Agents

Open-source, local-first desktop workspace for running Claude Agent SDK, DeepSeek Harness or Codex agents with scheduled tasks.

Open-source, terminal-first manager for running many CLI coding agents in parallel, with worktree handoffs and a phone view.

AI agent that holds a USDC wallet, pays for each model call and paid API, and runs tasks within a budget.

Open-source workspace that shows the status of coding agents such as Claude Code and Codex running in tmux panes.

Coding agent built on pi that hands routine decisions to a small judge model, so the main model can focus on the code.

Self-hosted open-source AI coding assistant with a CLI and web UI, multi-agent collaboration and Docker deployment.

Iterative search agent that keeps searching, reading web pages and reasoning until it finds an answer or runs out of budget.

The Pi coding agent compiled ahead of time into one native executable for Linux, macOS, Windows and Android (Termux).

Open-source AI orchestrator for running a team of coding agents from desktop, mobile and CLI, on any machine.

Local-first inbox for long-running AI agent work, built on DeepAgents and LangGraph with approvals and scheduled runs.

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

Autonomous research agent that forms hypotheses, edits code and runs experiments, keeping only gains that hold on held-out data

Coding agent for macOS and the terminal, built around DeepSeek models, with Swift, Bun and Rust versions

Terminal coding agent that isolates subagent work so the main model context stays small on long tasks, with any cloud or local model.

Open-source agentic SAST scanner: AI agents follow imports and call graphs to confirm findings in a repo or PR diff.

Open-source Rust terminal coding agent that edits and tests code, drives Firefox and desktop apps, and runs with many model providers.

Desktop and terminal AI coding workspace with persistent sessions, project memory, subagents and a managed browser.

Open-source terminal coding agent for the xAI Grok API with headless and Telegram control.

Single-file Python agent for shell and ops work that runs against any OpenAI-compatible model, with per-directory sessions.

Terminal coding agent that routes each development task to Claude, GPT or Gemini based on configurable rules.

Open-source coding agent available as a desktop app, a terminal CLI or a Skill, with separate planning, coding, review and testing roles.

Brief-driven runner that keeps coding agents working across sessions and asks only for decisions that are yours.

MIT-licensed AI coding agent with terminal, TUI and browser interfaces, durable project memory and specialist subagents.

Open-source desktop app where a read-only Mentor agent plans and reviews while an Executor agent writes code, cross-checking each other.