#knowledge-graph

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

Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agent-native, Obsidian-compatible second brain — markdown RAG, no vector DB.

ESG knowledge graph + RAG agent. Turn long-form sustainability disclosures into cited answers, extracted entities, and a reviewable graph of evidence.

Open-source AI code reviewer that auto-reviews GitHub PRs LangGraph agents, knowledge graph blast-radius detection, mem0 persistent memory Zero cost, self-hostable.

A full-stack multimodal meeting intelligence system with layered RAG, long-term memory, and skill-based generation.

Local-first memory engine for AI-agent teams — private/team/project ACL, associative recall, federated sync, and a built-in MCP server. One SQLite file, no LLM required. Apache-2.0.

MCP-native knowledge-graph memory for AI agents

AI agent knowledge & long-term memory · MCP server, knowledge graph, BM25 + RRF retrieval · drop-in for Claude Code/ Openclaw/ Cursor / Codex / Hermes

Agentic BI: Semantic and Ontology-driven Data Agent for natural language data Q&A，analysis，insights，and action recommendations.

AI-powered natural-language BI platform: NL→SQL→dashboard plus a power-user SQL editor, root-cause, proactive AI digest, agentic copilot, semantic/trust layer, workspaces + RBAC + row-level security, embedded analytics + white-label, FP&A scenario planning. FastAPI + React.

A brain-inspired cognitive engine in pure C. 14 brain regions, 12 topologies, zero AI framework dependencies. Runs on ARM embedded boards.

Local-first GraphRAG: Milvus hybrid (dense+BM25) + Neo4j local-search + cross-encoder rerank + contextual retrieval. Local-dev runs end-to-end on Ollama with no paid APIs; CI integration tier uses Ollama Cloud + OpenAI embeddings.

Ontology-aware RAG framework — RDF/OWL as the source of truth for LLM agents via MCP

The continuity substrate for AI agents — memory that becomes a mind: a versioned self-model, a cognitive heartbeat, a shared cortex, metacognition & debate, on temporal-graph memory. Apache-2.0, zero-dep core.

A personal memory layer for your AI tools. Intelligent authoring (gap detection, self-enriching graph, session-synthesis loop) + measurably good retrieval (94.9% blind Cov@10, sub-ms latency). Domain-agnostic framework — works for any context you want to track. MCP-native, Claude-Code-first, works with Cursor/Continue/Cline/OpenAI/Gemini.

AI Research Agent 2026 🔍 - Autonomous Deep Web Explorer & Adversarial Synthesis

HermesClaw Zero‑Config Sidecar is a lightweight local vector‑memory engine for Hermes and OpenClaw. It runs as a zero‑config sidecar, providing fast embeddings, persistent memory, and instant retrieval for agents and MCP tools. Built for speed, simplicity, and full local control.

OpenCode memory governance plugin — Knowledge Graph + Hybrid Search + Smart Compaction + Tool Firewall + Stop Gate. 6 MCP tools with slash-command UX. Apache-2.0.

Skein is an agentic AI platform that answers questions by weaving together structured and unstructured data, grounding every response in a knowledge graph, hybrid vector search, and a governed semantic layer. It escalates to humans when unsure, and runs free locally or scales to the cloud.

agent wayfinding. temporal knowledge store in one sqlite file. no neo4j, no cloud, no lock-in.

Memex.ai-Inspired AI Knowledge Base 2026 - Smart Markdown Wiki with Graph Search & Static Publishing

The cognitive operating system that gives AI coding agents memory, structure, and discipline — knowledge graph, Scrumban board, and an enforced engineering loop.

Android personal knowledge graph app - smart exocortex v3.0 (end-side AI + ambient capture + zero-anxiety)

🧠 Long-term memory for AI coding agents — switch tools or models without starting over. Local-first, shared across Claude Code / Codex / opencode via MCP.

Reverse-engineer any Python codebase into an interactive architecture knowledge graph with AI-powered layer detection, community discovery, and living documentation

Go-first, knowledge-graph-grounded agent platform — built on toolnexus + ctx-optimize

Second brain conversacional: grafo de conocimiento temporal con memoria histórica, ingesta remota de documentos vía MCP y multi-usuario aislado. Úsalo desde Claude en https://mybrain.rlz.cl

AI-powered Enterprise Knowledge Platform for Intelligent Decision Making, Agentic AI, and Enterprise Intelligence.

Claude Code skill that maps a project's dependency graph: an Obsidian vault for humans and a compact PROJECT_MAP.md for token-efficient AI navigation, with auto-refresh on source edits.

Persistent, token-efficient memory layer connecting Claude Code to an Obsidian vault — zero-manual cross-session context via /resume, /compress, /dream, /recall + a custom MCP server. Local-first; CoALA-structured tiered memory.

Obsidian-based persistent memory framework for AI coding agents. Set it up with just a single prompt.

Long-term agent memory as an RDF/OWL knowledge graph (AGSMO) with multi-step planning and provenance

AI-native worldbuilding canon: turn natural-language conversations into structured, validated Markdown/YAML and interactive graph views.

engramx's bi-temporal mistakes + structural code-graph as auto-discoverable Claude Code Skills. Catches recurring mistakes before agents repeat them. Apache 2.0, local SQLite, zero cloud.

Give your AI a second brain. Altretta connects your local, encrypted knowledge vault to 70+ AI agents with query-first, cited retrieval and signed provenance.

Your agent does not need memory. It needs a knowledge architecture.

Export a personal Slack channel, enrich + classify it with Claude, and build a Cognee knowledge graph — a showcase for the community pgGraph adapter.

Static code-analysis + knowledge-graph for AI coding agents. Index your codebase once — agents query only what they need. 87–91% token reduction, 12 MCP tools, 13 languages. MCP stdio + HTTP API. Works with Claude Code, Cursor, Antigravity, Codex.

The AI draws. You see. The next session remembers. — an MCP-native live graph workspace where AI pushes structure, findings, and the reasoning behind decisions into a GPU-rendered graph that outlives the session.

Apex-relevance subgraph retrieval for AI agents — feed your LLM the most relevant slice of a knowledge graph, within a token budget.