Test Sets for AI** | signal 24.6 | tags: benchmark | https://news.ycombinator.com/item?id=39042093
48. **Show HN: Real-time dashboard for Claude Code agent teams** | signal 24.4 | tags: claude code | https://github.com/simple10/agents-observe
49. **Q Evaluation Harness: open-source evals for LLMs on q/kdb+** | signal 23.1 | tags: evaluation harness, evals | https://github.com/KxSystems/q-evaluation-harness
50. **Show HN: Abralo – Free, easy way to run several Claude Code agents in one window** | signal 23.1 | tags: claude code | https://abralo.com/
51. **AI receptionist that answers real phone calls** | signal 22.9 | tags: evaluation harness, retrieval | https://news.ycombinator.com/item?id=45541794
52. **Show HN: ModelX – Prediction Exchange for LLMs** | signal 22.2 | tags: evaluation harness, benchmark | https://model-x.up.railway.app/
53. **Show HN: Caliper – pass@k reliability testing for Claude Code and Codex skills** | signal 21.8 | tags: claude code, evals | https://github.com/edonadei/caliper
54. **Show HN: Web-eval-agent – Let the coding agent debug itself** | signal 21.6 | tags: coding agent | https://github.com/Operative-Sh/web-eval-agent
55. **Show HN: Free local security checks for AI coding in VSCode, Cursor and Windsurf** | signal 21.6 | tags: coding agent | https://news.ycombinator.com/item?id=44309393
56. **Show HN: Vishu – Model Context Protocol (MCP) Suite** | signal 21.5 | tags: mcp agent, vector | https://news.ycombinator.com/item?id=44275368
57. **Productivity apps won't disappear, just the need to open them will** | signal 21.2 | tags: agent workflow | https://news.ycombinator.com/item?id=44139226
58. **Show HN: AgentKit – JavaScript Alternative to OpenAI Agents SDK with Native MCP** | signal 21.2 | tags: coding agent | https://github.com/inngest/agent-kit
59. **Why Codex works better than Claude Code for my production monolith** | signal 21.1 | tags: claude code, benchmark | https://news.ycombinator.com/item?id=47945185
60. **Show HN: Skilldeck – Desktop app to manage AI agent skill files across tools** | signal 21.1 | tags: claude code, tool use | https://github.com/ali-erfan-dev/skilldeck
61. **Show HN: Notebooklm-Py – Unofficial Python API for Google NotebookLM** | signal 21.1 | tags: claude code, rag pipeline | https://github.com/teng-lin/notebooklm-py
62. **Show HN: Rowboat – Open-source IDE for multi-agent systems** | signal 21 | tags: none | https://github.com/rowboatlabs/rowboat
63. **Show HN: Jido 2.0, Elixir Agent Framework** | signal 21 | tags: none | https://jido.run/blog/jido-2-0-is-here
64. **Launch HN: mrge.io (YC X25) – Cursor for code review** | signal 21 | tags: none | https://news.ycombinator.com/item?id=43692476
65. **Launch HN: Magic Patterns (YC W23) – AI Design and Prototyping for Product Teams** | signal 21 | tags: none | https://news.ycombinator.com/item?id=43752176
66. **Show HN: Inngest 1.0 – Open-source durable workflows on every platform** | signal 21 | tags: none | https://www.inngest.com/
67. **Show HN: Mcp-Agent – Build effective agents with Model Context Protocol** | signal 20.6 | tags: rag pipeline | https://github.com/lastmile-ai/mcp-agent
68. **Show HN: AgentWing – make AI agents complete tasks faster** | signal 20.3 | tags: agent workflow | https://news.ycombinator.com/item?id=48200511
69. **Context-Bench: Benchmarking LLMs on Agentic Context Engineering** | signal 20.2 | tags: context engineering, benchmark | https://www.letta.com/blog/context-bench
70. **Show HN: Tips for getting great Text2Cypher outputs from LLMs for Graph RAG** | signal 20.2 | tags: context engineering | https://blog.kuzudb.com/post/improving-text2cypher-for-graphrag-via-schema-pruning/
71. **Context Engineering – LLM Memory and Retrieval for AI Agents** | signal 20.1 | tags: context engineering, retrieval | https://weaviate.io/blog/context-engineering
72. **Show HN: Stop re-explaining context to every LLM (Git-based context engineering)** | signal 20.1 | tags: context engineering | https://github.com/jerpint/context-llemur
73. **At what level of deep context engineering does AI output become human-crafted?** | signal 20.1 | tags: context engineering | https://news.ycombinator.com/item?id=47330309
74. **Show HN: MarkdownLM – Stop being the human middleware for your AI agent** | signal 20.1 | tags: claude code, retrieval | https://news.ycombinator.com/item?id=47124474
75. **Why Your RAG Costs $2,400/Month (and How We Cut It by 73%)** | signal 20.1 | tags: rag pipeline, retrieval, vector | https://news.ycombinator.com/item?id=46234309
76. **Show HN: VittoriaDB – Zero-config embedded vector DB with HNSW and ACID storage** | signal 20.1 | tags: rag pipeline, benchmark, vector | https://github.com/antonellof/VittoriaDB
77. **Show HN: I built a circuit breaker that predicts AI failures** | signal 20.1 | tags: rag pipeline, langchain, vector | https://github.com/CULPRITCHAOS/Interlock
78. **Show HN: Create your own finetuned AI model using Google Sheets** | signal 19.9 | tags: none | https://promptrepo.com/finetune/
79. **Launch HN: JSX Tool (YC F25) – A Browser Dev-Panel IDE for React** | signal 18.6 | tags: none | https://news.ycombinator.com/item?id=45903161
80. **Show HN: I built "AI Wattpad" to eval LLMs on fiction** | signal 18.0 | tags: benchmark | https://narrator.sh/llm-leaderboard
81. **Show HN: MCP-C – cloud platform for running MCP agents and apps** | signal 17.9 | tags: mcp agent | https://docs.mcp-agent.com/get-started/cloud
82. **Show HN: CocoIndex – Open-Source Data framework for AI, built for data freshness** | signal 17.9 | tags: rag pipeline, vector | https://github.com/cocoindex-io/cocoindex
83. **Show HN: PolyMCP – A framework for building and orchestrating MCP agents** | signal 17.6 | tags: mcp agent | https://news.ycombinator.com/item?id=47017912
84. **Show HN: Jay - Fully programmable, fully hosted AI voice agents** | signal 17.6 | tags: rag pipeline, function calling | https://www.jay.so/
85. **Alternative of MCP with AI RAG Agentic Framework** | signal 17.3 | tags: mcp agent | https://news.ycombinator.com/item?id=43603324
86. **Show HN: PolyClaw – Autonomous Docker-First MCP Agent for PolyMCP** | signal 17.1 | tags: mcp agent | https://news.ycombinator.com/item?id=47047299
87. **Show HN: PolyClaw – An Autonomous Docker-First MCP Agent for PolyMCP** | signal 17.1 | tags: mcp agent | https://news.ycombinator.com/item?id=47036828
88. **Show HN: MCP-C – cloud platform for running MCP agents and apps** | signal 17.1 | tags: mcp agent | https://docs.mcp-agent.com/cloud/overview
89. **Show HN: PolyMCP – A framework for structuring and orchestrating MCP agents** | signal 17.1 | tags: mcp agent | https://news.ycombinator.com/item?id=47026179
90. **Show HN: Easily generate text and compute probabilities for any Hugging Face LLM** | signal 17.1 | tags: evaluation harness | https://github.com/RichardKelley/hflm
91. **Ask HN: What tools are you using for AI evals? Everything feels half-baked** | signal 16.9 | tags: evals, benchmark | https://news.ycombinator.com/item?id=44194187
92. **I build my LLM a Brain** | signal 16.7 | tags: context engineering | https://news.ycombinator.com/item?id=47928151
93. **Save 70-90% in tokens per session** | signal 16.6 | tags: coding agent, evals | https://news.ycombinator.com/item?id=47395507
