Everything in the catalog

Open-source workspace for building, deploying and governing AI agents and workflows, with 270+ integrations and self-hosting

Neovim plugin that gives AI code suggestions and applies them to your files, modeled on the Cursor IDE

Open-source desktop assistant that builds a knowledge graph from your work and runs background agents on events or schedules

Docker's open source MCP Gateway that runs MCP servers in isolated containers with credentials and access control.

Open-source generative BI engine that gives AI agents a governed semantic layer for correct SQL and shareable dashboards.

Open-source personal assistant that uses tools, memory and local or remote AI providers to carry out tasks

Open-source multi-agent coding system from the HKU Data Intelligence Lab, written in Python

Open-source library that optimizes LLM and visual generation inference with specialized kernels and a Python framework.

Open-source desktop app for running a multi-agent workforce on local or cloud models, with MCP and skill integration.

Observability and dev-tool platform for building, evaluating and monitoring AI agents

Open-source browser for AI agents that runs beside Chrome, with imported logins and live session replay.

OpenAI's coding agent for the terminal, editor, desktop app and ChatGPT cloud, included in ChatGPT plans

Terminal-native AI coding assistant that reads and writes code, runs commands, manages Git and keeps persistent project memory.

AI gateway giving one API to 250+ models, with observability, guardrails and prompt management.

Open protocol, CLI and SDK that give agents scoped credentials from a password manager without exposing the vault

Open-source desktop workspace that runs, supervises and follows coding agents across git worktrees, from task to merged pull request.

Single-file memory layer for AI agents with persistent, versioned and portable memory and no database.

Open-source AI agent that runs as a Chrome and Edge side-panel extension in your signed-in browser.

Open-source AI automation platform for agents, flows and tables, with an MCP server, 770+ apps and a cloud or self-hosted option

Open-source computer use agent from Simular that operates desktop and web apps by clicking, typing and scrolling.

Terminal coding agent from Moonshot AI that edits code and runs commands, with MCP, skills and ACP support.

Open-source research agent that plans questions, searches the web or your documents in parallel and writes a cited report with any LLM.

Open-source general-purpose agent built as an invite-free alternative to Manus

Self-hosted AI assistant for multiple users and agents, reachable from a web dashboard and chat apps.