Harness engineering applied to knowledge production: a self-evolving multi-agent newsroom that turns your documents into a cross-linked markdown wiki. A "reground" loop pulls published pages back in before they go stale — writer ≠ reviewer, local-first, a structured alternative to RAG.
$ git clone https://github.com/alfadur7/llm-wiki-newsroom.git▲ +2 ★ this week
⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero, Obsidian, Apple Notes supported now, local docs on the road). Native C++ search core: BM25 + passage ranking in ~15 ms. MCP server for Claude, Cursor, Cline & any MCP client.
Terminal-first, knowledge-grounded multi-agent software delivery pipeline: scope requirements, implement changes, run tests, and gate pull requests with deterministic QA and ensemble code review.
Claude Code / Codex 共用的长期记忆 MCP：本地 Markdown/Obsidian 存储，跨工具记住你的项目与偏好｜Local-first shared memory MCP for Claude Code & Codex
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.
A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.
Data from GitHub · snapshot Nov 13, 2026