4,052 tools found
El Yayster is a single-file Emacs package that lets a local LLM read your open buffers and act via gated Emacs Lisp, prompting before every mutation.
Promptfoo workflow testing security weakness classification using Abliteration Large V2 model with configurable reasoning settings.
engrim is a local-first SQLite memory store that lets you switch between Claude Code, Cursor, Antigravity, and Windsurf without losing project decisions.
MathKernel is an evidence-aware math engine (Python library or MCP server) tagging every result with a distinct trust level - exact, symbolic, or formal.
Game Sensitivity Coach discovers your mouse settings, carries them into another game, and reviews recorded gameplay for evidence-based tuning.
Pigeon issues signed, narrowed Passes for sub-agents instead of copying the parent's API key, so delegated authority is provably bounded.
OKF Agent Memory is a git-native, MIT-licensed persistent memory layer for AI agents, stored as plain Markdown with BM25 search and zero API cost.
Fixes grammar/typo mistakes in an email draft without touching voice, and only cleans tracking links when explicitly asked.
Query Entropy Box's public embodied-AI knowledge graph for grounded task chains, capabilities, assets, and source-backed evidence - not robot control.
A Laravel dev workflow: trace to root cause before fixing, build features in the app's existing shape, then verify proportionately.
Judgement layer over OrcaReplay's MCP server: tells an agent to read a recorded run instead of guessing what already happened.
AURA is a production-tested SRE agent platform, run in your own security boundary, that investigates incidents across your cloud and observability tools.
