Agents

Open-source super agent harness that runs sub-agents, memory, sandboxes and skills for research, coding and content tasks lasting minutes to hours.

Open-source platform where you configure multi-agent systems and workflows without writing code

Fully local, voice-enabled assistant that browses the web, writes code and plans tasks without cloud services

Free coding agents for terminal, desktop, web and GitHub repositories, supported by text ads.

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

Desktop harness that coordinates several terminal coding agents as one team on your own machine.

Minimal software engineering agent built around bash only, scoring above 74% on SWE-bench Verified.

Open-source persistent development workspace with unattended tasks, schedules and heartbeat monitoring.

Open-source desktop and mobile AI agent client that runs Claude Code and Codex on your own machine.

Stateful agent harness whose agents keep memory across sessions and run on schedules through a CLI, browser and chat apps.

Cross-platform desktop app that orchestrates parallel coding agents, playbooks and phone control.

Open-source terminal AI agent that runs shell, Python and web tools on any model, including local ones.

Open-source platform for running coding agents, with a browser control center, CLI, SDK and self-hosted or cloud backends

Open-source personal assistant with a RAG knowledge base, agent loops and MCP tool access.

Free desktop app where AI agent teams work tasks from a kanban board, message each other and review each other's work.

Open-source local-first desktop app where a Commander agent splits goals into to-dos for built-in and third-party coding agents.

Open-source desktop and CLI agent that keeps its identity, memory and history across tasks and can modify the code it runs on.

Research agent from Princeton and Stanford that lets a language model fix GitHub issues and other tasks by using tools on its own

Open-source reverse-engineering agent that uses Ghidra and LLMs to rebuild and validate C/C++ functions from binaries.

Open-source control center that runs Claude Code, Codex, OpenCode and other coding agents in parallel, each in its own worktree

Self-hosted mission control that runs Claude Code, Codex, Gemini and other coding CLIs in tmux sessions, viewable from any browser

Native macOS AI agent that connects many LLM providers to a task loop that drives apps through Accessibility and builds in Xcode.

Local-first agent OS that runs Claude Code, Codex and OpenCode on your machine and lets you drive them from a browser or chat apps.

DeepSeek-native coding agent for the terminal, written in Rust, with a TUI and a headless exec mode for scripts and CI.