94. **Show HN: Modulus – Cross-repository knowledge orchestration for coding agents** | signal 16.6 | tags: coding agent | https://modulus.so
95. **Show HN: A local merge queue for parallel Claude Code agents** | signal 16.5 | tags: claude code | https://github.com/funador/claude-code-merge-queue
96. **Ask HN: How are you LLM-coding in an established code base?** | signal 16.5 | tags: none | https://news.ycombinator.com/item?id=46292682
97. **Show HN: OpenCastor Agent Harness Evaluator Leaderboard** | signal 16.4 | tags: evals, benchmark | https://craigm26.github.io/OpenCastor/
98. **Launch HN: OneCLI (YC S26) – OSS sandboxed agent harness for teams** | signal 16.4 | tags: none | https://github.com/onecli/onecli
99. **Best AI Coding Agents – Gosu Evals** | signal 16.1 | tags: coding agent, evals | https://gosuevals.com/agents.html
100. **Evals Skills for Coding Agents** | signal 16.1 | tags: coding agent, evals | https://hamel.dev/blog/posts/evals-skills/
101. **Show HN: PokemonGym – 387 milestones designed to test agents and LLMs** | signal 16.1 | tags: tool use, benchmark | https://twitter.com/xdotli/status/1908373420032795083
102. **Show HN: Cockpit for you Claude Code agents in Rust** | signal 16.1 | tags: claude code | https://episko.dev/
103. **Context engineering is just software engineering for LLMs** | signal 15.9 | tags: context engineering | https://www.inngest.com/blog/context-engineering-is-software-engineering-for-llms
104. **Show HN: Daf·thunk – open-source Editor for Prototyping Workflows on Cloudflare** | signal 15.9 | tags: cursor rules | https://www.dafthunk.com/
105. **Launch HN: Openlayer (YC S21) – Testing and Evaluation for AI** | signal 15.9 | tags: none | https://news.ycombinator.com/item?id=38532593
106. **SOTA on the hardest AI memory benchmark (BEAM, 10M tokens), with a smaller model** | signal 15.8 | tags: benchmark, retrieval | https://news.ycombinator.com/item?id=49085375
107. **Show HN: Foolery – a web UI for orchestrating Claude Code agents on top of Beads** | signal 15.8 | tags: claude code | https://github.com/acartine/foolery
108. **Context Engineering for the LLM OS: User vs. Kernel Context** | signal 15.7 | tags: context engineering | https://www.letta.com/blog/guide-to-context-engineering
109. **Show HN: Crew – Let Claude Code agents talk to each other** | signal 15.6 | tags: claude code | https://github.com/0xmmo/crew
110. **Ask HN: Claude Code–style agent, but Aider-like and model-agnostic?** | signal 15.6 | tags: claude code | https://news.ycombinator.com/item?id=44693354
111. **Show HN: Modulus – Run multiple coding agents with shared project memory** | signal 15.6 | tags: coding agent | https://modulus.so
112. **Show HN: Hiver – Chrome DevTools for Agents** | signal 15.5 | tags: claude code | https://hiver.sh
113. **DeepSWE – Best Benchmark for Evaluating AI Coding Agents?** | signal 15.3 | tags: coding agent, benchmark | https://www.i-programmer.info/news/105-artificial-intelligence/19016-deepswe-best-benchmark-for-evaluating-ai-coding-agents.html
114. **Folks who work for large tech companies: How are you using Cursor?** | signal 15.3 | tags: cursor rules | https://news.ycombinator.com/item?id=43450576
115. **Show HN: PlanWiki – Open-source platform for product teams and agents to execute** | signal 15.3 | tags: claude code | https://github.com/planwiki/planwiki-app
116. **Show HN: Kote – Capture and reuse engineering context from AI chats and Git** | signal 15.2 | tags: claude code | https://github.com/pedroaugusto04/Kote
117. **Claude Code Open Source?** | signal 15.2 | tags: claude code | https://news.ycombinator.com/item?id=47285571
118. **Show HN: Taurus Agents, my take on multi-agent hierarchies** | signal 15.2 | tags: claude code | https://taurusagents.com/
119. **Show HN: Oc-mnemoria – Persistent memory for AI coding agents** | signal 15.2 | tags: coding agent | https://github.com/one-bit/oc-mnemoria
120. **Show HN: Voicetest – open-source test harness for voice AI agents** | signal 15.2 | tags: claude code | https://news.ycombinator.com/item?id=47048811
121. **Show HN: Claude Code Agent Farm** | signal 15.2 | tags: claude code | https://github.com/Dicklesworthstone/claude_code_agent_farm
122. **Are AI coding tools fundamentally changing Agile/team software development?** | signal 15.2 | tags: claude code | https://news.ycombinator.com/item?id=45584707
123. **Show HN: Airut – Sandboxed Claude Code sessions over email** | signal 15.1 | tags: claude code | https://github.com/airutorg/airut
124. **SpecTree: Composable Context Engineering for LLMs** | signal 15.1 | tags: context engineering | https://www.fuzzycomputer.com/posts/spectree
125. **Introductory field guide to Context Engineering for LLM users** | signal 15.1 | tags: context engineering | https://andybromberg.com/field-guide-context-engineering
126. **Context Engineering in an LLM Harness** | signal 15.1 | tags: context engineering | https://udnes.dev/posts/context-engineering-harness-part-1-ontology/
127. **Agentic Context Engineering: Evolving Contexts for Self-Improving LLMs** | signal 15.1 | tags: context engineering | https://arxiv.org/abs/2510.04618
128. **Context Engineering for Agents: A Practical Guide** | signal 15.1 | tags: context engineering | https://blog.malt.engineering/dont-take-this-out-of-context-feeding-your-llm-exactly-what-it-needs-0db8a86d2151
129. **Show HN: A visual AI interface to understand topics/books/papers with LLMs** | signal 15.1 | tags: context engineering | https://www.kerns.ai/
130. **DeepSWE – Best Benchmark for Evaluating AI Coding Agents?** | signal 15.1 | tags: coding agent, benchmark | https://www.i-programmer.info/professional-programmer/103-i-programmer/18759-why-software-engineering-will-never-die-revisited-in-the-age-of-spec-driven-development.html
131. **The Kotlin Benchmark for AI Coding Agents** | signal 15.1 | tags: coding agent, benchmark | https://blog.jetbrains.com/kotlin/2026/07/introducing-the-kotlin-benchmark-evaluate-ai-coding-agents-on-real-world-kotlin-tasks/
132. **Write a prompt once, sync it to Cursor, Claude Code and VS Code automatically** | signal 15.1 | tags: claude code | https://news.ycombinator.com/item?id=47849308
133. **Show HN: Dev platform for generating MCP Tools** | signal 15.1 | tags: langchain, autogen | https://news.ycombinator.com/item?id=44429590
134. **Show HN: AlphaEvolve inspired evolution harness for Pokemon** | signal 15.1 | tags: coding agent | https://github.com/papercomputeco/pokemon
135. **Show HN: SHTMLs – HTML pastebin where the AI uploads its own output** | signal 15.1 | tags: claude code | https://news.ycombinator.com/item?id=47426450
136. **Show HN: Stop manually syncing rules between Claude, Cursor, and Codex** | signal 15.1 | tags: claude code | https://github.com/nanxiaobei/ai-global
137. **Show HN : Pilot – System to improve dramatically your AI coding** | signal 15.1 | tags: claude code | https://github.com/clementrog/pilot
138. **Show HN: MemoryGate – Open-source persistent memory for AI agents via MCP** | signal 15.1 | tags: rag pipeline, vector | https://www.memorygate.ai
139. **Garvata: Observability and Debugging for AI Agent Stack** | signal 14.3 | tags: retrieval, vector | https://news.ycombinator.com/item?id=42293942
