100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB backend and advanced agentic code analysis tools through MCP for efficient code agent context management

Context-Engine MCP - Agentic Context Compression Suite

The IM for agents. Shared Agent Context & Memory, supervised execution, and cross-agent audit across AI providers.

Skill librarian MCP server — every installed skill costs tokens; the librarian keeps your whole collection out of agent context. Agents ask, get the few right skills for the task, and their outcomes curate the collection. Fully local: Ollama + SQLite + optional Apple Intelligence.

A memory layer for AI Agents

Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations

Persistent memory for AI coding agents

LeanKG: Stop Burning Tokens. Start Coding Lean.

Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.

Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain, CrewAI & OpenClaw integrations.

Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.

Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agent harnesses, pure Rust.