Agents

Open-source desktop agent workspace for document work, visual design and coding over ACP.

Open terminal coding agent that runs on local Ollama models or any OpenAI-compatible API.

Open-source personal agent for phones, computers and the browser that does tasks and asks before anything irreversible.

Free open-source desktop app for Windows and macOS that runs AI agents with one-click install, sandboxed workspaces and Skills.

Open-source web, desktop and mobile control room for running coding agents such as Claude Code and Codex on your own machines.

Free MIT-licensed desktop workspace that runs Codex and Claude Code sessions in parallel, with visual editors and task tracking.

Open-source layer that turns a recorded task into a replayable program for computer-use agents, with read-back checks on every save

Terminal coding agent that edits files and runs commands, lets you pick the model and permission level, and runs on your machine.

Terminal kanban board that assigns tasks to several coding agents and hands work between them by phase.

Minimal coding agent written in Rust with multi-provider models, a permission system, MCP support and session resume.

Local-first desktop harness for running several bounded AI agents in a pixel-art station, using your own model keys.

Open-source browser extension that puts an AI agent in a side panel to chat about pages and run multi-step browser tasks.

Open-source full-stack agent with a desktop app and a CLI/TUI for coding, files, research and content work.

Agent that takes a job in chat or Slack, picks its own tools, and leaves outbound work as drafts for a person to approve

Lightweight terminal coding assistant with a tool loop and TUI, offered as TypeScript, Python and Rust versions

Local-first macOS desktop app that runs one task across several agent CLIs, collects their findings and gates file writes behind approval

Agentic IDE built around the pi coding agent, with isolated git-worktree workspaces, living specs and MCP support

Desktop app that runs Claude Code, Codex and other coding agents in parallel, each in its own git worktree

Python terminal coding agent with DeepSeek by default, MCP tools, sub-agents, approval prompts and reusable learned skills

Terminal coding agent with permission rules, OS sandboxing, MCP, skills and sub-agents, for Anthropic, OpenAI-compatible, Gemini and local models

Coding agent tuned for small local models, built on the pi agent harness and run from the terminal.

Kanban workspace for running several coding agents in parallel, reviewing their changes and opening pull requests

Terminal coding agent built on DeepSeek Harness, with a background host that keeps sessions running and hands tasks between sessions

Background agent that picks up Linear, GitHub, GitLab and Slack issues and runs Claude Code, Codex or other coding agents on them.