Agents

Personal desktop AI agent for files, writing, planning and daily tasks, with companions, plugins, scheduled runs and MCP.

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

Open-source, local-first desktop app where a team of AI coding agents shares one session, a visible plan and an issue list.

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

Local-first desktop AI agent that drives Claude Code, Codex, Gemini and other AI CLIs from one command center.

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

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

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.

Locally run, multi-provider AI coding workspace for the desktop, with sessions you can continue from a phone on the same LAN.

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

Desktop GUI for the Pi coding agent that runs the same engine as the Pi CLI, with multi-session chat and tool approvals.

Open-source desktop agent combining real-time voice chat, a speaking character and delegated work with visible permissions.

Desktop workspace that runs AI coding agents side by side in panes, with per-task git worktrees and hunk-level review of their changes.

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

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

Self-hosted personal AI agent with a desktop app and web dashboard that talks over Telegram, Slack, Discord, WhatsApp or the browser

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

Local-first open-source desktop IDE for long-running agent work, with code, Git, terminal, browser and MCP in one workspace

Local-first credit-risk agent that turns data files into governed analysis, models, strategy code and audit-ready reports.

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

Desktop app that runs Claude Code, Codex, Copilot CLI and pi side by side as crews on one shared mission feed, in real terminals.

Local-first MIT coding agent with DeepSeek defaults, provider switching, OS sandboxing and a checkpoint for every patch.

Enterprise desktop AI assistant with parallel agents, scheduled tasks, skills and Feishu integration.