Havuz

AI research agent for nuclear physics: 23 expert skills that install, run, and verify open-source codes (FRESCO, TALYS, SMASH, ...) plus a 6

Installable DeepSeek Harness knowledge base plugin

Karpathy's LLM Wiki, built from your Claude Code sessions: a folder of markdown you own, Obsidian-native when you want it. Keeps what you de

Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agen

本地优先的文献知识库 RAG(DeepSeek Harness 插件):混合检索正文与图注,把模糊记忆定位到具体段落与图表,DOI 一键直达原文。Local-first literature RAG for DSH — turn a fuzzy memory into an ex

Whiteboards and documents that nest inside each other. An open-source Notion/Excalidraw hybrid with real-time collaboration.

301 open-source coding agent skills across 22 domains — methodology, judgment & gotchas packaged as Claude Agent Skills for the Asgard AI Pl

A local-first workspace for documents, tasks and meetings on macOS — nested spaces, typed properties, relations and saved views, with transc

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

AKB — Agent Knowledgebase. Organizational memory for AI agents: vault-scoped docs / tables / files unified by URI graph, served over MCP.

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

Turn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, s

An extension of Karpathy's LLM Wiki pattern: atom layer, topic-branches, two-layer Lint. Distilled from running the pattern end-to-end.

Terminal-first, knowledge-grounded multi-agent software delivery pipeline: scope requirements, implement changes, run tests, and gate pull r

A lightweight CPU only memory approach with ranked retrieval. Simple, yet effective.

Local-first AI knowledge app and Agent Skill with evidence-backed Wiki, an interactive knowledge universe, Viki Q&A, and shareable knowledge

Memoriki - LLM Wiki + MemPalace. Personal knowledge base with real memory.

Turn isolated Claude sessions into a continuous working relationship

Modular Context | Karpathy LLM Knowledge Base + Gmail & G-Cal — multi-account MCP server for Claude Code, encrypted local-first

面向招投标场景的本地化 RAG 标书解析、资质匹配与红线提醒助手

Turn your markdown vault into a compounding knowledge wiki (Karpathy inspired). Six agent skills - knowledge grows with every conversation.

LLM-managed personal knowledge base. Auto-extracts from git repos, Claude Code sessions (via ccrider FTS5), and iMessage bookmarks. Cross-pr

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

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

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.

Claude Code skill for building persistent, interlinked knowledge bases from source documents. Knowledge is compiled once and kept current —

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

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)

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

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

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

Generic markdown vault MCP with hybrid search

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

跳蛛先生的 AIGC 创作方法论公开知识库，沉淀 AI 图像、视频、音乐、角色一致性、复盘机制与人机协作工作流中的可复用 insight。

Governance-grade, OKF-compatible knowledge-base format with a single-writer MCP server and CLI. Pre-release.

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

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。

Template for creating a long-term sync hub that checks your company's data sources into Git as plain Markdown, giving AI coding agents durab

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-first AI knowledge base for PDFs, Office docs, web clips and Markdown notes — ask your whole library and get citations that jump back

Self-hosted AI memory: a private Markdown knowledge base, MCP server, and operations dashboard with verifiable source citations. By OBELYTH.

Codex skill for building an Obsidian + ChatGPT sidebar workflow with vault-scoped MCP tools and ngrok remote access

An self-hosted AI platform that talks to your customers for you: it answers in messengers, email and web chat, and hands your team only the

Free and open-source production-grade RAG platform that converts documents into conversational AI assistants. Enable private deployment for

A cross-linked Obsidian knowledge brain for writing correct, idiomatic, current Rust (edition 2024). 584 linked notes plus a Rust agent.

Wenshu（文枢）— 面向人文社科研究的 AI 知识处理工作流：本地知识库 / RAG / 中文引文 / 理论谱系。AI knowledge workflow for humanities & social sciences: local knowledge base, RAG