context-engine

Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra knowledge. 61% less tokens, 84% fewer calls, 37x faster. Cloud in beta.

Symbol Delta Ledger (SDL-MCP) is a policy-centered context budget layer for coding agents: Symbol-graph intelligence combined with precision tools. It turns sprawling codebases into compact, high-signal context that saves tokens, speeds up workflows, and improves agent output.

Shared memory for AI agents

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

Local-first code knowledge graph and context harness for coding agents. MCP + DeepSeek Harness (dsh) plugin.

Clinia Context Engine Studio - open-source studio app for the Clinia Context Engine.

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

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.

Project Intelligence Layer for AI-assisted development. Preserve project decisions, reasoning, constraints, history, and evolving state across AI tools.

A Local Context Engine

Local code-intelligence engine for AI agents — indexes a repository into a PostgreSQL code graph and serves token-budgeted context (symbols, effects, contracts, blast radius, similar code) over MCP and HTTP.

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

A model of you, built from your own AI history, on your machine. Every AI you use reads it. So every AI finally knows you.

Claude Code plugin: local-first documentation indexer with advanced RAG search (vector + BM25 + RRF + cross-encoder reranking)

Private AI on your own servers: an open-source knowledge platform for companies, models included. RAG with a cited source on every answer, permission-aware retrieval, MCP, integrations. Fully local on Ollama or vLLM, proven by an egress check, or any provider you choose. Apache 2.0.

Universal Persona Substrate Protocol — Give Your AI a Persistent Identity. Seven Files, One Self, Infinite Conversations.

Local dependency graphs and context intelligence for AI coding agents.

A tool for experimenting with context (aka prompts) for LLMs. Provides context template editor, websocket streaming API, drafting, testing, and analytics.

Local-first, host-agnostic project memory and bounded context for coding agents. MCP stdio server, CLI, and optional OpenCode adapter.