140. **Show HN: CLI for agentic activity tracking in Codex** | signal 14.1 | tags: retrieval, vector | https://news.ycombinator.com/item?id=47163587
141. **PA bench: Evaluating web agents on real world personal assistant workflows** | signal 13.7 | tags: benchmark | https://vibrantlabs.com/blog/pa-bench
142. **Show HN: Zipy.ai – Live web debugging with error monitoring and session replay** | signal 13.7 | tags: none | https://www.zipy.ai/
143. **Show HN: Verdic Guard – Deterministic guardrails to prevent LLM hallucinations** | signal 13.3 | tags: prompt engineering | https://news.ycombinator.com/item?id=46602822
144. **Show HN: Unify Browser – WebKit Browser Built with SwiftUI and MLX** | signal 13.1 | tags: prompt engineering | https://apps.apple.com/us/app/unify-ai-browser/id6478436147?mt=12
145. **Show HN: I Built an AI-Powered Pull Request Review Tool** | signal 13.1 | tags: code review workflow | https://github.com/HighGarden-Studio/HighReview
146. **Outworked – An Open Source Office UI for Claude Code Agents** | signal 13.0 | tags: claude code | https://github.com/outworked/outworked
147. **Launch HN: Coasty (YC S26) – An API for computer-use agents** | signal 12.4 | tags: none | https://coasty.ai/docs
148. **Launch HN: Patched (YC S24) – AI workflows for post-code tasks** | signal 12.3 | tags: none | https://news.ycombinator.com/item?id=42009089
149. **Show HN: A police department for your Claude Code agents** | signal 12.2 | tags: claude code | https://github.com/varmabudharaju/agent-pd/blob/master/README.md
150. **A review of OpenAI o1 and how we evaluate coding agents** | signal 12.1 | tags: coding agent | https://www.cognition.ai/blog/evaluating-coding-agents
151. **Show HN: Fast-agent – Compose MCP enabled Agents and Workflows in minutes** | signal 12.1 | tags: retrieval | https://github.com/evalstate/fast-agent
152. **Show HN: AI-powered web service combining FastAPI, Pydantic-AI, and MCP servers** | signal 12.1 | tags: none | https://github.com/Aherontas/Pycon_Greece_2025_Presentation_Agents
153. **Show HN: Self-bench – build SWE-bench style evals from private repos** | signal 11.2 | tags: evals | https://github.com/mupt-ai/self-bench
154. **Show HN: Eval based agent builder (pls roast us)** | signal 11.2 | tags: langchain, evals | https://github.com/seer-engg/seer
155. **Bad MCP design costs your agent 5x more tokens** | signal 11.1 | tags: benchmark | https://news.ycombinator.com/item?id=48407391
156. **Show HN: Real-time visualization of Claude Code agent orchestration** | signal 11.1 | tags: claude code | https://github.com/patoles/agent-flow
157. **Show HN: OpenJet – An offline agent harness for memory-constrained edge hardware** | signal 11.1 | tags: evals | https://github.com/L-Forster/open-jet
158. **Show HN: A/B Test Your LLM Prompts in Production** | signal 11.1 | tags: evals | https://switchport.ai/
159. **Show HN: Krira Augment – Production-ready RAG in minutes** | signal 11.1 | tags: rag pipeline | https://www.kriralabs.com/waitlist
160. **Show HN: A JSON API for YouTube Transcript with MCP Support** | signal 11.1 | tags: rag pipeline | https://transcriptapi.com/
161. **Show HN: AI Interoperability to the Max – The Intelligence Hub** | signal 11.1 | tags: rag pipeline | https://theintelligencehub.azurewebsites.net/
162. **Ask HN: Anyone solved hallucination or semantic drift in RAG?** | signal 11.1 | tags: rag pipeline | https://news.ycombinator.com/item?id=44746089
163. **My Claude Code Agent for Writing Prompts** | signal 10.8 | tags: claude code | https://olshansky.info/posts/2025-09-29-prompt-writer-agent
164. **Ferretlog: Git log for your Claude Code agent runs** | signal 10.7 | tags: claude code | https://github.com/eitanlebras/ferretlog
165. **Curie – ship Claude Code agents to Kubernetes with Git push** | signal 10.6 | tags: claude code | https://github.com/curie-eng/curie
166. **Replaced Clay.com with Claude Code Agent** | signal 10.6 | tags: claude code | https://github.com/chaitanyya/sales
167. **I built IDE-layer policy enforcement for Claude Code/Cursor agents** | signal 10.4 | tags: claude code | https://www.oculisecurity.com/
168. **Connect multiple Claude Code agents into one collaborative team** | signal 10.4 | tags: claude code | https://openagents.org/showcase
169. **15 AI Coding Agents evaluated with the same prompt** | signal 10.3 | tags: coding agent | https://github.com/The-Focus-AI/june-2025-coding-agent-report
170. **Why Claude Code's Agent Loop Is over 1,400 Lines** | signal 10.3 | tags: claude code | https://internals.laxmena.com/p/why-claude-codes-agent-loop-is-over
171. **Show HN: I run a full software company solo with Claude Code agents** | signal 10.3 | tags: claude code | https://theonemancompany.com/
172. **Show HN: I built an open-source Rust/TS AI agent runtime with a Next.js-style DX** | signal 10.2 | tags: langchain | https://docs.trysoma.ai
173. **New Inference Server for DGX Spark: large model C4:55-90 tok/s no spec decode** | signal 10.2 | tags: benchmark | https://news.ycombinator.com/item?id=49014048
174. **How to evaluate models for production coding agents** | signal 10.2 | tags: coding agent | https://blaxel.ai/blog/llm-coding-benchmarks
175. **FlyCrys – Native Linux GUI for Claude Code Agents (Rust and GTK4)** | signal 10.2 | tags: claude code | https://github.com/SergKam/FlyCrys
176. **20 Claude Code agents, one terminal: a tmux + AppleScript setup** | signal 10.2 | tags: claude code | https://pkarnal.com/blog/parallel-ai-agents
177. **Securely run Claude Code agents in Docker** | signal 10.2 | tags: claude code | https://edspencer.net/2026/2/4/run-claude-code-agents-docker-herdctl
178. **Show HN: I built a context-engineering CLI/MCP tool** | signal 10.1 | tags: retrieval | https://github.com/jerpint/context-llemur
179. **Evaluating Coding Agents** | signal 10.1 | tags: coding agent | https://www.aiuc-1.com/research/technical-docs-evaluating-coding-agents
180. **When your coding agent doesn't listen: evaluating a 241-turn Claude session** | signal 10.1 | tags: coding agent | https://www.kurrent.io/blog/when-your-coding-agent-doesnt-listen/
181. **Engine-Bench: Evaluating Coding Agents on Writing Game Engine Code** | signal 10.1 | tags: coding agent | https://github.com/JoshuaPurtell/engine-bench
182. **Evaluating Coding Agents with Terminal-Bench 2.0** | signal 10.1 | tags: coding agent | https://snorkel.ai/blog/evaluating-coding-agent-capabilities-with-terminal-bench-snorkels-role-in-building-the-next-generation-benchmark/
183. **Show HN: A Framework for Evaluating Coding Agents on Sequential SWE** | signal 10.1 | tags: coding agent | https://arxiv.org/abs/2604.03035
184. **ReactBench – evaluation for coding agents on realistic React work** | signal 10.1 | tags: coding agent | https://www.reactbench.com/
185. **No one is evaluating AI coding agents in the way they are used** | signal 10.1 | tags: coding agent | https://marginlab.ai/blog/the-problem-with-coding-benchmarks/
186. **Show HN: Apitoll Payment InfrastructureforAIagents75 Live APIs,USDCmicropayments** | signal 10.1 | tags: langchain | https://github.com/TasnidChain/apitoll-demo
187. **Show HN: Cortex Click – LLM-Driven Developer Marketing Platform** | signal 10.1 | tags: retrieval | https://news.ycombinator.com/item?id=41583460
