Enterprise-grade (40m+ lines) codebase intelligence in a zero-setup, private and local Plugin/Skill or MCP: managed indexing, hybrid semantic search, polyglot code dependency graphs, cross-project/repo & branch-aware search, and DB/API/infra knowledge. Benchmark: 61% less tokens, 84% fewer calls, 37x faster than AI grep. Cloud in private beta.

Context-Engine MCP - Agentic Context Compression Suite

Open Source Context infrastructure for AI agents. Auto-capture and share your agents' context everywhere.

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

Compass is a context engine that builds a knowledge graph of your organization's metadata, capturing entities, relationships, and lineage across systems and time, making it discoverable and queryable for both humans and AI agents.

Local-native Context Engine MCP server for codebase indexing, semantic retrieval, planning, and review workflows.

MCP server that provides code context and analysis for AI assistants. Extracts directory structure and code symbols using WebAssembly Tree-sitter parsers with Zero Native Dependencies.

Database Freedom Platform - Mathematical search optimization for whatever database you already have. 27,000x faster than vector databases with SMT-powered search across 8+ database types. One-time 9-2999 vs 00-500/month recurring.

Universal Memory & Context Engine (MCP Server) to give Long-Term Memory to AI Agents.

Give one OpenClaw session durable memory, topic-aware continuity, and bounded token growth.

A Local Context Engine

A production-ready TypeScript MCP server that provides comprehensive project analysis, intelligent code search, dependency tracking, and coordinated multi-file editing capabilities.

The Physics Engine for AI Coding Agents.

Self-hosted adaptive code search: micro-chunk precision, hybrid rerank, VS Code/MCP-ready

Autonomous context engine plugin for OpenClaw — pre-search memory retrieval with salience scoring, QMD integration, and cross-agent memory support

Arq - Spec-first AI coding agent with deep codebase understanding

Persistent local memory engine for OpenClaw — replaces default memory-system with a full context lifecycle: hybrid vector recall, automatic compaction, and domain-adaptive gating over LibraVDB

This is your operating system for thinking - A context and decision engine that filters signals and tells you what actually matters.

🔭 V.I.S.O.R. — Visual Intelligence System for Orchestrated Reasoning. A local-first MCP server that indexes your codebase via AST parsing, ranks code with a 5-signal scoring engine, and delivers surgical context to AI coding agents. Works with Antigravity, VS Code, Cursor, and Claude Code.

Passive-first iPhone context runtime for AI agents. Turns on-device signals into deterministic, policy-aware events for OpenClaw.