Lody
Share, dispatch, and supervise your team's existing coding agents across desktop, mobile, web, and CLI.
- Source repo
- LodyAI/Lody
- Stars
- ★ 1.8k
- Last updated
- today
- License
- Apache-2.0
- Primary language
- TypeScript
- FA score
- 63/100 · Some gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformCodex · Claude Code
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A development team already using Codex, Claude Code, Kimi, or OpenCode can share live conversations instead of circulating screenshots and logs.
- Not a fit if
- Teams that require a fully local-first architecture today
- Environments that must operate without networking or sign-in
- Users seeking a bundled coding model rather than bringing an existing Agent
- Website
- lody.ai ↗ set on GitHub
- Maintenance
- Commits in the last 30 dayslast commit 2026-11-21latest release v0.109.0 (2026-10-30)+6.1 ★/day over 7 days
- Source review
- 63/100 · Some gaps
What does this agent do, and when should you use it?
Lody is a shared workspace for connecting a team's existing coding agents and the machines that run them; it is not presented as a new coding model. Through ACP, it works with Claude Code, Codex, Kimi, OpenCode, and other compatible agents while retaining each machine's existing subscriptions, logins, models, and permission modes. Users can create and follow sessions from desktop, mobile, web, or CLI, with access to transcripts, runtime status, files, code changes, and permission requests. A machine joins the workspace through npx lody daemon start, while the CLI can register projects, inspect machines and Agent configurations, create sessions, and archive or restore them. Parallel jobs can use separate Git worktrees, and an Agent can coordinate investigation, implementation, and testing through independent child conversations. The project uses CRDT-based synchronization and is working toward full local-first support, but the README says that transition is not yet complete.
Lody runs lody daemon on a workstation, server, or cloud VM and connects that machine to a workspace through a sign-in link. It reads and exposes registered project files, Git diffs, session history and status, linked repositories, machine details, and Agent configurations; its review interface also places pull request, CI, and GitHub review information beside the conversation. Users can invoke lody session create with a workspace, Agent configuration, and repository, inspect sessions with lody session list, and message, cancel, archive, restore, or fork sessions. A coordinating Agent can create or reuse other conversations, read their status and history, send follow-up instructions, and bring results back, while separate Git worktrees isolate concurrent edits. Desktop, mobile, web, and CLI surfaces share progress, permission requests, attachments, and code changes; the built-in web preview can also send element-level visual annotations to the Agent.
- A development team already using Codex, Claude Code, Kimi, or OpenCode can share live conversations instead of circulating screenshots and logs.
- A team with workstations, servers, or cloud VMs can dispatch coding work remotely and approve permission requests from a phone or desktop.
- An engineering lead investigating a defect can ask a coordinating Agent to separate analysis, implementation, and testing into parallel conversations.
- Developers exploring multiple approaches in one repository can isolate each session in its own Git worktree.
- Reviewers can examine files, diffs, pull requests, CI status, and GitHub threads beside the Agent conversation that produced the change.
- Frontend teams can open a running application, switch responsive viewports, and return element-level visual annotations to the Agent.
Key setup facts
Pulled from the install and usage notes below. The project README has the current values.
- Install / run
npx lody daemon startnpx lody session create --workspace my-team --agent-config codex \npx lody session list --workspace my-team
How do you install or deploy this agent?
The source does not provide complete commands for building every application from the repository. Its documented first connection path requires a terminal capable of running npx and completion of the sign-in flow opened by the command. Start the machine daemon with:
npx lody daemon startThis opens a sign-in link, connects the workstation, server, or cloud VM to the workspace, and leaves it available for work dispatched from desktop, mobile, web, or CLI. The required Node.js version, account-creation procedure, and self-hosted backend deployment steps are not specified.
How do you use this agent?
After connecting and signing in on the machine, make sure the intended project, workspace, and Agent configuration are available. This example creates a task using the codex configuration in the my-team workspace against owner/repo:
npx lody session create --workspace my-team --agent-config codex \
--repo owner/repo "Fix the failing test"List sessions in that workspace with:
npx lody session list --workspace my-teamOpen the same session from desktop, mobile, web, or CLI to inspect its state, history, files, and diffs or add instructions. For parallel work, assign separate Git worktrees or let a coordinating Agent create, reuse, and monitor other conversations. CLI commands that support --json can supply workspace data to scripts and other tools.
What are this agent's strengths and limitations?
- ACP support connects existing Claude Code, Codex, Kimi, and OpenCode setups while preserving their subscriptions, logins, models, and permission modes.
- One session remains visible across desktop, mobile, web, and CLI, including conversations, permission requests, progress, and code changes.
- Agents can create, reuse, inspect, and direct other conversations, enabling parallel investigation, implementation, and testing.
- Separate Git worktrees, adjacent diffs, line comments, pull request state, and CI visibility keep execution and review in one context.
- Mobile notifications, diff inspection, permission approval, and iOS Live Activities support supervision away from the development machine.
- The project explicitly says it is still moving toward full local-first support, so adopters should not assume that architecture is complete.
- A machine must be connected through a sign-in link; no offline or account-free operating path is documented.
- Lody expects users to bring and configure an ACP-compatible coding Agent rather than supplying a bundled model or standalone coding engine.
