MCP servers and skills: search, filter by where they run, and compare.
A reading path for CPU performance engineering, from one instruction to production inference. Primary sources only, with a runnable benchmark for every section.
PythonMIT★ 1.2kNo key
One shared brain for every AI agent in your terminal. Local-first and verbatim, on your PC; 88.8% on LongMemEval with zero model calls at write time.
PythonAGPL-3.0★ 4Few starsNo key
Zit: a git extension that lets developers and coding agents change one repository at the same time without stepping on each other's toes, and it's kind to your SSD.
SkillGPL-2.0★ 9No key
Agentic ETL for Python. Declare pipelines in YAML where each step is a connector, a function or an LLM agent. Read CSV, Excel, PDF, Word, email, HTTP, S3 and SQL, validate outputs with schemas, and ge
PythonMIT★ 1Few starsNo key
PythonMIT★ 1Few starsNo key
Node.jsMITFew starsNo key
Local-first agent harness (Windows + Ollama) for 2–9B models. Same 2B model: 0.017 → 0.821 across four agent harnesses — 48×. 288-cell benchmark, every cell public. One-click zero-outbound mode. 本地优先，
SkillApache-2.0★ 21No key
Who stands behind it
