
bb is an agentic orchestrator GUI, not unlike the Codex app, but it works with any provider: Claude Code, Codex, OpenCode, and more. What makes bb different is that it can customize and extend itself. Almost anything in bb can be changed with a single prompt. Ask for a task tracker, and one appears. bb also creates a skill that teaches all of your agents how to use it. Instead of waiting for your agentic workspace to add the feature you need, you can just ask for it.
Loading comments…
Project Info
Product Keywords
bb is an agentic orchestrator GUI that brings multiple AI coding agents into one unified workspace. Unlike the Codex app, which is tied to a single provider, bb works with any provider—Claude Code, Codex, OpenCode, and more. The core idea is simple: instead of juggling separate terminal windows for different agents, you get one interface where they all live, work, and coordinate. What truly sets bb apart is its extensibility: nearly every part of the tool can be modified with a single prompt, letting you shape the workspace to fit your exact workflow.
Almost anything in bb can be changed with a single prompt. Ask for a task tracker, and a sidebar panel, a bb tasks command, and a skill that teaches every agent to use it all appear at once. Many of bb’s own features—the GitHub integration, agent memory, scheduled jobs, and even remote access—are built as plugins using the same tools you have access to.
The same CLI your agents use is open to any program you write. A shell script, a cron job, or a bot in Telegram, Signal, or Slack can each spawn a thread that’s waiting in your sidebar when you return. It runs on your machine and is ready when you are, making it easy to trigger work from anywhere.
Claude Code, Codex, Cursor, Pi, OpenCode, Grok, omp, and Hermes all live in bb. You can give a task to whichever fits best, and have one agent spawn and manage another, each in its own thread. Every agent runs on your own subscription—billed by the provider, not by bb.
bb is MIT-licensed end to end. You can fork the repo, customize the agents, tools, and UI, and deploy your own build across your entire organization. It still runs local-first on your machines, on the provider subscriptions you already pay for.
"Nothing is stopping you from building your ideal workbench."
That’s the philosophy in action. Most agent tools are closed boxes—you get what the vendor ships and you wait for updates. bb flips that model by making its own features plugins you can inspect, modify, and replace. The combination of prompt-driven customization and full MIT licensing means the tool evolves with you, not the other way around. It’s rare to find a GUI that’s both this flexible and this transparent.
You’re already juggling multiple AI coding agents and want a unified, local-first workspace. You’re the type who builds your own tools and hates waiting for feature requests. Or you simply want an open-source orchestrator that respects your existing provider subscriptions and runs on your own hardware. bb is free, installs in under a minute, and is waiting to be shaped into exactly what you need.
Other tools you might consider
The moment an agent needs to deploy something, it slams face-first into a wall built for humans. Today we're rolling out Temporary Accounts on Cloudflare Workers. Any agent can now run wrangler deploy — temporary and get a live Worker in seconds.
GitHits gives coding agents access to the open-source code your app depends on. Get real implementation examples, dependency source navigation, package inspection and documentation. Agents can grep and read your codebase. They can't grep and read the open-source code your app depends on. That's where they start guessing, retrying, and looping. GitHits builds a version-aware index on demand. Agents can search, navigate, and inspect the code behind their dependencies. CLI: npx githits@latest init
You're running more coding agents than ever, but you can't keep up with them. That's where AgentPeek comes in. It pulls every session up into your Mac notch, live. Glance up, approve a prompt, watch token usage and manage the entire flow without pausing your YouTube video. All local, all yours.
Octopoda is an open source infrastructure layer that gives AI agents persistent memory, automatic loop detection, and full observability. Agents forget everything between sessions. Octopoda fixes that with a remember/recall API that survives restarts, crashes, and deployments. The loop detection system monitors 5 signals to catch agents stuck repeating themselves before they burn your API budget, with real-time cost estimation showing exactly how much each loop wastes. A built-in dashboard shows every agent's health score, memory explorer with version history, audit trail logging every decision with reasoning, and a timeline replay that lets you scrub through everything your agent did step by step. Works with LangChain, CrewAI, AutoGen, and OpenAI Agents SDK with one-line integrations. Runs locally with SQLite or connects to cloud with one environment variable. Free tier, MIT licensed. 177 signups, 120 GitHub stars, zero marketing spend.
Maker
neon_dev
Alternatives
Loading comments…