188. **Cursor Rules for Writing Temporal Workflows with TypeScript** | signal 10.1 | tags: cursor rules | https://stevekinney.com/writing/cursor-rules-temporal-typescript
189. **KernelEvolve: Agentic kernel coding for heterogeneous AI accelerators (Meta)** | signal 10.1 | tags: benchmark | https://news.ycombinator.com/item?id=46442841
190. **Open Source LLMOps Stack** | signal 9.6 | tags: none | https://oss-llmops-stack.com
191. **Show HN: VectorGuard-Nano – Free secure messaging for AI agents** | signal 9.4 | tags: vector | https://github.com/Active-IQ/VectorGuard-Nano
192. **I Got Pwned by a Malicious AI Plugin: A Technical Breakdown** | signal 9.3 | tags: vector | https://news.ycombinator.com/item?id=47109114
193. **Dispelling Misconceptions and Unveiling the Truth about GOT and OT in General** | signal 9.1 | tags: vector | https://news.ycombinator.com/item?id=36643393
194. **Show HN: Local LLM Notepad – run a GPT-style model from a USB stick** | signal 8.8 | tags: none | https://github.com/runzhouye/Local_LLM_Notepad
195. **Ask HN: What's your 2025 code review workflow? GitHub UI feels ancient** | signal 8.6 | tags: code review workflow | https://news.ycombinator.com/item?id=44583146
196. **My Current AI Code Review Workflow** | signal 8.3 | tags: code review workflow | https://guissmo.com/blog/my-current-ai-code-review-workflow/
197. **SHOW HN: A usage circuit breaker for Cloudflare Workers** | signal 8.2 | tags: none | https://news.ycombinator.com/item?id=47322794
198. **Show HN: AI-Friendly Toolchain – Dev Tools for Working with LLMs** | signal 8.1 | tags: prompt engineering | https://github.com/trknhr/awesome-ai-friendly-toolchain
199. **Show HN: Hopsule – Persistent memory and decision layer for AI development** | signal 7.5 | tags: none | https://news.ycombinator.com/item?id=47415402
200. **Show HN: An open-source Operator that can use computers** | signal 7.1 | tags: none | https://github.com/aditya-nadkarni/spongecake
201. **I'm starting to feel tired of AI features that solve problems I don't have** | signal 6.5 | tags: none | https://news.ycombinator.com/item?id=45734499
202. **The way every agent framework handles MCP is a latent security problem** | signal 6.3 | tags: none | https://news.ycombinator.com/item?id=47683498
203. **Does anyone use MCP servers in their dev workflow?** | signal 6.3 | tags: none | https://news.ycombinator.com/item?id=43258552
204. **Building a production-ready RAG pipeline and eval platform** | signal 6.1 | tags: rag pipeline | https://docs.vectorize.io/core-concepts/vectorize-architecture
205. **Show HN: Ductwork – A Go platform for running AI agents on autopilot** | signal 6.0 | tags: none | https://github.com/dneil5648/ductwork
206. **Show HN: Velvet – Data platform with an AI SQL editor** | signal 6.0 | tags: none | https://www.usevelvet.com/
207. **Built a content system that 6x'd traffic. Turning it into product. Want to test?** | signal 6.0 | tags: none | https://news.ycombinator.com/item?id=46337608
208. **Seeking feedback: Integrated product discovery workflow tool** | signal 5.9 | tags: none | https://news.ycombinator.com/item?id=45830436
209. **Show HN: OQP – A verification protocol for AI agents** | signal 5.8 | tags: none | https://github.com/OranproAi/open-qa-protocol
210. **Show HN: Capcat – CLI/TUI to Archive Articles as Markdown and HTML (FOSS)** | signal 5.7 | tags: none | https://capcat.org/
211. **I have a project with ~200k LoC, written with AI codegen. AMA** | signal 5.6 | tags: none | https://news.ycombinator.com/item?id=45351057
212. **If the differentiation is domain and GTM?** | signal 5.5 | tags: none | https://news.ycombinator.com/item?id=47329075
213. **Show HN: Agent File (.af) – A standard file format for serializing AI agents** | signal 5.5 | tags: none | https://github.com/letta-ai/agent-file
214. **Windmemory** | signal 5.5 | tags: none | https://news.ycombinator.com/item?id=42751099
215. **Show HN: Like grep but for natural questions. Mixtral 8x7B – 28 tok/s on 8GB GPU** | signal 5.5 | tags: none | https://github.com/moritztng/fltr
216. **Prompt to make Claude more autonomous in web dev** | signal 5.5 | tags: none | https://news.ycombinator.com/item?id=47379947
217. **Beginner's Guide to MCP (Model Context Protocol)** | signal 5.5 | tags: none | https://news.ycombinator.com/item?id=43758713
218. **Stopped Using Cursor, for Now** | signal 5.5 | tags: none | https://news.ycombinator.com/item?id=44985565
219. **Show HN: Using classic dev books to guide AI agents** | signal 5.5 | tags: none | https://news.ycombinator.com/item?id=47098555
220. **Show HN: Acceptify – AI personas that run user acceptance tests on your product** | signal 5.5 | tags: none | https://acceptify.ai/
221. **AI Power Internal Tools** | signal 5.4 | tags: none | https://news.ycombinator.com/item?id=44494999
222. **Show HN: Prismy – GitHub-Native, AI Localization for Dev and Product Teams** | signal 5.4 | tags: none | https://www.prismy.io
223. **Show HN: No-Code, Private AI Agents – Build and Run Locally** | signal 5.4 | tags: none | https://browseragent.dev
224. **Show HN: AI agent that works autonomously while I'm offline** | signal 5.3 | tags: none | https://hire-your-ai-guide.vercel.app
225. **Show HN: EvenKeel – a free financial planning chatbot** | signal 5.3 | tags: none | https://evenkeel.c6e.me/
226. **Show HN: DiffDeck, a PR review tool with file context and code navigation** | signal 5.3 | tags: none | https://diffdeck.dev/login
227. **Show HN: Inference API that adapts to your SLA and quality constraints** | signal 5.3 | tags: none | https://models.exosphere.host/
228. **Show HN: Why delegation beats memory in AI Agents** | signal 5.2 | tags: none | https://www.getseer.dev/blogs/lessons-dec-2025
229. **Show HN: We built an AI-agent with a state machine instead of a giant prompt** | signal 5.2 | tags: none | https://nomos.dowhile.dev/
230. **Show HN: OQP – A verification protocol for AI agents** | signal 5.2 | tags: none | https://news.ycombinator.com/item?id=47758801
231. **Show HN: Owl and MCP Integration – Plug-and-play agents with external tools** | signal 5.2 | tags: none | https://www.camel-ai.org/blogs/owl-mcp-toolkit-practice
232. **Show HN: Freeze the Model, Train the Harness** | signal 5.2 | tags: none | https://github.com/workofart/harness-training
233. **Show HN: CriteriaBot – A Universal Customizable Classifier** | signal 5.2 | tags: none | https://criteriabot.io/
234. **Ask HN: What eval harness holds up in practice, and what is still missing?** | signal 5.2 | tags: none | https://news.ycombinator.com/item?id=49430207
235. **Show HN: Auditi – open-source LLM tracing and evaluation platform** | signal 5.2 | tags: none | https://github.com/deduu/auditi
236. **Show HN: AI Dev Assistant Framework – Add structure, rules and memory to LLM** | signal 5.2 | tags: none | https://github.com/Fr-e-d/ai-dev-assistant-framework
237. **Show HN: Everdone CodeReview – AI code reviews as a trackable workflow** | signal 5.2 | tags: none | https://everdone.ai/
238. **Show HN: AI Code Review CLI** | signal 5.2 | tags: none | https://github.com/kodustech/cli
239. **Show HN: GPT-reviewer – Simple AI code reviewer for GH Actions** | signal 5.2 | tags: none | https://github.com/vayqerlukashakkarainen/gpt-reviewer
240. **AI-powered Git CLI that generates commit messages automatically** | signal 5.2 | tags: none | https://news.ycombinator.com/item?id=47035076
