
Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

Local MCP server that builds a code knowledge graph for AI coding agents
Runs locally
Code knowledge graph that gives coding assistants shared, source-linked context

Memory for coding agents that saves decisions and fixes, with optional hosted sync

Open-source RAG engine with a document pipeline, hybrid search and visual agent workflows

Local search engine for AI agents with cited answers over your code and docs
Runs locally
Agent meta-harness that adds swarms, memory and MCP tools to Claude Code and Codex

Long-term memory layer for AI agents that stores typed facts and consolidates beliefs

Local-first, privacy-focused note-taking app with block references and encrypted sync

Open-source book and 109 experiments explaining AI agent design and engineering

Distributed SQL database with vector search and transactions for AI workloads

Vectorless RAG engine that finds answers by reasoning over a document's page tree

Open-source knowledge framework for RAG Q&A, agent tasks and auto-built wikis

Open-source Python framework for building production RAG pipelines and agents

Open-source shared memory hub that gives agent teams common conversation and code memory

MCP server for searching the Claude Code Ultimate Guide from any MCP client
Runs locally
Open-source enterprise agent platform with RAG knowledge bases and workflows

Agent skill that distils a person's materials into a reusable profile for AI agents

Platform for stateful agents that learn from experience, with an open-source CLI harness

Tutorial generator that turns a GitHub repository into a beginner guide

Self-evolving engine that lets agents share and reuse learned capabilities

Local-first long-term memory layer for AI agents, served over MCP
Not checked yet
Zotero plugin with a research agent for reading papers, citing sources and saving notes

Self-hosted chat workspace with knowledge bases and MCP tools

Use when exploring unfamiliar code, mapping architecture, finding symbols or relationships, tracing callers, callees, data flow or dependenc

Use before reporting any cosine similarity computed over embeddings or transformer hidden states, whether the agent computed the vectors or

Merges mature lessons from a domain memory file into its instruction file

A persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured knowledge graph

Build production RAG pipelines and persistent agent memory using Pinecone as the vector database backend

Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.

Guides Qdrant deployment selection