Agents

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

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

Terminal-based AI pair programmer that edits code in your local git repo and works with most cloud and local LLMs

Web workspace where teams and coding agents share live spatial boards, with each git branch running its own agent sessions.

CLI-first penetration-testing agent in Rust that runs recon, testing and validation, with a second model checking each finding.

Personal AI assistant with eight memory types, hourly proactive check-ins and channels from macOS and iOS to Slack and Telegram.

Free open-source personal AI assistant that runs in your own Cloudflare account, with chat, memory, tasks and scheduled reminders.

Open-source visual editor for designing Next.js and Tailwind apps with AI chat and direct edits in the browser

Open-source personal learning agent with three memory layers, a cron scheduler, Feishu and WeChat channels and a practice lab.

Self-hostable autonomous pentesting agent that re-exploits each finding with an independent verifier before reporting it.

Autonomous research agent that reads papers, runs experiments and compiles a LaTeX report with no human in the loop

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

Open-source AI agent for building apps and sites, doing research, and producing documents and slides, runnable locally with your own keys.

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

Gradio web UI for running browser-use AI agents in your own browser, with support for several LLM providers.

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

Python rebuild of Claude Code with multi-agent teams, output-compression filters, a nano mode and a web UI

Self-hosted web command center for OpenCode with sessions, git, terminal and schedules, usable from a phone or desktop

Self-hosted web UI for the Pi Coding Agent that keeps agent sessions running in real workspaces

Self-hosted browser workspace built on the Pi Coding Agent, with chat, file editing, command runs and scheduled tasks

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

Open-source JVM operator console that runs an always-on agent with a browser, terminal, editor and MCP tools

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

Web app for penetration testing with AI chat and an agent mode that runs commands in E2B cloud sandboxes, using OpenRouter models