A knowledge graph your AI agents build, query, and grow. Built for agents that need structure beyond vectors
#context-engineering
49 posts
Git-native context control plane for AI coding agents
Better context transport for AI coding agents.
Unified MCP context intelligence platform — pip-installable CLI that absorbed 6 foundational repos. Context engineering for AI agents.
Engineering knowledge infrastructure for AI coding agents.
Secure AI Memory with Dynamic Project Detection, Automatic Session Briefing, Personal+Team Session Summary Prompts, Triple Search, Knowledge...
Agent-facing Bicameral MCP tools for ingest, preflight, binding, and review commands
Opencode-Raven keeps noisy tool work behind a focused Raven agent, so your main model gets compact answers instead of raw search results, do...
Episodic memory for AI agents. Records your screen locally, compiles it into structured activity frames, serves them over MCP. No cloud, no...
Persistent, encrypted memory for AI agents: one Rust binary, one file, no cloud. 57 MCP tools, hybrid recall (BM25 + dense + RRF), bi-tempor...
Hybrid RAG (DuckDB vector + BM25 + RRF + recency/keyword priors + optional cross-encoder rerank) as an installable library + CLI.
Git-native context for AI coding agents — CLI and local MCP server