241. **Show HN: Freeplay – Testing and Evaluation for LLM-powered features** | signal 5.2 | tags: none | https://freeplay.ai/
242. **Show HN: open source framework for building nanoservices** | signal 5.2 | tags: none | https://news.ycombinator.com/item?id=43164465
243. **Show HN: TheFoundry – Easy bootstrapping framework for MultiAgent Systems** | signal 5.1 | tags: none | https://github.com/aavilagallego/TheFoundry
244. **Show HN: LedgerMind – true zero-touch autonomous memory for AI agents** | signal 5.1 | tags: none | https://github.com/sl4m3/ledgermind
245. **Show HN: Mdchat – Markdown-first terminal / CLI tool for LLM collaboration** | signal 5.1 | tags: none | https://www.npmjs.com/package/mdchat
246. **Show HN: WorldBuild Bench repo: testing LLM world coherence with 3D games** | signal 5.1 | tags: none | https://github.com/sebnado/worldbuild-bench
247. **Show HN: CreateMVP.app – First open-source tool to generate MVP specs for LLMs** | signal 5.1 | tags: none | https://createmvps.app/
248. **Show HN: Visual Editor for Cursor** | signal 5.1 | tags: none | https://shuffle.dev/cursor
249. **Show HN: I made an open source Idea to App WebApp** | signal 5.1 | tags: none | https://github.com/rohitg00/CreateMVP
250. **Show HN: Framework to structure LLM dev workflows with Markdown-based protocol** | signal 5.1 | tags: none | https://github.com/Fr-e-d/ai-dev-assistant-framework
251. **My tiny workflow for an AI code review assist** | signal 5.1 | tags: none | https://news.ycombinator.com/item?id=45959846
252. **Show HN: AI code review now available on Azure DevOps** | signal 5.1 | tags: none | https://kodus.io/en/
253. **Show HN: CREV – A Go-based CLI tool for AI code reviews and codebase exports** | signal 5.1 | tags: none | https://news.ycombinator.com/item?id=41757003
254. **Show HN: I released a OS remote agent callable from mobile** | signal 5.0 | tags: none | https://github.com/epavanello/fixodev
255. **Show HN: Arkain – AI-powered Cloud IDE for building real apps from your words** | signal 5.0 | tags: none | https://arkn.ai/qH22w
256. **Show HN: Chaos engineering for LLMs – Making models cross-examine each other** | signal 5.0 | tags: none | https://www.usecouncil.app/
257. **Rate my privacy-first AI ad architecture (patent pending)** | signal 5.0 | tags: none | https://news.ycombinator.com/item?id=47340497
258. **Show HN: Residuum | Agentic AI with continuous context** | signal 5.0 | tags: none | https://github.com/Grizzly-Endeavors/residuum
259. **Ask HN: What are you running for .windsurfrules?** | signal 5.0 | tags: none | https://news.ycombinator.com/item?id=43026575
260. **Show HN: Aidevshield NPM audit for AI coding tool workflows** | signal 5.0 | tags: none | https://github.com/aidevshield/aidevshield
261. **Show HN: AI Resource Manager** | signal 5.0 | tags: none | https://github.com/jomadu/ai-resource-manager
262. **Show HN: Deff – Review AI-generated code changes** | signal 5.0 | tags: none | https://github.com/flamestro/deff
263. **Show HN: Shell script for AI-powered code reviews using local LLMs** | signal 5.0 | tags: none | https://gist.github.com/alwin-augustin-dev/c1caaa30361f7ee320fb9cb957b3b0e9
264. **Show HN: Monitor, audit & alert on AI agent actions and interactions** | signal 5.0 | tags: none | https://pingpulsehq.com
265. **Show HN: Autonomous outbound research and outreach drafts** | signal 5.0 | tags: none | https://www.prospecter.io
266. **Show HN: KitchenAI Open Source LLMops development kit. Notebook to server** | signal 5.0 | tags: none | https://github.com/epuerta9/kitchenai
267. **Ask HN: CI/CD and Hosting for GPU-Based ML Demos** | signal 5.0 | tags: none | https://news.ycombinator.com/item?id=39273121
268. **Show HN: I scraped 200M Shopify products to build a search engine** | signal 2.2 | tags: none | https://www.searchagora.com/#
269. **Why Vertical AI Agents May Replace RPA in Complex Enterprise Workflows** | signal 1.1 | tags: none | https://news.ycombinator.com/item?id=44245754

## github (67)

1. **ratel-ai/ratel** | signal 34.4 | tags: context engineering, retrieval, vector | https://github.com/ratel-ai/ratel
2. **hung12ct/culi** | signal 30.1 | tags: context engineering, claude code | https://github.com/hung12ct/culi
3. **rohithkandula19/Ronin** | signal 27.6 | tags: claude code, coding agent, evals | https://github.com/rohithkandula19/Ronin
4. **skynetcmd/m3-memory** | signal 25.7 | tags: langchain, langgraph, retrieval, vector | https://github.com/skynetcmd/m3-memory
5. **Vuongngu8186/langgraph-langchain-agent-setup** | signal 25.0 | tags: agent workflow, langchain, langgraph | https://github.com/Vuongngu8186/langgraph-langchain-agent-setup
6. **JasonColapietro/suede-creator-skills** | signal 23.6 | tags: claude code, evals | https://github.com/JasonColapietro/suede-creator-skills
7. **Muizzkolapo/agent-actions** | signal 22.8 | tags: context engineering | https://github.com/Muizzkolapo/agent-actions
8. **Ryanaldo34/tacklr** | signal 22.3 | tags: context engineering, retrieval | https://github.com/Ryanaldo34/tacklr
9. **bonigarcia/context-engineering** | signal 21.6 | tags: context engineering | https://github.com/bonigarcia/context-engineering
10. **Adam-S-Daniel/GHA-bench** | signal 21.4 | tags: coding agent, evals, benchmark | https://github.com/Adam-S-Daniel/GHA-bench
11. **ryanportfolio/tracebench** | signal 21.0 | tags: coding agent, evals, benchmark | https://github.com/ryanportfolio/tracebench
12. **IngSquared99/agent-sync** | signal 20.6 | tags: claude code, coding agent | https://github.com/IngSquared99/agent-sync
13. **MrPeppersDev/agent-infrastructure-landscape** | signal 20.3 | tags: langchain, benchmark, vector | https://github.com/MrPeppersDev/agent-infrastructure-landscape
14. **lightsound/solid2-agent-kit** | signal 20.2 | tags: claude code, coding agent | https://github.com/lightsound/solid2-agent-kit
15. **MoeenUddin01/SpecRAG** | signal 20.0 | tags: context engineering, retrieval | https://github.com/MoeenUddin01/SpecRAG
16. **Drlinglong/Remis** | signal 18.4 | tags: context engineering | https://github.com/Drlinglong/Remis
17. **The-AIE/the-gibson** | signal 18.1 | tags: claude code | https://github.com/The-AIE/the-gibson
18. **Ilyat9/Agentalyze** | signal 17.2 | tags: evaluation harness, benchmark | https://github.com/Ilyat9/Agentalyze
19. **tokencanopy/e2a-bench** | signal 17.1 | tags: evaluation harness, benchmark | https://github.com/tokencanopy/e2a-bench
20. **victorzhong0110/da-verify** | signal 17.0 | tags: evaluation harness, benchmark | https://github.com/victorzhong0110/da-verify
21. **raghu619/llm-code-porting-eval** | signal 17.0 | tags: evaluation harness, benchmark | https://github.com/raghu619/llm-code-porting-eval
22. **yusufkaracaburun/ai-kit** | signal 16.9 | tags: claude code | https://github.com/yusufkaracaburun/ai-kit
23. **linny006/agent-eval-harness** | signal 16.1 | tags: coding agent, benchmark | https://github.com/linny006/agent-eval-harness
24. **DaizeDong/skill-smith** | signal 16.1 | tags: claude code, evals | https://github.com/DaizeDong/skill-smith
25. **heygen-com/hyperframes** | signal 16 | tags: none | https://github.com/heygen-com/hyperframes
26. **Rheosoph/flow-like** | signal 16 | tags: none | https://github.com/Rheosoph/flow-like
