Harness’ official MCP Server
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.
Local RAG layer and optimizer for your Markdown knowledge base. CLI + MCP server: grounded answers for any AI client, stale-note detection, session harvesting into memories. Local-first.
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.
Let LLMs control embedded devices via the Model Context Protocol.
An MCP server that lets LLM agents play Civilization VI.
A headless browser for AI agents that fetches modern web pages, runs JavaScript, manages sessions, and returns token-efficient Markdown.
Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.
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.