ContextKit - Token-Efficient Context Engineering + Agentic AI Pipelines. Scaffold structured standards for AI assistants and run autonomous multi-role pipelines (PO → Architect → Dev → Test → Review → Doc) grounded by that same context layer. Works with C

Web Context layer to perform boltz swaps

Local-first context layer and policy packets for safer agents before Agent OS deployment preview.

Product Context Layer — MCP server for AI-assisted product development

Sovereign, portable LLM context layer

CLI for the awrk shared context layer

Open organization graph and delegation-context layer for agentic systems

Local stdio MCP server for Leji: retrieve the spec and schemas, and run validation and conformance against a context layer, natively from an AI agent.

OriginAI CLI — your missing product context layer for AI coding. Login, MCP bridge, skill link, release sync, RPML validate

The context layer for modern software development. A Rust-powered developer context engine that builds reliable, local understanding of any codebase — for humans and their tools. This package downloads the native `blink` binary for your platform on instal

Full AI context layer over MCP — tree-sitter code-map, document RAG (PDF/Office/HTML/email + OCR + reranker), shared agent memory, on-demand web crawl, git history + blame + per-symbol diff. 300+ languages, 10+ coding-agent harnesses, content-addressed Fj

Lightweight project context layer for Agent Coding and CrewBee integration.

Context layer for AI coding agents — syncs your meetings, Slack, and iMessage into .context/ files your agents read automatically

PhantomindAI — AI Context Layer with Real-Time Automation, Multi-LLM Support & Agent Orchestration

Pi extension for AlchemystAI Context Layer — persistent, retrievable memory for coding sessions

The official UseMyContext SDK for the personal context layer for AI - a typed client + React hook for the structurally-blind personal-context MCP. npm i usemycontext, then drop the user's compiled context straight into any AI app.

Full AI context layer over MCP — tree-sitter code-map, document RAG (PDF/Office/HTML/email + OCR + reranker), shared agent memory, on-demand web crawl, git history + blame + per-symbol diff. 300+ languages, 10+ coding-agent harnesses, content-addressed Fj

Connect ClariLayer — the individual-analyst context layer for your data and engineering context (decisions, constraints, incident lessons) — to Claude Code, Cursor, or Codex in one command.

Reference SDK and CLI for Leji, the open specification for the shared context layer of AI-native teams: validate, index, changelog, freshness, conformance, status, route, federation mounts, viewer, view, init, adopt, detect, start, ci, and agent.

Pathrule, the context layer for AI coding agents: path-scoped memories, rules, and skills for Claude Code, Cursor, Codex, and Windsurf.