Lody: A shared workspace for the coding agents your team already uses.
What problem it solves
Teams using coding agents need a shared way to access conversations, dispatch work, and follow activity across machines and surfaces. Screenshots, pasted logs, and separate agent sessions make context difficult to preserve and coordinate.
Key features
Shared agent conversations — Open the same conversation with teammates and follow its transcript, runtime status, files, and code changes. Add instructions without circulating screenshots or pasted logs.
Source: README
Existing agents and machines — Connect ACP-compatible agents and the machines where they are already configured. Subscriptions, logins, models, and permission modes remain on the user’s machines until their owner shares them.
Source: README
Work dispatch from any surface — Select a connected machine when dispatching work from desktop, mobile, web, or CLI. Permission requests, progress, conversations, and code changes remain visible across those surfaces.
Source: README
Agent coordination — Agents can create or reuse conversations, inspect their status and history, send instructions, cancel work, and collect results. One conversation can coordinate investigation, implementation, and testing across parallel conversations.
Source: README
Code and execution tools — Run parallel work in separate Git worktrees and inspect diffs, pull requests, CI, files, and visual feedback beside the conversation. Sessions also provide tabs, terminals, previews, and element-level annotations.
Source: README
Quick start
Copied verbatim from the project's README.
npx lody daemon startnpx lody session create --workspace my-team --agent-config codex \
--repo owner/repo "Fix the failing test"
npx lody session list --workspace my-teamWho it may suit
This may suit teams that already use ACP-compatible coding agents and want to share conversations, manage multiple private machines, and dispatch or review work across desktop, mobile, web, and CLI.
Topics to discuss
How should teams structure shared permissions for privately owned machines?
Which local-first collaboration workflows should be prioritized beyond conversations?
How should agents coordinate parallel conversations without making their context difficult to follow?
Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.
Read the original README https://github.com/LodyAI/Lody#readme
ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.
Comments
…