Local context engine for AI coding agents. Routes tasks to relevant files, tests, rules, and skills, supports prompt caching, and builds compact context packs for Claude Code, Codex, Cursor, MCP, and more.

Live context engine and MCP server for AI agents. Resolves git, services, and tests into ready context. Local-first, MIT. PyPI: perseus-ctx.

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

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

🧠 Open-source context engine that feeds AI agents with policy-compliant enterprise knowledge. MCP-native, GDPR & EU AI Act ready, self-hosted.

Context Memory eXchange — a retrieval-first, engine-enforced-grounding context engine for Hermes Agent and a drop-in LCM replacement. Keeps 100% verbatim history (SQLite FTS5+trigram+embeddings; Postgres optional), retrieves exact slices every turn, and forces + verifies grounding so the model answers from real history or honestly refuses.

AIN State Compiler is a local-first enterprise AI state compiler that continuously transforms Slack, Jira, and Gmail logs into executable, conflict-resolved operational state. Built with Python and SQLite.

**Fully Local AI Runtime for Windows 11 — Modular, Offline, and Built for Safe Natural‑Language Automation.**

Standalone Kontext long-term memory backend, MCP bridge, hooks, and evaluation tooling.

Deterministic live context for Google ADK agents. Compiled by Perseus and injected as a system instruction.

🚀 AI-powered Persistent Context Engine for Autonomous SRE that remembers operational history, reconstructs incident context, detects recurring failures, and recommends proven remediations in real time.

Context Engine with self-improving memory over a code corpus. RAG-shaped but built for 2026 long-context models: dumb high-recall retrieval, four-channel merge (BM25 + ripgrep + symbol + vector), OpenAI + MCP server surfaces.

Unit27 public field kit for governed, token-aware context packages for AI agents.

Near-optimal vector quantization for OpenClaw context compression, based on the TurboQuant algorithm from Google Research.

TOON v4 · 99.97% compression · 3/3 tool bridge · 5 MCP graph tools · Auto-sync pipeline · Single-command install

Buena Property Context Engine: compiles fragmented property-management data into a durable, editable, queryable context artifact.

🧠 Lightweight AI Agent Memory & Context Management Engine - Zero dependencies, multi-tier storage, TF-IDF search, session management | 轻量级AI Agent记忆与上下文管理引擎