Havuz

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

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

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

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

Self-hosted AI workbench for a company LAN. One command on a Windows server sets up login, roster, model gateway, company disk and knowledge

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

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

A minimal CLAUDE.md template that turns any LLM CLI into a personal knowledge base. Drop in one file, start ingesting articles. Karpathy's L

目标打造全球跨境卖家的开源 AI 全能运营助手：基于 LangGraph、RAG 与多智能体协作，连接 Amazon、独立站、ERP 和广告平台，覆盖市场洞察、智能选品、竞品监控、关键词研究、Listing 优化、广告投放、销量预测、库存补货、利润核算、客服分析、合规风控、内容营

Self-hosted IT documentation, asset management, and data intelligence platform built around a relational knowledge model.

AI 原生多租户 SaaS 开发框架 — FastAPI + Vue 3 + PostgreSQL，内置 AI Agent、RAG、插件系统、RBAC、异步任务等核心能力，助力快速构建行业 SaaS 应用。

Binders for macOS: local-first dictation, meeting notes and memory, with an MCP server for your AI tools. Private by design, free, open sour

Local document knowledge base for DeepSeek Harness: library_add/remove/list, hybrid semantic+keyword library_search with diversity re-rankin

Local-first memory context for Pi coding agents.

Athena RAG Intelligence – AI-powered document intelligence platform with RAG, semantic search, source citations, voice assistant, analytics,

Installable DeepSeek Harness knowledge base plugin

A personal second brain for Claude Code: a Markdown vault compiled into cited wiki pages, with a deterministic Python engine.

韫玉 · 本地优先的知识库与学习工作台（Tauri 2 + React）

Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge

421 movements, 274 hand-drawn styles, 100 director/film styles and 157 camera-move recipes - each decomposed into 7 swappable AI prompt laye

Evidence-aware personal knowledge system for AI agents: schema-governed Obsidian vault, proposal-gated MCP gateway, and the skills around it

The local-first AI knowledge workspace — an infinite canvas for research, learning, and creation (Tauri 2 + Vue 3)

Local-first personal knowledge base CLI — hybrid FTS + pgvector search, a GraphRAG entity graph, and LLM enrichment over your notes, transcr

倪海厦中医知识数据库 - 3,867条记录，涵盖中药/方剂/医案/经典/针灸/天纪 | Ni Haixia TCM knowledge base: 3,867 structured SQLite records + 2,987 OCR lecture transcripts, R

Low-power, offline retrieval (RAG) for disaster and infrastructure-failure guidance.

shared-memory-vault, birden fazla agent’in bulutla senkronize edilen Markdown dosyaları üzerinden ortak hafıza kullanması için kurallar ve otomasyon script’leri sunuyor.

Neden yükseliyor · 23 günlük bir repoda 96 yıldız dikkat çekiyor; agent hafızası ve ortak bilgi tabanı ihtiyacına doğrudan hitap etmesi ilgi görmüş olabilir. Ancak son 28 günde 1 commit ve 1 farklı yazar var; mevcut veriler geliştirme ivmesini veya topluluk katkısını doğrulamıyor.

⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero, Obsidian, Apple Notes supported now, loca

Hybrid RAG system combining vector search, knowledge graph (LightRAG), and cross-encoder reranking — with Docling document parsing, visual i

Your First LLM-Wiki Conversation Knowledge Base

LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM Wiki pattern — implemented an

Turn your Claude Code session history into a searchable local knowledge base — 13 MCP tools, pure stdlib, nothing leaves your machine

Local-first Markdown workspace and AI game design assistant for game development teams

Pharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP ex

Harness engineering applied to knowledge production: a self-evolving multi-agent newsroom that turns your documents into a cross-linked mark

Self-hosted AI customer-support platform — per-KB RAG on Qdrant, 13 LLM providers, SSE streaming, embeddable chat widget. FastAPI + Vite + S

Persistent memory plugin for OpenCode. Obsidian-style knowledge base that survives across sessions

Forward videos from IM to transcript, Markdown, and your knowledge base — with raw and skill-updated outputs.

A hyper-relational knowledge base with content-addressable storage, built on Prolog, SQLite, and C.

Second yourself. One agent that remembers you, with many hands to act for you: a multi-agent harness (Claude Code, with Codex helpers), a se

Git-backed shared memory for AI agent fleets: searchable knowledge base, incident and task tracking, every write versioned and attributed. C

Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown kno

Self-hosted AI Agent Memory + Code Intelligence Platform — one MCP endpoint for persistent memory, AST-aware code search, shared knowledge,

CLI tool for LLM agents to build and maintain personal knowledge bases

Shared memory for AI coding tools: hybrid search, cited Q&A, harness memory discovery and a built-in Web console. Local index, MCP + HTTP.

知归是一个面向个人使用的 AI 知识归档工具。把内容链接（微信公众号、稀土掘金、GitHub、小红书、抖音、B站）发送给飞书机器人，知归会自动完成内容提取、AI 分类与总结，并将结果沉淀到飞书多维表格中。Send WeChat Article / Douyin / Xiaohon

面向 PRD、业务规则、SOP、流程文档和产品截图的证据型 RAG 知识库。

Multi-agent engineering framework: evidence packs, runtime validation, task decomposition, cross-window worker execution, and CI artifact ve

Turn your team's AI coding sessions, GitHub code, and docs into one shared, searchable memory — a self-hosted git truth store you query righ

Installable agent skills for browser automation, local knowledge, skill management, external CLI workflows, and session handoffs.

A git template for building your own LLM-powered personal wiki. Training period, metadata standard, lint system included. Clone and go.