A TypeScript runtime that runs Claude Code, Codex, Grok Build, OpenCode and other coding agent CLIs behind one API, with checks the runtime runs itself.
LodyAI/Lody
A shared workspace where teams connect machines and coding agents via ACP, share agent conversations, and dispatch work from desktop, mobile, web, or CLI.
- Stars
- 1,670
- Forks
- 181
- Open issues
- 271
- Last commit
- 10 hours ago
What is it?
Lody lets a team share coding agent conversations and the machines they run on. Developers connect a workstation, server, or cloud VM with a single daemon command, then bring agents such as Claude Code, Codex, Kimi, or OpenCode through the Agent Client Protocol (ACP). Teammates can open the same conversation to see the full transcript, runtime status, files, and code changes, and add instructions without passing screenshots or logs around.
Work can be dispatched from desktop, mobile, web, or a CLI that can also create sessions, read history, and emit JSON for scripts. Agents can create, read, message, and cancel other conversations, so one session can coordinate parallel investigation and implementation. Each session can get its own Git worktree, and the workspace shows file browsing, per-turn diffs, pull request and CI status, and a web preview with element-level annotations sent back to the agent.
The repository is a monorepo with an Electron desktop app, a CLI, shared UI packages, and documentation site. Some local-first sync and end-to-end encryption work based on Loro CRDTs is described as in progress.
Key features
- 01Connect any machine and run ACP-compatible coding agents such as Claude Code and Codex.
- 02Share full conversation transcripts, files, and code changes with teammates.
- 03Dispatch work from desktop, mobile, web, or the CLI, with permission requests visible on each surface.
- 04Give each session its own Git worktree for parallel work.
- 05Let agents create, message, and coordinate other conversations.
- 06Preview running web apps and send element-level annotations to the agent.
Use cases
- A team that wants to follow and steer an agent's work on a shared server without screen sharing.
- Splitting a bug fix into parallel investigation, implementation, and testing conversations.
- Reviewing agent-produced diffs and PR CI status alongside the conversation that made them.
- Triggering or monitoring agent sessions from scripts using the CLI's JSON output.
Quick start
- 1
Connect a machine with the Lody CLI
npx lody daemon start - 2
Create a session from the CLI
npx lody session create --workspace my-team --agent-config codex --repo owner/repo "Fix the failing test"
Things to know
- Requires a sign-in to a Lody workspace before machines can be used.
- Some planned features such as documents and full local-first support are not yet available.
In collections
Topics
FAQ
- What is Lody?
- A shared workspace where teams connect machines and coding agents via ACP, share agent conversations, and dispatch work from desktop, mobile, web, or CLI. Lody lets a team share coding agent conversations and the machines they run on. Developers connect a workstation, server, or cloud VM with a single daemon command, then bring agents such as Claude Code, Codex, Kimi, or OpenCode through the Agent Client Protocol (ACP). Teammates can open the same conversation to see the full transcript, runtime status, files, and code changes, and add instructions without passing screenshots or logs around.
- Is Lody free to use? What license does it have?
- Lody is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is Lody still maintained?
- Actively maintained. The last commit to Lody was on Nov 6, 2026.
- What can I use Lody for?
- A team that wants to follow and steer an agent's work on a shared server without screen sharing. Splitting a bug fix into parallel investigation, implementation, and testing conversations. Reviewing agent-produced diffs and PR CI status alongside the conversation that made them. Triggering or monitoring agent sessions from scripts using the CLI's JSON output.
- How do I install Lody?
- Connect a machine with the Lody CLI: npx lody daemon start Create a session from the CLI: npx lody session create --workspace my-team --agent-config codex --repo owner/repo "Fix the failing test"
- Where can I get Lody?
- The source code and installation instructions are on GitHub: https://github.com/LodyAI/Lody
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A self-hosted AI agent team that runs on your machine, using the agent CLI subscriptions you already have to plan, code, review and merge tasks.
A terminal multiplexer that runs multiple AI coding agents in parallel, each in its own tmux pane with a separate git worktree and branch.
Desktop app to run Claude Code, Codex, and other AI coding agents in parallel, each isolated in its own git worktree and branch.
An agentic IDE built around the pi coding agent, running each task in isolated git-worktree workspaces with living specs and reusable skills.
A Python CLI that wraps coding agents like Codex and Claude Code with an optional supervisor, reviewer, adversary, and local log distiller, each on its own model.