- The source does not specify the Node.js version, backend self-hosting procedure, authentication details, or service pricing.
- Stable releases do not build or upload installers or auto-update artifacts; the documented release workflow only synchronizes versions and creates a GitHub Release.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Lody This agent | 63 · Some gaps | Self-hosted service | ★ 1.8k | today | TypeScript | Codex · Claude Code |
| Alas Agent Workspace | 79 · Good | Desktop appFree + model costs | ★ 25 | today | Swift | Codex · Claude Code |
| Ateam Agent Workbench | 64 · Some gaps | Desktop appFree + model costs | ★ 18 | today | TypeScript | Codex · Claude Code |
| Happier | 62 · Some gaps | Desktop appFree + model costs | ★ 2.2k | today | TypeScript | Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
The README says machines remain private until their owner shares them, permission requests stay visible, and the CLI entry point has application cleanup paths; AGENTS documents a local-only desktop boundary and disabled telemetry. Deductions: the sample does not show the full permission, data-transfer, or key-storage implementation or revocation/recovery behavior; dependency and security files exist, but no dependency audit evidence is supplied.
The CLI reports retained login-shell probe failures and aggregates cleanup errors, while CI configuration covers static checks and several test groups. Deductions: the material does not establish that checks ran successfully, and recovery and dependency-availability guidance is incomplete relative to the CLI's broad scope.
The README identifies ACP agents, workstations/servers/cloud VMs, and desktop, mobile, web, and CLI surfaces, with team-sharing, parallel worktree, and review scenarios. Deductions: platform boundaries are described mainly in the README and internal rules; a full support matrix and operational limits are not shown.
Repository areas, quick start, CLI documentation, release notes, contribution guidance, and an Apache-2.0 license are present; the README states mobile is under active development and local-first support is incomplete. Deductions: the sample provides no verifiable version history or named maintenance owner, and FAQ/troubleshooting coverage is limited.
Shared conversations, cross-device dispatch, visible permission requests, diff review, and agent coordination provide a concrete team workflow benefit. Deductions: use requires a compatible Node runtime, connected machines, and agents; deployment or account costs and a cost-benefit comparison are not provided.
README claims are partly corroborated by the CLI entry point, package map, test samples, CI configuration, and release notes; license and security-reporting guidance have dedicated files. Deductions: only a sample of repository files is available, and CI configuration is not evidence of executed results, so descriptive claims must remain distinct from verified outcomes.
- This assessment uses only the supplied static sample; no code, tests, or CI were executed, and files outside the packet were not inspected.
- Before adoption, review the detailed data flows, credential and key handling, permission confirmation, revocation, and recovery documentation; the sample cannot establish their completeness.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
v0.109.0 Lody OSS 0.109.0
Release notes excerpt
What's Changed * fix: compact Roost renderer change receipts by @Lampese in https://github.com/LodyAI/Lody/pull/1784 * perf: commit Roost renderer metadata with content by @Lampese in https://github.com/LodyAI/Lody/pull/1791 * docs: record packed Roost storage contract validation by @Lampese in https://github.com/LodyAI/Lody/pull/1800 * perf(roost): reuse unchanged owner projections by @Lampese in https://github.com/LodyAI/Lody/pull/1804 * perf: install certified Roost text append projections by @Lampese in https://github.com/LodyAI/Lody/pull/1806 …View on GitHub ↗ -
v0.108.0 Lody OSS 0.108.0
Release notes excerpt
What's Changed * fix: preserve Agent Role mention selection and positioning by @wibus-wee in https://github.com/LodyAI/Lody/pull/1317 * fix(e2e): realign Daily journey observations by @wibus-wee in https://github.com/LodyAI/Lody/pull/1318 * fix: recover main after accidental Roost merge by @Lampese in https://github.com/LodyAI/Lody/pull/1323 * fix: use Chromium transport for desktop OAuth by @tommy0103 in https://github.com/LodyAI/Lody/pull/1331 * fix(cli): record one failure notice for pre-prompt ACP errors by @delete-cloud in https://github.com/LodyAI/Lody/pull/1276 …View on GitHub ↗ -
v0.104.0 Lody OSS 0.104.0
Release notes excerpt
What's Changed * fix: realign daily desktop e2e journeys by @wibus-wee in https://github.com/LodyAI/Lody/pull/1134 * feat: add session document viewers and PDF controls by @wibus-wee in https://github.com/LodyAI/Lody/pull/1139 * feat: store each model's effort and Fast support in its own capability row by @zxch3n in https://github.com/LodyAI/Lody/pull/1126 * fix: pause the scroll engine while its tab is hidden by @lodystage[bot] in https://github.com/LodyAI/Lody/pull/1129 * fix: keep composer mention menu with the caret by @wibus-wee in https://github.com/LodyAI/Lody/pull/1140 …View on GitHub ↗
FAQ
Does Lody include its own coding model?
Are connected machines automatically visible to the whole team?
Can Lody operate as a fully local-first system?
Can concurrent Agent changes be isolated?
Are paid accounts or API keys required?
Is Lody open source?
Is Lody safe to use?
Is Lody still maintained?
Who makes Lody?
What is Lody's official website?
Thanks — we use this to improve the page.