Download V1.0.8
LOCAL-FIRST · MULTI-AGENT COLLABORATION
Meldwork is a local-first multi-Agent collaboration workspace. Your existing Agents share context, discuss approaches, carry out authorized work, and check results — with less relaying and coordinating from you. Set the goal and permissions, then step in when they need information or a key decision.
DETECTED ON YOUR MACHINE
Meldwork detects a compatible local Agent command and exposes its readiness, capabilities, and session behavior. Approved Agent Connectors can be added through the Agent Connector SDK.
THE SHORT ANSWER
Meldwork is a local-first multi-Agent collaboration workspace for research, analysis, writing, planning, review, and implementation. Selected Agents advance the same task through discussion, authorized execution, and peer review. You set the boundaries and make key decisions when needed.
Codex, Claude Code, Gemini CLI, Qwen Code, Kimi Code, MiMo Code, OpenCode, OpenCodeReview, Hermes, Zcode, Pi Agent, OpenClaw, WorkBuddy — detected natively on your machine.
Direct · Concurrent Responses · Auto Discussion
Agents build on peer contributions and request the next steps, reducing manual coordination.
macOS · Apple silicon · Electron
Local conversations and run history; models may use external providers.
THE WORK CELL
Choose the local Agents and participants. Participants are always selected by you — never auto-assigned from a roster.
Bound the goal, working directory, context, and permissions. Every run starts from a frozen task snapshot.
Start Auto Discussion so Agents can discuss, request contributions, carry out authorized work, and check deliverables.
Step in for missing information, permissions, or key decisions. Check the deliverables and request changes when needed.
COLLABORATION MODES
Work with one Agent, compare independent replies, or let a group advance a task together.
One selected Agent keeps its conversation and native session when supported.
Best for focused work with one Agent.Selected Agents receive the same frozen task snapshot and return independent replies in stable order.
Best for comparing approaches before choosing one.Agents propose, discuss differences, request peer contributions, carry out authorized work, and check results.
Best for multi-step work with less manual coordination.INSIDE AUTO DISCUSSION
From a mention to a shared plan. Watch Agents take a code review forward.
Review this code change. Find risks and suggest improvements.
CodexStartingI’ll map the change and bring in two peers to check edge cases and implementation.
CodexPeer request@Hermes, check requirements and edge cases. @OpenCodeReview, review the implementation and tests.
HermesEdge casesCheck empty input and retry behavior so the task can recover from failures.
OpenCodeReviewImplementation reviewThe approach looks viable. Add a retry test and check that errors are clear.
CodexNext stepsNext: cover empty input, add a retry test, and improve error messages for your review.
INSIDE THE WORK CELL
Pick the participants before any work runs. Meldwork detects installed CLIs and shows their adapter status.
Agents compare approaches and check each other's contributions in the same task context.
Agents discuss, request contributions, and advance authorized work across rounds. Step in when a decision needs you.
Work with one Agent and continue its native session when supported. Keep the conversation and results together.
Try a task such as reviewing a PR, analyzing a bug, or drafting a plan. Choose compatible Agents, give them shared context, and start Auto Discussion. They can compare approaches, request further work, and check deliverables. Authorize workspace writes when implementation is needed, and respond when they need a key decision.
HOW MELDWORK DIFFERS
Meldwork brings the Agent tools you already run into a local-first collaboration workspace. Let the group discuss and advance the task, while you focus on the goal, boundaries, and key decisions.
Agents can request a peer's input or review, and the delivery owner judges whether more work or a user decision is needed.
Enable workspace writes for implementation tasks. Agents can carry out work within that scope and ask peers to check the deliverables.
Runs in your Electron work cell with existing CLIs. No cloud Agent fleet, no required server, conversations stay local.
Keep the brief, peer replies, run state, and deliverables together so you can revisit progress and continue the work.
WHERE MELDWORK FITS
Meldwork focuses on shared tasks across the local Agent tools you choose. Here is how that focus relates to other ways of organizing Agent work.
THE BOUNDARY
ANSWERS
Short, honest answers — the long versions live in architecture.md ↗.
Meldwork is a local-first multi-Agent collaboration workspace for macOS. It brings your existing Agents into one working group to share context, discuss approaches, carry out authorized work, and check results. You choose the participants, set goals and permissions, and step in when information or key decisions are needed.
Meldwork stores conversations and coordinates work locally. Selected Agents may send prompts, attachments, or Skills to the model provider configured in their own CLI. Local-first describes where Meldwork stores and coordinates the work; it does not mean the model runs offline.
Thirteen today — Codex, Claude Code, Gemini CLI, Qwen Code, Kimi Code, MiMo Code, OpenCode, OpenCodeReview, Hermes, Zcode, Pi Agent, OpenClaw, and WorkBuddy. Approved Agent Connectors can be added through the Agent Connector SDK; custom executables use the desktop custom-Agent path.
Selected Agents start with independent proposals, then discuss differences, request peer contributions, carry out authorized work, and check deliverables. A delivery owner judges progress and whether more work or a user decision is needed. You do not need to direct every round, but missing information, permissions, or key decisions can still require your input.
Meldwork adds task-level collaboration across selected Agent CLIs: shared context, peer discussion, requests for further contributions, authorized execution, and review of deliverables. This reduces the work of relaying replies and coordinating next steps yourself. Collaboration history and run state stay local so you can revisit progress and blockers.
You choose the Agents, goal, context, and permissions. Auto Discussion lets Agents advance the work without you directing each turn, but missing information, permission requests, or key tradeoffs may require your input. Workspace writes are opt-in. Check important deliverables before using them; peer review does not guarantee correctness.
Open source under the Apache License 2.0. Commercial use, private use, modification, and redistribution are permitted under the license terms. No separate commercial authorization or license fee is required. Apache-2.0 does not grant trademark rights — see COMMERCIAL_USE.md ↗.
The current V1.0.8 preview targets Apple silicon macOS (ad-hoc signed, not notarized — open Open Anyway in System Settings → Privacy & Security on first launch). Cross-platform builds are on the roadmap; the app is Electron so the same source compiles everywhere once those targets land.
OpenClaw
WorkBuddy
Zcode
Pi Agent
MiMo Code
OpenCode