27. **Claire56/ruhusa** | signal 15.9 | tags: agent workflow | https://github.com/Claire56/ruhusa
28. **khaoss85/agent-crm** | signal 15.3 | tags: claude code | https://github.com/khaoss85/agent-crm
29. **Muvon/octobench** | signal 15.3 | tags: coding agent, benchmark | https://github.com/Muvon/octobench
30. **ankityadav-ui/context-engineering-harness** | signal 15.0 | tags: context engineering | https://github.com/ankityadav-ui/context-engineering-harness
31. **api-evangelist/contextai** | signal 15.0 | tags: agent workflow | https://github.com/api-evangelist/contextai
32. **tbaums/fun-with-friends** | signal 14.1 | tags: claude code | https://github.com/tbaums/fun-with-friends
33. **aryaminus/controlkeel** | signal 12.3 | tags: evals, benchmark | https://github.com/aryaminus/controlkeel
34. **liminalarc/litmus-ai** | signal 12.1 | tags: evaluation harness | https://github.com/liminalarc/litmus-ai
35. **Kyyota-Wang/cloverailab** | signal 12.0 | tags: evaluation harness | https://github.com/Kyyota-Wang/cloverailab
36. **rohithreddybc/FairMedAgent** | signal 12.0 | tags: evaluation harness | https://github.com/rohithreddybc/FairMedAgent
37. **jeffreyrsachs-agentic/agent-eval-harness** | signal 12.0 | tags: evaluation harness | https://github.com/jeffreyrsachs-agentic/agent-eval-harness
38. **wiper44/pharmadoc-extractor** | signal 12.0 | tags: evaluation harness | https://github.com/wiper44/pharmadoc-extractor
39. **Ed-Marcavage/awesome-security-agent-harnesses** | signal 11.8 | tags: evals, benchmark | https://github.com/Ed-Marcavage/awesome-security-agent-harnesses
40. **jameswniu/realtime-voice-agent-turn-taking-stack** | signal 11.0 | tags: evals | https://github.com/jameswniu/realtime-voice-agent-turn-taking-stack
41. **Texarkanine/.cursor-rules** | signal 10.8 | tags: cursor rules | https://github.com/Texarkanine/.cursor-rules
42. **SamuelAlev/control-center** | signal 10.2 | tags: coding agent | https://github.com/SamuelAlev/control-center
43. **ArtJack/verdict** | signal 10.1 | tags: claude code | https://github.com/ArtJack/verdict
44. **imagin5786/ases-ai-scrum-system** | signal 10.0 | tags: claude code | https://github.com/imagin5786/ases-ai-scrum-system
45. **rijojon121/oracle-gym** | signal 10.0 | tags: coding agent | https://github.com/rijojon121/oracle-gym
46. **Akshata4/eval-investigation-skill** | signal 10.0 | tags: claude code | https://github.com/Akshata4/eval-investigation-skill
47. **william-london/ownframework-loop** | signal 10.0 | tags: coding agent | https://github.com/william-london/ownframework-loop
48. **Kruppmagnetichead257/claude-skill-product-optimize** | signal 10.0 | tags: claude code | https://github.com/Kruppmagnetichead257/claude-skill-product-optimize
49. **gollem-dev/gollem** | signal 9.4 | tags: none | https://github.com/gollem-dev/gollem
50. **vishalChoudhary-git/ai-platform** | signal 9.2 | tags: langchain, vector | https://github.com/vishalChoudhary-git/ai-platform
51. **VPSDance/ai-proxy-rules** | signal 8.0 | tags: none | https://github.com/VPSDance/ai-proxy-rules
52. **nori72ny/myAIspecials** | signal 7.5 | tags: none | https://github.com/nori72ny/myAIspecials
53. **zeweihan/aiworkdeck** | signal 7.0 | tags: none | https://github.com/zeweihan/aiworkdeck
54. **Bande-a-Bonnot/Boucle-framework** | signal 6.2 | tags: none | https://github.com/Bande-a-Bonnot/Boucle-framework
55. **Laaaaksh/ai-evals** | signal 6.0 | tags: evals | https://github.com/Laaaaksh/ai-evals
56. **ssheleg/agent-stack** | signal 6.0 | tags: evals | https://github.com/ssheleg/agent-stack
57. **AlbusChen/GameForge-Harness** | signal 5.1 | tags: benchmark | https://github.com/AlbusChen/GameForge-Harness
58. **api-evangelist/poolside** | signal 5.0 | tags: none | https://github.com/api-evangelist/poolside
59. **VNDT1625/TomniHubOs** | signal 5.0 | tags: benchmark | https://github.com/VNDT1625/TomniHubOs
60. **api-evangelist/hyperbrowser** | signal 5.0 | tags: none | https://github.com/api-evangelist/hyperbrowser
61. **sandbaseai/deepseek-harness-handbook** | signal 5.0 | tags: none | https://github.com/sandbaseai/deepseek-harness-handbook
62. **mj9733246-cloud/code-review-expert** | signal 5.0 | tags: benchmark | https://github.com/mj9733246-cloud/code-review-expert
63. **exha1078/agentic-workflow-orchestrator** | signal 5.0 | tags: langgraph | https://github.com/exha1078/agentic-workflow-orchestrator
64. **dcellison/kai** | signal 3.0 | tags: none | https://github.com/dcellison/kai
65. **DonaldMurillo/gofastr** | signal 1.9 | tags: none | https://github.com/DonaldMurillo/gofastr
66. **HIDORAKAI002/ai-workspace-archive** | signal 1.6 | tags: none | https://github.com/HIDORAKAI002/ai-workspace-archive
67. **iliaal/whetstone** | signal 1.6 | tags: none | https://github.com/iliaal/whetstone

## stackoverflow (29)

1. **Claude Code - Looking for guidance on where to start with coding and tools** | signal 11.4 | tags: claude code | https://stackoverflow.com/questions/79927051/claude-code-looking-for-guidance-on-where-to-start-with-coding-and-tools
2. **Best Approach to Evaluate a Graph RAG Pipeline Using Metrics?** | signal 11.4 | tags: rag pipeline, retrieval | https://stackoverflow.com/questions/78881336/best-approach-to-evaluate-a-graph-rag-pipeline-using-metrics
3. **Globally catch exceptions in a WPF application?** | signal 9.4 | tags: none | https://stackoverflow.com/questions/793100/globally-catch-exceptions-in-a-wpf-application
4. **MCPToolConversionError: Failed to get tools from MCP server: 404** | signal 5.3 | tags: langchain | https://stackoverflow.com/questions/79705666/mcptoolconversionerror-failed-to-get-tools-from-mcp-server-404
5. **Langchain, Huggingface: Can't evaluate model with two different inputs** | signal 5.3 | tags: langchain | https://stackoverflow.com/questions/76137512/langchain-huggingface-cant-evaluate-model-with-two-different-inputs
6. **Restrict responses from a language model (LLM) to only information available in a specific document** | signal 5.1 | tags: retrieval | https://stackoverflow.com/questions/78333793/restrict-responses-from-a-language-model-llm-to-only-information-available-in
7. **Is there a framework of many open-source code LLMs for generation?** | signal 5.0 | tags: benchmark | https://stackoverflow.com/questions/78287327/is-there-a-framework-of-many-open-source-code-llms-for-generation
8. **How can I debug an internal error in the .NET Runtime?** | signal 4.5 | tags: none | https://stackoverflow.com/questions/14238657/how-can-i-debug-an-internal-error-in-the-net-runtime
9. **Error - "There is no script engine for file extension .vbs" when using "Git Bash Here" in Windows 7** | signal 3.5 | tags: none | https://stackoverflow.com/questions/17757248/error-there-is-no-script-engine-for-file-extension-vbs-when-using-git-bash
10. **Transparent user session over several sites (single sign-on + single sign-off)** | signal 3.3 | tags: none | https://stackoverflow.com/questions/1043111/transparent-user-session-over-several-sites-single-sign-on-single-sign-off
11. **Current state and solutions for OpenGL over Windows Remote** | signal 2.5 | tags: none | https://stackoverflow.com/questions/51705471/current-state-and-solutions-for-opengl-over-windows-remote
