Added Oct 28 as particle/particle-1, Particle AI's model is tuned to finish software tasks with shorter reasoning and fewer trial-and-repair rounds, with a 1M-token context, tool use and image input at $0.125/$0.50 per million tokens. npx vercel ai-gateway setup points Claude Code, Codex or Cursor at it, though the token-saving claims are Particle's own (model page).
Shown on HN Nov 1 under MIT, npx amidumb reads /.claude/projects and /.codex/sessions and computes a fixed, local score across specification, steering, verification, discipline and leverage, then has your own claude or codex write a roast and three habits to paste into CLAUDE.md or AGENTS.md . The roast sends about 150 redacted, trimmed prompts to your CLI ( no roast sends nothing), and the author says the rubric is better at the extremes than in the middle…
Shown on HN Nov 1 under MIT/Apache 2.0, parts are plain JSON step programs, and claude mcp add geop geop mcp (or the Codex equivalent) lets your agent sketch, extrude, fillet, inspect and export STEP or STL through the same editor as the browser app. The in browser assistant sends your messages and program to Geop's server and Anthropic, while the CLI and MCP route run locally (Show HN)…
Shown on HN Nov 1, the test installed 67 npm MCP servers in a sandbox with no internet route and no real credentials, called no tools, and found 7 looked up undeclared domains at startup while 24 offered tools their README doesn't name (2 did both). It's one run that only reads the shipped README, so the author says it isn't a ranking, and 29 finding pages stay unpublished until hand checked…
Shown on HN this week, the Rust daemon keeps a live mirror of each screen's accessibility tree and frames, with no APK or XCTest runner needed on Android or the Simulator, and its CLI copies agent browser's command grammar while mobile agent mcp serves the same tools to Claude Code, Codex or Cursor. It's an experimental pre release, built from source only (macOS for everything, Linux for Android), and leans on private Apple and hidden Android APIs (Show HN)…
Shown on HN Nov 1 under MIT, the Docker stack polls OpenProject 17 work packages, dispatches the pi coding agent as frontend, backend or designer to open a PR, then hands it to a reviewer agent that merges it or kicks it back for fixes, with the engine (never the agents) doing every status change. It needs one time OpenProject admin setup, a GitHub token that can push and merge, and one model provider key such as OpenRouter or a local llama.cpp (Show HN)…
Spotted something we missed? Start a thread.