AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Dev Tooling/
Lody
Lody logo

Lody

Active·★ 1.6k·Apache-2.0·Updated 2026-10-27

Lody is an Apache-2.0 workspace for the coding agents a team already uses. You connect a laptop, workstation, server or cloud VM with npx lody daemon start, bring any ACP-compatible agent such as Claude Code, Codex, Kimi or OpenCode, and keep the logins, subscriptions and permission modes configured on that machine. Teammates can open the same conversation and see the transcript, runtime status, files and code changes, then add instructions without passing screenshots around.

Work can be dispatched to any connected machine from desktop, mobile, web or CLI, and the CLI also scripts sessions with JSON output. Agents get tools to spawn and coordinate child conversations, each session can have its own Git worktree, and diffs, line comments, PR status and CI sit beside the conversation. The mobile apps handle permission approvals and iOS Live Activities. The README says Lody is still moving toward full local-first support and that its end-to-end encryption package is not yet wired into the product.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#coding-agents#acp#team-collaboration#claude-code#codex#mobile#worktrees
↗ Visit site★ GitHub
01

Features

01Shared agent conversations with transcript, files and diffs
02Connect any machine with npx lody daemon start
03Agents can create and coordinate child conversations
04Per-session Git worktrees keep parallel work isolated
05Mobile approvals, notifications and iOS Live Activities
02

Why choose it

+Teammates can open the same agent conversation with its full transcript, diffs and status
+Keeps each machine's existing Claude Code or Codex logins and subscriptions
+Approve agent permission requests and follow progress from your phone
03

Trade-offs

!Sign-in to a Lody workspace is required, and full local-first support is still in progress.
!End-to-end encryption exists as a library but is not yet wired into the product.
!Only agents that speak ACP can be connected.
04

Maintenance check

ActiveChecked: 2026-10-27
Last commit
2026-10-27
Commits, last 90 days
100+
Releases, last 90 days
5
Latest release
v0.108.0 (2026-10-24)
Open issues
250
Recent issues with at least one comment
0/4

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #507 [E2E] Daily desktop journey failure44 comments · 2026-09-08
  • #930 [Feature Request] Add a built-in Oh My Pi ACP adapter9 comments · 2026-09-24
  • #104 [Feature Request] Add global and provider-level controls to disable MCP5 comments · 2026-08-28
  • #1501 [Feature Request] 支持 Codex ultrafast 模式4 comments · 2026-10-12
  • #1028 [Bug] Machine access registration fails with a Server Error on every daemon start, leaving the live machine unauthorized (session create say4 comments · 2026-09-26

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Use cases

↳Teams sharing and reviewing coding agent sessions
↳Dispatching agent work to a remote workstation from a phone
↳Running parallel agent tasks in separate worktrees
06

Alternatives

⚡Top VS:
VSzeroshot★2.0k→VSai-devkit★1.7k→VSagentpack★18→VSawesome-gamedev-agent-skills★5.1k→
zeroshot logo
zeroshot★ 2.0k
Open-source meta-harness for coding agents. Define your own workflows, reviewers and repair loops. zeroshot enforces the process you configure.
VSCompare→
ai-devkit logo
ai-devkit★ 1.7k
The control plane for AI coding agents.
VSCompare→
agentpack logo
agentpack★ 18
Local task-state ledger for AI coding agents. Preserve decisions, source conclusions, evidence, and checkpoints across Codex, Claude Code, Cursor, and other MCP clients.
VSCompare→
awesome-gamedev-agent-skills logo
awesome-gamedev-agent-skills★ 5.1k
74 game-dev skills for AI coding agents — Godot, Unity, Unreal, Phaser, PixiJS, three.js, Bevy, pygame, LÖVE, Roblox. Portable SKILL.md Agent Skills (the format Anthropic launched as Claude Skills), with a router that loads the right skill for your engine and task. Runs in Claude Code, Cursor, Kiro, Codex, Copilot, Gemini CLI and more.
VSCompare→
kungfu logo
kungfu★ 4.5k
Your agents don’t hand off the work. Kungfu keeps the same Work moving across Codex, Claude, OpenCode, and your own execution surface.
VSCompare→
oh-my-hermes logo
oh-my-hermes★ 4.4k
The packages for Hermes Agent ⚚ skills, coding harness, long-term memory, model optimized subagent & bot team workflows
VSCompare→
elephant-goldfish-model logo
elephant-goldfish-model★ 3.1k
Open-source skills for designing and reviewing software with AI agents
VSCompare→
agent-orchestrator logo
agent-orchestrator★ 13.8k
Open-source (Apache-2.0) orchestrator for Claude Code, Codex & 30+ coding agents. Plan, run and supervise agent teams from task to merged PR. Desktop (macOS, Windows, Linux) + iPhone & Android apps.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Use cases06Alternatives
LodyAI /
Lody
↗

Shared team workspace for Claude Code, Codex and other ACP agents, reachable from desktop, phone, web or CLI

1.6kApache-2.0
Last commit1d ago
StatusActive
CategoryDev Tooling
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.