Mustel
Non-AI static analysis, built for AI coding agents
What it does
Mustel is a local-first static analysis layer built specifically for AI coding agents like Cursor, Claude Code, and Windsurf. It runs Ruff, Bandit, and pip-audit under the hood, then compresses the output into a single sub-200-char agent_prompt field agents can act on directly - no wasted turns re-reading files or parsing raw linter noise. Dev Mode scans in under 30ms via mtime+size caching; Audit Mode runs deeper checks in CI. Auto-registers as an MCP server across major editors.
Mustel is a fully open-source, MIT-licensed Python CLI linter and MCP server on PyPI that prevents AI coding agents (Cursor, Claude Code, Windsurf) from hallucinating or missing deterministic bugs.
Mustel is a local, non-AI static analysis layer that intercepts editor save loops. It formats and compresses code diagnostics into ultra-short prompts to guide coding agents without context bloat. Standard coding agents transfer thousands of lines of raw, duplicate linter logs on every save loop. These verbose payloads clog context windows, increase latency, and inflate your API bills. Out-of-the-box rule configurations covering 26 core packages, cloud SDKs, web frameworks, and system utilities. Mustel executes linter checks, deduplicates overlap reports, and runs custom YAML pattern checks locally. It formats all issues and creates a sub-200 character summary to instruct AI agents clearly.…from mustel.vercel.app
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com