Agent Context, Memory & Knowledge

Open-source context database for AI agents that unifies agent memory, knowledge RAG, and skills as a virtual filesystem. AGPL 3.0 licensed.

Local-first, source-grounded project memory for coding agents with bounded MCP retrieval, citations and provenance, atomic changesets, and optional document and code knowledge graphs. Apache 2.0 licensed.

Agent skills and open-format tooling for Obsidian vaults, Markdown, Bases, and JSON Canvas compatible with Claude Code, Codex, and OpenCode. MIT licensed.

MIT-licensed Obsidian and Claude Code integration that organizes Markdown vaults with local indexing and links.

Pipeline to distill books, videos, and podcasts into structured, executable agent skills using verification and testing workflows. MIT licensed.

Git-backed platform for managing and sharing skills, tools, and context across AI agents through a remote MCP server. Apache 2.0 licensed.

Local pre-indexed code knowledge graph for coding agents to reduce token usage and redundant tool calls across Claude, Codex, and other agents.

Local source-backed AI knowledge base and LLM wiki for coding agents, with Markdown pages, hybrid retrieval, knowledge graphs, CLI workflows, and MCP integrations. Apache 2.0 licensed.

Local-first code knowledge graph and code intelligence engine built in Golang with multi-repository support and real-time graph actualisation. Built for AI coding agents aiming to expose only the needed information, reducing token usage by up to 50x. Works natively with Claude, Codex, Hermes, and other agents.

AI coding assistant skill that indexes codebases, databases, and documents into a queryable knowledge graph for coding agents. MIT licensed.

Open-source workspace intelligence CLI that models polyglot workspaces, builds proof-backed knowledge graphs, runs health and release gates, and generates bounded context for AI coding agents. MIT licensed.

Context compression proxy for tool outputs, logs, and RAG chunks, reducing token pressure while preserving intent for AI agents.

Self-hosted Rust proxy, MCP server, CLI, and library that compresses LLM prompts, tool outputs, and replies to cut token usage, quality-gated so it never raises your bill. MPL-2.0 licensed.

Security-first, self-hosted email knowledge system that synchronizes IMAP mailboxes into user-owned PostgreSQL for lexical and semantic retrieval, cited answers, local-model operation, and MCP access. AGPL-3.0 licensed.

High-performance, benchmarked AI memory system for persistent recall and retrieval in long-horizon autonomous workflows.

Framework-agnostic, local-first memory lifecycle for AI agents with a Rust CLI, SQLite/FTS recall, redaction, forgetting, audit checks, consolidation, and agent-skill guidance. MIT licensed.

Memory layer over the session transcripts coding agents already write to disk — Claude Code, Codex, Cursor, opencode, Zed and more — including sessions from before it was installed; local BM25 recall over them with no LLM or embeddings, MCP tools, and credentials redacted at index time. MIT licensed.

Persistent agent-memory system that captures session observations, summarizes them, and retrieves relevant context across coding-agent sessions. Apache-2.0 licensed.

High-performance C-based codebase intelligence engine and MCP server that indexes repositories into local type-resolved knowledge graphs. MIT licensed.

CLI tool that distills technical books, documents, and reference materials into structured, on-demand agent skills. MIT licensed.

Native GNOME desktop app (GTK 4, Libadwaita) implementing the Karpathy LLM Wiki pattern: ingests documents into an Obsidian-compatible Markdown wiki with source provenance, works offline or with Ollama and OpenAI-compatible endpoints, and exposes the wiki to coding agents through an MCP server. MIT licensed.

Rust-native long-term memory server and MCP client for agent coding CLIs, featuring Karpathy-style LLM wiki compilation, FTS5 recall, and cross-agent session handoffs. MIT licensed.

Open-source database and workspace that gives AI agents structured data, durable knowledge, docs, skills, and apps through MCP, OpenAPI, CLI, and coding-agent skills; material writes can remain reviewable ChangeRequests before becoming canonical. MIT licensed.

Local-first archive and semantic search for AI conversation histories across multiple providers, with local embeddings, LanceDB storage, complete thread retrieval, HTTP and CLI access, and a stdio MCP server.