Agents

Lightweight terminal workspace that coordinates Codex, Claude, Gemini and other CLI coding agents.

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

Open-source background agent with local memory, permission rules and chat access from many apps.

Open-source local-first agent that runs browser and file tasks on local or cloud models.

Self-hosted B2B lead-finding agent that qualifies people from a product description and emails them.

Local-first control app for running and following coding agents from a desktop or a Linux server.

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

Go terminal coding agent with cost-aware routing across LLM providers, shipped as one binary.

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

Open-source, self-hosted swarm of AI agents for authorized API and web-app penetration testing.

Minimal Python autonomous agent for GPT-3.5 and GPT-4 with web search, memory and a critic option.

Open-source local daemon that runs Claude Code, Codex and Cursor CLIs on cron, webhooks and approvals.

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

Retrieval augmented generation package that answers questions from scientific papers and documents with citations.

Command-line multi-agent tool that writes a full-length novel from a one-line brief and resumes from saved checkpoints.

Open-source experimental LLM agent that plans tasks and runs tools in a Docker ToolServer.

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

Terminal coding agent packaged as a single Rust binary that can run fully offline with a local GGUF model.

Rust port of the Pi coding agent CLI with streaming responses, 36 built-in tools and a single binary.

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.

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