12. **Store Django Log messages in a database?** | signal 2.1 | tags: none | https://stackoverflow.com/questions/11887816/store-django-log-messages-in-a-database
13. **How to validate the origin of a web service invokation** | signal 2.0 | tags: none | https://stackoverflow.com/questions/14023348/how-to-validate-the-origin-of-a-web-service-invokation
14. **Running Keras model for prediction in multiple threads** | signal 1.9 | tags: none | https://stackoverflow.com/questions/43136293/running-keras-model-for-prediction-in-multiple-threads
15. **How to disable context menu on right click/long touch in a kiosk mode of Chrome?** | signal 1.8 | tags: none | https://stackoverflow.com/questions/28222548/how-to-disable-context-menu-on-right-click-long-touch-in-a-kiosk-mode-of-chrome
16. **Mac OS X: Can one process render to another process's window?** | signal 1.8 | tags: none | https://stackoverflow.com/questions/583202/mac-os-x-can-one-process-render-to-another-processs-window
17. **Client-Side CommunicationException while Service works properly** | signal 1.8 | tags: none | https://stackoverflow.com/questions/15429934/client-side-communicationexception-while-service-works-properly
18. **How can I get a password containing a caret (^) passed unchanged as a parameter to a Windows batch file?** | signal 1.8 | tags: none | https://stackoverflow.com/questions/5254460/how-can-i-get-a-password-containing-a-caret-passed-unchanged-as-a-parameter
19. **can I turn off optimization, so in-scope variables from closures aren't "optimized out"** | signal 1.7 | tags: none | https://stackoverflow.com/questions/58861823/can-i-turn-off-optimization-so-in-scope-variables-from-closures-arent-optimiz
20. **Windows: avoid pushing full x86 context on stack** | signal 1.7 | tags: none | https://stackoverflow.com/questions/994555/windows-avoid-pushing-full-x86-context-on-stack
21. **Which StatsD client should I use for a java/grails project?** | signal 1.6 | tags: none | https://stackoverflow.com/questions/17243168/which-statsd-client-should-i-use-for-a-java-grails-project
22. **Set audio endpoint devices application specific (programmatically)** | signal 1.2 | tags: none | https://stackoverflow.com/questions/52973464/set-audio-endpoint-devices-application-specific-programmatically
23. **How can I set the RTS with ioctl() in a Mac plugin?** | signal 1.2 | tags: none | https://stackoverflow.com/questions/14693724/how-can-i-set-the-rts-with-ioctl-in-a-mac-plugin
24. **IntelliJ IDEA: Cannot run program "C:\Program Files\nodejs\npx": CreateProcess error=193 when using MCP server** | signal 1.2 | tags: none | https://stackoverflow.com/questions/79722494/intellij-idea-cannot-run-program-c-program-files-nodejs-npx-createprocess-e
25. **Query OLAP Mondrian (MDX, XMLA) with a Python interface?** | signal 1.2 | tags: none | https://stackoverflow.com/questions/3793215/query-olap-mondrian-mdx-xmla-with-a-python-interface
26. **Windows Aero Rendering Bug** | signal 1.1 | tags: none | https://stackoverflow.com/questions/27450042/windows-aero-rendering-bug
27. **Harvesting the power of highly-parallel computers with python scientific code** | signal 1.1 | tags: none | https://stackoverflow.com/questions/18234484/harvesting-the-power-of-highly-parallel-computers-with-python-scientific-code
28. **searching good embedded & hosting language pair** | signal 1.1 | tags: none | https://stackoverflow.com/questions/7843234/searching-good-embedded-hosting-language-pair
29. **ruamel_yaml.constructor.ConstructorError: could not determine a constructor for the tag 'tag:yaml.org,2002:python/tuple' in "<unicode string>"** | signal 1.0 | tags: none | https://stackoverflow.com/questions/66609054/ruamel-yaml-constructor-constructorerror-could-not-determine-a-constructor-for

## lobsters (75)

1. **Google’s exponential path to climate-wrecking digital bloat** | signal 18.2 | tags: none | https://ketanjoshi.co/2026/07/01/googles-exponential-path-to-climate-wrecking-digital-bloat/
2. **What are you doing this weekend?** | signal 14.8 | tags: none | https://lobste.rs/s/oveaa3/what_are_you_doing_this_weekend
3. **The feature in OxCaml that more languages should steal** | signal 13.9 | tags: none | https://theconsensus.dev/p/2026/06/27/the-feature-in-oxcaml-more-languages-should-steal.html
4. **What are you doing this week?** | signal 13.9 | tags: none | https://lobste.rs/s/lo28ad/what_are_you_doing_this_week
5. **Better Batteries** | signal 13.9 | tags: none | https://matklad.github.io/2026/08/20/better-batteries.html
6. **Why Rocq is better than Lean for program verification** | signal 13.8 | tags: none | https://joomy.korkutblech.com/posts/2026-07-28-why-rocq-is-better.html
7. **The Root of The Root of All Evil** | signal 13.1 | tags: none | https://www.youtube.com/watch?v=hpj6r6CjJf8
8. **What are you doing this weekend?** | signal 13.1 | tags: none | https://lobste.rs/s/ittn74/what_are_you_doing_this_weekend
9. **Self-hosting email the hard way from your own routable IPv4 block up** | signal 12.9 | tags: none | https://anil.recoil.org/notes/recoil-self-hosting-2026
10. **The turbulent AI era is here** | signal 12.4 | tags: none | https://www.gatesnotes.com/work/make-ai-work-for-everyone/reader/a-turbulent-ai-era-and-critical-choices-to-make?WT.mc_id=20260826_ai-overture-2026-med-med
11. **My favorite Computer Science books, and why** | signal 11.9 | tags: none | https://backtracking.github.io/en/2020/02/20/cs-books.html
12. **Are there any decent programs for pdf viewing and editing for Linux that replace Adobe Acrobat?** | signal 11.7 | tags: none | https://lobste.rs/s/kxualw/are_there_any_decent_programs_for_pdf
13. **Just a rumour of a bug is enough to find a security exploit these days** | signal 11.3 | tags: none | https://anil.recoil.org/notes/rumour-is-the-exploit
14. **OCaml 5.5.0 released** | signal 11.3 | tags: none | https://discuss.ocaml.org/t/ocaml-5-5-0-released/18265
15. **Are Latent Reasoning Models Easily Interpretable?** | signal 11.2 | tags: none | https://arxiv.org/abs/2604.04902
16. **Meta Garbage Collection: Using OCaml's GC to GC Rust** | signal 10.4 | tags: none | https://soteria-tools.com/blog/meta-garbage-collection
17. **GUIs should be fully keyboard-driven** | signal 10.2 | tags: none | https://ckardaris.com/blog/2026/08/28/keyboard-driven-guis.html
18. **Two years of vector search at Notion: 10x scale, 1/10th cost** | signal 10.1 | tags: vector | https://www.notion.com/blog/two-years-of-vector-search-at-notion
19. **Any true alternatives to electron JavaScript?** | signal 9.1 | tags: none | https://lobste.rs/s/vji9aj/any_true_alternatives_electron
20. **Taking OCaml and Eio for a spin** | signal 8.9 | tags: none | https://mattjhall.co.uk/posts/taking-ocaml-eio-for-a-spin.html
21. **Parsing the Infamous Japanese Postal CSV (2020)** | signal 8.8 | tags: none | https://www.dampfkraft.com/posuto.html
22. **If I release it, you won’t get the same experience I get** | signal 8.7 | tags: none | https://notes.highlysuspect.agency/cant-release-that.html
23. **why use F# for scripting and automation?** | signal 8.3 | tags: none | https://iev.ee/blog/why-use-fsharp/
24. **Guarded methods in OCaml** | signal 8.1 | tags: none | https://xvw.lol/en/articles/oop-refl.html
