Havuz

Open source local-first knowledge base maintained by an LLM agent. Implements Andrej Karpathy's LLM Wiki pattern.

Notes, Diagrams, Chat, Calls, Files, Projects, Calendar. One private workspace, everything talks back. Plus an optional agent harness on top

Repo Explainer — turn any GitHub repo into a visual explainer page. Pipeline + 5 live examples.

Community-maintained reference guides and megathreads for Hermes Agent.

A practical guide to DSH plugin quality: ENTRY checks, FLOW journeys, and BOOST practices. Community guide; not a certification or ranking.

Self-hosted semantic memory for AI agents, served over MCP. Persistent sessions, experience scoring, a graveyard for dead ends and skills co

Stop re-explaining your research to your AI agent. Persistent, LLM-maintained wikis that compound over time. Drop PDFs, URLs, YouTube - your

Local-first AI PKM for coding conversations: import Claude Code/Cursor/Codex, distill notes, semantic search, tag graph, MCP memory.

一款跨平台智能笔记 Agent 应用，支持多格式笔记、本地知识库、AI 智能助手、向量语义检索 。

Local LLM-maintained personal wiki, built on Karpathy's LLM-Wiki pattern. Runs on Ollama + Qwen3 + QMD.

Grade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines

A post-retrieval temporal layer for RAG systems — validity filtering, time decay, document kind classification, and hybrid reranking in one

A Repository-Aware, Knowledge-Learning local MCP that understands your codebase in Real Time powered by Hybrid Semantic + Full-Text Engine,

Git-backed wiki engine with MCP server — build knowledge that compounds

Agent-driven SAP/ABAP knowledge base engine that turns S/4HANA custom objects into citable Markdown/Obsidian context for humans and AI agent

Autonomous knowledge base plugin for Claude Code - captures reserch, ideas, and decisions into an interlinked wiki with reserch-on-miss, sem

Local-first memory governance for AI agents: shared, reviewable, auditable memory via SQLite and MCP.

An AI assistant whose memory belongs to you. Local-first Mac app, plain markdown workspace, bring your own model.

Your coding agents remember what you decided — and what you changed. Plain-Markdown memory in Obsidian, shared by Claude Code, Codex and Cur

AI-powered CLI and MCP server for browsing GitHub project documentation (unofficial tool)

Local-first Markdown notes for Linux, Windows and Android. Plain .md folders, optional end-to-end encrypted sync to a server you run yoursel

开源知识站脚手架：图文/视频、会员订阅与单课购买，面向 Coding Agent 一键搭建

Local RAG layer and optimizer for your Markdown knowledge base. CLI + MCP server: grounded answers for any AI client, stale-note detection,

Fastest way to scaffold your LLM powered personal knowledge base - Obsidian, Claude Code, qmd, Github

An AI native macOS reader. Built for professional reader.

A compounding knowledge base maintained by LLM agents — inspired by Karpathy's LLM Wiki pattern

Caelune (凯露恩) — Local-first retrieval for private Markdown, PDF, and Tika documents, with a Windows desktop app and read-only MCP server.｜本地

First general Wiki MCP following google's Open Knowledge Format. Let your agent to use, manage, maintain, and health check the wiki (knowled

Public, source-cited Fable 5, Mythos, Claude Code, and agent-operations second brain. Not affiliated with Anthropic.

AgentMill - Enterprise-Grade AI Agent Platform & Agent Factory for Building Custom Digital Employees

微信文章归档工具 - 本地Markdown保存 ｜ Archive WeChat Official Account articles as local Markdown for Obsidian, Logseq, and personal knowledge bases.

Memory database for AI agents — stores typed memories (facts, preferences, events, entities, relations) with provenance, confidence, and bi-

Markdown-first work-memory protocol for existing agents, with maintained knowledge, candidate notes, evals, and an example KB.

Turn your ~/.claude history into a shareable Quartz knowledge base.

A free, living knowledge base on vibe coding — building SaaS fast with AI agents, local AI, and agentic workflows.

A schema standard for LLM-compiled personal knowledge bases. AGENTS.md spec, templates, worked example, spaced repetition learning layer.

Multilingual source-grounded research workspace with agentic RAG, cited chat, podcasts, PowerPoint, and video.

Self-hosted team docs where every save is a Git commit: WYSIWYG editor, built-in MCP server for AI agents, whitelabel branding. Source-avail

Your markdown vault, compiled into a 6-persona MCP team for Claude Code, Codex, OpenCode, and Gemini CLI. Headless-first. Cites, doesn't gue

Unofficial source-linked AWS best practices for every AWS service, organized by Well-Architected pillar for Claude Code, OpenAI Codex, and A

Install once, talk to your agent. ThinkWiki turns documents and notes into a local Markdown wiki with inbox review, content knowledge graph,

Open-source customer support platform: ticketing, help center, live chat widget and grounded AI — one deploy, many brands. Self-hosted alter

Generic markdown vault MCP with hybrid search

This is a mathematical discovery engine, which searches new mathematics applying techniques to existing results

WeChat & Web to Obsidian Sync Engine (Cloudflare Workers + Obsidian Plugin)

🚀 多Agent协作智能知识库系统 — 五层可编排Agent架构 + RAG全链路 + 统一ToolRegistry，Spring Boot + FastAPI + React，核心亮点是 五层可编排 Agent 架构——Interface、Orchestrator、Tool、M

A local-first studio for roleplay and long-form writing: a roleplay chat with a living Narrative State, a Worldbuild that keeps your canon,

Claude Code plugin for building LLM-maintained Obsidian wikis from raw research — compile, query, lint, and evolve your personal knowledge b

A research lab's Claude Code setup: 67 skills, hooks and rules, plus a knowledge base in plain git — GitHub for ideas. A question goes in, k

Standalone MCP server for Obsidian vaults — hybrid search, structured memory, task management, files, OAuth 2.1. Run locally, self-host, or