|
supermu — a persistent workspace for humans and AI coding agents
Run Claude Code, Codex, shells, and development processes as durable sessions. Close your terminal, reconnect later, and everything is still there — and supe...
|
84 % |
|
TurboTTY — a command center for coding agents
TurboTTY is a native macOS terminal built around repositories. Each task gets its own git worktree and a real, GPU-drawn terminal. Sessions survive quit.
|
83 % |
|
VibeRevert: undo an AI coding session, keep your own work
Undo an AI coding session and keep the work you hadn't committed. Deterministic risk checks for vibe coding and production agent workflows. Local, open source.
|
83 % |
|
Axocoatl — the harness you can trust to run coding agents
The harness you can trust to run coding agents on your own machine or infrastructure: isolation built in, a complete record of every step, any model, local o...
|
83 % |
|
Codrift: run many AI coding agents at once
A desktop control surface for running many AI coding agents at once. Live terminals, isolated worktrees, one diff, one shared memory, driven from the keyboard.
|
83 % |
|
Cocurdex
Multi-agent development workspace for professional developers. Chat, terminal, editor, and browser preview in one desktop shell.
|
82 % |
|
Helioterm - Know when your agent needs you
Helioterm is browser access to the terminal and AI-agent sessions on your machine. It flags agents waiting on you, keeps sessions alive in tmux, and stays pr...
|
82 % |
|
Aya - workspace for long-lived coding agents
A free, open-source desktop workspace for long-lived Claude Code, Codex, and other coding agents, organized by project, with tiling splits and a status rail.
|
81 % |
|
Signal Inbox — one board for every coding agent
Queue work for your coding agents, run it on hardware you own, and get told the moment one finishes, fails, or needs an answer. Open-source runner, free tier...
|
81 % |
|
Agentree | Supervise Multiple Coding Agents in One Graph
Supervise multiple coding agents in one graph. Branch from any agent message, run isolated worktrees, and write plain-English workflows for multi-step coding...
|
81 % |
|
opentine — Git for agent runs
Git-shaped provenance for agent runs: capture, import, verify, fork, replay, attest, synchronize, and export portable execution history.
|
81 % |
|
Rath Team
Rath Team builds OpenRath, a session-first runtime direction for inspectable multi-agent workflows, sandbox-backed execution, and practical agent engineering.
|
81 % |
|
flowgate — Guardrails for AI coding agents that actually hold
Your AI coding agent deployed before tests and approved before review, and a longer prompt didn't fix it. flowgate puts agents on a state machine they can't...
|
81 % |
|
Tegment — A control room for parallel AI coding agents
Tegment gives every coding agent its own git worktree, terminals and ticket context. Run multiple Claude Code sessions in parallel without stepping on each o...
|
81 % |
|
qmux — The queueing terminal multiplexer
qmux is a macOS desktop terminal with a native control plane for AI coding agents.
|
81 % |
|
agterm — a simply good macOS terminal with a full control API
Native macOS terminal with named workspaces and a local control API for scripts, AI coding agents, and multi-session workflows.
|
80 % |
|
Landry’s Chain of Thoughts
A local-first agentic OS. Goals in, an inspectable policy-gated run out — from a terminal, from Telegram, or from an approval console.
|
80 % |
|
Rulvar - agent workflows that survive the process
Rulvar is an embeddable TypeScript runtime for durable, budget-bounded multi-agent LLM workflows with per-call model routing, replay, typed outcomes, and tests.
|
80 % |
|
Lanes | Run your agentic fleet at scale.
Lanes lets you run autonomous agents in parallel with the right context, memory, and governed access.
|
80 % |
|
Tazzie.ai — Symphonic Intelligence
Autonomous coding agent, 8 frontier models, semantic memory, Python sandbox. Chat, code review, and autonomous missions.
|
80 % |
Detected social media networks