25. **A line-by-line translation of the OCaml runtime from C to Rust** | signal 8.1 | tags: none | https://discuss.ocaml.org/t/a-line-by-line-translation-of-the-ocaml-runtime-from-c-to-rust/18247
26. **Inventing ELIZA - How the First Chatbot Shaped the Future of AI** | signal 8.0 | tags: none | https://mitpress.mit.edu/9780262052481/inventing-eliza/
27. **Why ML/OCaml are good for writing compilers (1998)** | signal 8.0 | tags: none | https://flint.cs.yale.edu/cs421/case-for-ml.html
28. **Freedom to Handcraft Software** | signal 7.9 | tags: none | https://rohanrd.mataroa.blog/blog/freedom-to-handcraft-software/
29. **strace-ui, Bonsai_term, and the TUI renaissance** | signal 7.8 | tags: none | https://blog.janestreet.com/strace-ui-bonsai-term-and-the-tui-renaissance/
30. **The 'Breaking' News: The OpenAI–Hugging Face Incident** | signal 7.6 | tags: none | https://youtu.be/87DyyMV0kCY
31. **jj_tui: terminal user interface to jujutsu focused on speed and clarity** | signal 7.5 | tags: none | https://tangled.org/elidowling.com/jj_tui
32. **Robot comment classifier** | signal 7.4 | tags: none | https://entropicthoughts.com/ai-comment-classifier
33. **Introducing Incremental (2015)** | signal 7.4 | tags: none | https://blog.janestreet.com/introducing-incremental/
34. **Unfortunately you sometimes need to do the thing** | signal 7.4 | tags: none | https://griffinberlste.in/blog/do-the-thing/
35. **You Could Have Come Up With Kimi Delta Attention** | signal 7.3 | tags: none | https://blog.doubleword.ai/you-could-have-come-up-with-kimi-delta-attention
36. **Syntax with Purpose in a Programming Language** | signal 7.3 | tags: none | https://www.youtube.com/watch?v=_HLZoeFREFo
37. **Using TypeScript to Obtain One of the Rarest License Plates (2025)** | signal 7.3 | tags: none | https://www.jack.bio/blog/licenseplate
38. **The Limits of AI (1985)** | signal 7.2 | tags: none | https://www.youtube.com/watch?v=ePsQksj99LM
39. **Why we write our own C and C++ inference engines** | signal 7.1 | tags: none | https://localai.io/blog/why-we-write-our-own-engines/
40. **Xavier Leroy on programming, languages and formal verification** | signal 7.0 | tags: none | https://www.youtube.com/watch?v=9Cswiqrq6So
41. **png2jxl: Convert PNG to lossless JPEG XL with byte-for-byte reconstruction of the original PNG** | signal 7.0 | tags: none | https://github.com/JiangJQ2000/png2jxl
42. **bonsai: A library for building dynamic webapps, using Js_of_ocaml** | signal 6.8 | tags: none | https://github.com/janestreet/bonsai
43. **What Rose Petals Teach Us about Induction** | signal 6.7 | tags: none | https://www.oranlooney.com/post/rose-petals/
44. **Languages as designed latent spaces** | signal 6.6 | tags: none | https://blog.jsbarretto.com/post/languages-as-latent-spaces
45. **Flow’s OCaml to Rust Port** | signal 6.6 | tags: none | https://medium.com/flow-type/flows-ocaml-to-rust-port-78b95bcf49e9
46. **Bongard Problems** | signal 6.5 | tags: none | https://matthodges.com/posts/2026-08-19-bongard-problems/
47. **A novel computer Scrabble engine based on probability that performs at championship level (2021)** | signal 6.5 | tags: none | https://upcommons.upc.edu/server/api/core/bitstreams/1339ae43-3d65-4015-8e11-3689e5572b23/content
48. **Data race freedom in OxCaml** | signal 6.5 | tags: none | https://kcsrk.info/ocaml/oxcaml/x-ocaml/blogging/2026/05/07/data-race-freedom-in-oxcaml/
49. **InferenceFS: Never worry about data again! (Again!)** | signal 6.5 | tags: none | https://github.com/philipl/inferencefs/
50. **Tensor is the might** | signal 6.4 | tags: none | https://zserge.com/posts/tensor/
51. **Retrofitting a build system into a compiler** | signal 6.4 | tags: none | https://www.dra27.uk/blog/platform/2025/09/25/building-with-effects.html
52. **social media rabbit holes, clusters, and the relative mixing times of random walks** | signal 6.3 | tags: none | https://notes.hella.cheap/twitter-isnt-a-town-square-its-a-high-school-cafeteria.html
53. **Wrapping GTK4 in 800 lines of Clojure with Jolt** | signal 6.3 | tags: none | https://yogthos.net/posts/2026-08-29-glimmer-ui.html
54. **The Power of Ten: Rules for Safety Critical Coding** | signal 6.3 | tags: none | https://www.youtube.com/watch?v=GRJtYwneG2Q
55. **Problem with concurrent linter fixes** | signal 6.3 | tags: none | https://jfmengels.net/concurrent-linter-fixes/
56. **Super-intelligence or Superstition? Exploring Psychological Factors Influencing Belief in AI Predictions about Personal Behavior** | signal 6.2 | tags: none | https://arxiv.org/abs/2408.06602
57. **Categorization with NLP** | signal 6.2 | tags: none | https://softwaremaniacs.org/blog/2026/07/30/categorization-with-nlp/
58. **Human-like Neural Nets by Catapulting** | signal 6.2 | tags: none | https://gwern.net/llm-catapult
59. **A global workspace in language models** | signal 6.2 | tags: none | https://www.anthropic.com/research/global-workspace
60. **Language integrated LLMs as an OCaml function** | signal 6.2 | tags: none | https://anil.recoil.org/notes/language-integrated-llms
61. **Announcing Pyro Caml: The First Continuous Profiler for OCaml** | signal 6.2 | tags: none | https://semgrep.dev/blog/2026/announcing-pyro-caml-continuous-profiler-ocaml
62. **OCaml Infrastructure: How the opam-repository Works** | signal 6.2 | tags: none | https://ocaml.org/backstage/2025-11-05-how-the-opam-repository-works
63. **O(x)Caml in Space** | signal 6.2 | tags: none | https://gazagnaire.org/blog/2026-05-14-borealis.html
64. **Building textlog without JavaScript** | signal 6.2 | tags: none | https://gist.github.com/stagas/09ad937b493bf8cd3285917279de2488
65. **Performing Digital Surgery to Fix MIDIs for My Hardware (and Then Discovering the Entire Premise of My Post Was Wrong)** | signal 6.2 | tags: none | http://mistys-internet.website/blog/blog/2026/08/25/how-i-fixed-an-mt-32-midi-soundtrack-for-the-hardware-i-use
66. **Sloc Cloc and Code 4.0 (scc) - Finding the files that need the most attention** | signal 6.2 | tags: none | https://boyter.org/posts/sloc-cloc-code-hotspots-finding-files-that-need-attention/
67. **Categorization with NLP** | signal 6.1 | tags: none | https://softwaremaniacs.org/blog/2026/07/30/categorization-with-nlp/en/
68. **Debootstrapping without Archeology: Stacked Implementations in Camlboot** | signal 6.1 | tags: none | https://arxiv.org/abs/2202.09231
69. **Understanding and implementing a simple big unsigned integer library (2020)** | signal 6.1 | tags: none | https://www.sunshine2k.de/articles/coding/biguint/bigunsignedint.html
70. **Programming Paradigms** | signal 6.1 | tags: none | https://amenzwa.github.io/stem/PL/Paradigms/
71. **How to write the perfect function** | signal 6.1 | tags: none | https://www.youtube.com/watch?v=2OMRWPOSw9s
72. **AscendNPU-IR: MLIR for Ascend** | signal 6.0 | tags: none | https://gitcode.com/Ascend/AscendNPU-IR
73. **But what is cross-entropy? | Compression is Intelligence Part 2 - YouTube** | signal 6.0 | tags: none | https://www.youtube.com/watch?v=GlYgs6v2YfU
74. **Why Do Cognitive Scientists Hate LLMs? (2023)** | signal 6.0 | tags: none | https://minihf.com/posts/2023-10-16-hermes-lecture-3-why-do-cognitive-scientists-hate-llms/
75. **Matrix Orthogonalization Improves Memory in Recurrent Models** | signal 6.0 | tags: none | https://ayushtambde.com/blog/matrix-orthogonalization-improves-memory-in-recurrent-models/