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
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.
A production-ready TypeScript MCP server that provides comprehensive project analysis, intelligent code search, dependency tracking, and coordinated multi-file editing capabilities.
Deterministic, offline-first agent sandbox with concept-graph memory. Reflex→retrieval→planning→filter for repeatable outputs. Stable baseline for v4 external reasoning.
Arq - Spec-first AI coding agent with deep codebase understanding
SkyOne is the cognitive nucleus of the Sky Ecosystem — an AI-driven bootloader designed to coordinate modular memory, journaling, and orchestration across all Sky tiers. It handles context persistence, data flow management, and reflection pipelines to unify intelligent behavior across SkyServer and SkyWeb.
DAG-native multi-window command center for live agent orchestration (MCC from VETKA).
Core library: scoring, selection, and caching for the Context Engine
SDK-only OpenClaw plugin and context engine bridging OpenClaw threads into an isolated headless OpenCode + OmO runtime.
Self-hosted adaptive code search: micro-chunk precision, hybrid rerank, VS Code/MCP-ready
Perplexity-powered agent for finding information regarding any real estate property. Built during the Perplexity Hackathon.
Documentation and how-to guides for the Context Engine platform
Protocol specifications, architectural decisions, and design documents
OpenClaw TeamBrain plugin for multi-agent and multi-project external memory workflows
A local-first, privacy-focused personal context engine that lets you chat with your documents using offline AI models. Built with Electron, Python, and Ollama.
Add a description, image, and links to the context-engine topic page so that developers can more easily learn about it.
To associate your repository with the context-engine topic, visit your repo's landing page and select "manage topics."