Havuz

Connect your company's data, let an agent draft an ontology over it, and load it into HelixDB as one graph you can explore and ask questions

git diff for knowledge graphs: semantic, visual diff and review for RDF, OBO and JSON graphs

Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.

本地优先的全栈 AI 创作工作站：AI对话 · AI漫画 · 漫剧创作 · 写作台 · 知识学习五大模块；vLLM / llama.cpp / Transformers 多引擎本地推理，显存智能调度、舱壁隔离自愈、仅供学习使用，欢迎交流指正。（最新进度（除插件系统）受到协议限制，

Read it. See it. Get it. Built at GDG AI Hack Milan 2026 for "Learn Different" track.

Not another ChatGPT wrapper. This is a local-first tool that turns your notes, web pages, PDFs and audio/video into a personal knowledge gra

OnCo: total information dominance on cancer. A public, cited knowledge graph of oncology with a website, JSON API, MCP server and CLI: one p

TYSA (Teach Yourself Anything): an learning harness that finds where your understanding ends and teaches from there. Electron app built on M

Intent-driven workflow orchestration for multi-agent AI development — adaptive lifecycle engine, self-reinforcing knowledge graph, and visua

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

Turn long ChatGPT conversations into visual maps — jump back to any message, organize topics, and export your knowledge.

Evidence-backed AI industry intelligence — trends, source updates, daily data refreshes, and weekly decision briefs.

AI assistant in Telegram that remembers everything and helps you run your life. Self-hosted in one command.

基于LangChain、LangGraph、FastAPI和React的RAG项目，主分支为基于知识图谱的知识管理平台，base-rag分支为完整的向量RAG项目供学习使用

distill any book down to its spine

墨台 VibeHolding：AI 时代全链路基建选型知识库（A–V 图廓 · 关系边 · 方案）+ 桌面/Web 客户端。本地优先，内容可 PR。

Buddhist Digital Text Platform — 10,500+ texts, 613 sources, trilingual cross-canon, AI Q&A (RAG), knowledge graph, full-text search

Local-first Memory OS for personal AI assistants with L0-L3 memory, Wiki++ knowledge, skill routing, and TokenLess context compression.

Self-hosted, traceable document-to-knowledge workspace with deterministic workflows, optional AI, search, RAG, and an editable knowledge gra

Local-first agent workspace for knowledge, tasks, documents and verifiable workflows · Локальная агентная система для знаний, задач и провер

VedAnvaya — an evidence-led digital atlas for reading, exploring, hearing, questioning, and navigating connections across the Vedic corpus.

Self-hosted shared memory for AI agents: vaults of people, facts and decisions your agents recall over MCP or REST, with semantic, keyword a

CodeWiki is a knowledge platform that analyzes repositories into AST graphs, builds GraphRAG indexes, and generates source-grounded develope

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

Open-source, real-time collaborative AI canvas - notes, mini-apps, and agents on one infinite board.

High-performance Knowledge Graph engine for AI, LLMs, and GraphRAG — built for the next generation of intelligent applications.

The context spine that 10x's every AI coding session. Live in 8 IDEs (Claude Code, Cursor, Cline, Continue, Aider, Codex, Windsurf, Zed) via

English translation of MiroFish (github.com/666ghj/MiroFish) - A concise and universal swarm intelligence engine for predicting everything.

Zero-config entity resolution feeding a durable identity layer: messy records from any source become stable golden entities, a Customer 360

High-performance Knowledge Graph engine for AI, LLMs, and GraphRAG — built for the next generation of intelligent applications.

玄霖超脑 · 无量网络 v4 重构版— 66 模块6通道 AI 认知神经系统 · 装一次，你所有的 AI 工具从此共享一个永远不失忆的大脑。跨会话记忆 · 多 Agent 互通 · 自动代码审查 · 零配置

Local-first, spec-driven SDLC workbench with governance gates, knowledge graphs, and MCP for AI coding agents.

Harness as code — the Terraform for AI agents. Define your agent team AND its memory once, deploy to Claude Code, OpenClaw, Cursor, Codex, G

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

Open-source, web-based knowledge base — Obsidian-style linked markdown notes, backlinks and a GPU-rendered knowledge graph. FastAPI + Next.j

🌿 StoryMoss (草苔) — AI导演式小说创作系统。Tauri+Rust驱动的桌面写作软件，集成知识图谱、伏笔追踪、StyleDNA风格引擎、协同编辑、7阶段全自动创作工作流。让AI成为你的创作搭档，越写越懂你。

Personal Knowledge OS — Capture → Distill → Compile → Serve. Self-hosted knowledge data platform with AI agents, Telegram bot, and REST API.

Convert Hermes / OpenClaw agent memory (JSONL sessions, MEMORY.md) to markdown for gBrain ingest

Open source brain viewer and project management for AI agents. Give your AI a brain.

Multi-agent AI/CS learning assistant: LangGraph routing, LightRAG graph RAG, three-layer memory, learning roadmaps. FastAPI + React.

Local-first creative intelligence for mobile-game UA teams — decompose creatives into structure, link them into a graph, turn every human ru

Claude Code plugin — code quality hooks, knowledge graph, impact-aware reviews, decomposition enforcement. Babysitter for your AI's code qua

Interactive Wikipedia knowledge graph - crawl topics, visualize connections, and explore unexpected paths.

An Agent with Semantic Memory. This is an experiment for Neuro-Symbolic AI

A local MCP server for cross-repository semantic code intelligence in TypeScript and Go, backed by a persistent LadybugDB graph.

CapsuleCraft - zero-database, pure-MIME multimodal workspace and personal knowledge engine. Every note is an RFC 5322 .eml file. Native desk

Open-source bitemporal knowledge graph — long-term memory for AI agents. Hybrid retrieval, conflict-aware ingest, GDPR forget. REST + native

Cognitive engine for AI agents — semantic memory, observations, embeddings, dream consolidation. Cloud Run service + MCP tools.

A local, open-source alternative to NotebookLM. Chat with your documents using any LLM.

Evidence-first, self-hosted OSINT workspace for public-source collection, grounded AI research, relationship intelligence, monitoring, and v