The Open Context Layer for Data and AI , OpenMetadata is the open platform for building trusted data context and business semantics for humans, AI assistants, and agents.
-
Updated
Nov 18, 2026 - TypeScript
The Open Context Layer for Data and AI , OpenMetadata is the open platform for building trusted data context and business semantics for humans, AI assistants, and agents.
The open-source context layer for AI agents and enterprise AI search. Permission-aware search and cited answers across 30+ sources, including Slack, Drive, Jira, GitHub and Microsoft 365, for people and agents through MCP, SDKs and built-in agents. Self-hosted or Cloud.
ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, or other AI agents to query analytical databases accurately and with full context of your company
The ledger for agentic data work.
Memory for your AI work across projects and sessions. Save decisions, rules and lessons with source and applicability. Connect over MCP.
Honeydew AI plugins for coding agents (Claude Code, Codex, Cursor, Github Copilot, Gemini, etc...)
The trust layer between AI and your data. Turns your database schema - messy joins, undocumented tables, into a governed semantic model so AI answers with correct SQL and a receipt on every answer. Run it locally, or self-host a shared team server with Docker.
Remote MCP server, local stdio bridge and CLI for PipesHub: permission-aware company search with citations for Claude Code, Codex, Cursor and other MCP clients.
Maximem Synap Core: open-source, self-hosted memory for AI agents. 83.6% on LongMemEval (Synap Cloud: 95.6%). Extraction, entity resolution, temporal reasoning and vector + graph retrieval behind the same API as Synap Cloud. One docker compose up. Python and JS SDKs.
Analyze Once, Reuse Context Everywhere — For Developers and AI Agents
Local-first shared memory and task ledger for AI coding agents. Keeps context across sessions in SQLite via MCP.
The open specification for the shared context layer of AI-native teams
Open-source context layer for LLM agents — a single Rust binary served over MCP that feeds Claude, ChatGPT, Codex or any MCP client the facts, decisions & history they need. Local-first, on-device embeddings, hybrid BM25 + vector + graph retrieval. Apache-2.0.
Agent skills that put a trust ladder under the AI Context layer: a Linked OKF knowledge bundle where every claim is a draft, checked by automation, or confirmed by a person.
A study of production memory systems for AI agents — storage topology, write policy, scopes, schema, and recall surface.
She who was never born yet sheltered the maiden whom her first mother could not love. M.O.T.H.E.R, May I come home?
Persistent memory for mngr coding agents. A mngr plugin that recalls past project decisions, with dates, into a new agent's first prompt so it does not start from scratch.
UseMyContext plugin for Claude Code - your personal context layer for AI, read over MCP in the terminal
Persistent, agent-agnostic project context for AI coding agents.
AI Business Operating System: the brain and heart of your business. Context layer, skills, tools, hooks, data ingestion, reporting and learning in one place. Entrepreneurs have to run every business function themselves or with a small team. This is how you do it. The ultimate tool for entrepreneurs. You will not be able to live without it.
To associate your repository with the context-layer topic, visit your repo's landing page and select "manage topics."