Meldwork is a source-available Electron desktop app and local-first multi-agent collaboration workspace for developers, researchers, and technical teams who use more than one AI Agent. It brings local Agent CLIs such as Codex, Claude Code, Gemini CLI, OpenCode, and Qwen Code into one workspace for direct chats, concurrent responses, evidence-aware runs, and human-in-the-loop Agent orchestration.

The current public preview is a single-user Apple-silicon macOS work cell. You choose the participants, working directory, context, permissions, and final adoption decision. No Meldwork account, server, or hosted conversation store is required.

Download the Apple silicon macOS preview · Release notes · Architecture · Desktop guide · License

Who it is for

Use Meldwork when you:

already have multiple local Agent CLIs and need one task to span them;
need independent review for code, research, or product analysis before choosing a path;
need inspectable traces, evidence, and human review before workspace writes.

Workflow

Select the local Agents and participants.
Scope the goal, working directory, context, and permissions.
Run Direct, Concurrent Responses, or Auto Discussion V4.
Review and adopt the result, evidence, and any Human Gate before changing the workspace.

Collaboration modes

Mode	What happens	Best for
Direct	One selected Agent keeps its conversation and native session when supported.	Focused work with one Agent.
Concurrent Responses	Selected Agents receive the same frozen task snapshot and return independent replies in stable order.	Comparing approaches before choosing one.
Auto Discussion V4	Selected Agents propose, challenge, negotiate responsibilities, execute dependency-aware work, then verify the result.	Multi-round work that needs explicit responsibility and review.

Participants are always selected by the user. Automatic selection from a larger roster is outside the current preview.

See it in action

Local Agent discovery	Multi-agent review	Direct multimodal work

Example: give Codex, Claude Code, and Gemini CLI the same change-review context, compare their independent findings, then adopt only the evidence-backed result you approve.

Supported local Agent CLIs

Meldwork detects and invokes an installed command when its adapter and the CLI version are compatible:

Codex (codex) · Hermes (hermes) · OpenClaw (openclaw) · WorkBuddy (codebuddy) · Pi Agent (pi, pi-agent, piagent) · Kimi Code (kimi) · MiMo Code (mimo) · Claude Code (claude) · Gemini CLI (gemini) · OpenCode (opencode) · Qwen Code (qwen) · OpenCodeReview (ocr)

Approved Agent Connectors can be added through the Agent Connector SDK; custom executable Agents use the desktop custom-Agent path. See the desktop guide for the full adapter and capability matrix.

Quick start

Apple silicon macOS preview

Download Meldwork-0.1.3-arm64.dmg from the official V1.0.3 prerelease, move Meldwork to Applications, and install at least one supported local Agent CLI. The prerelease is ad-hoc signed and not notarized; macOS may require Open Anyway in System Settings -> Privacy & Security on first launch.

Run from source

Prerequisites: Node.js 22.12+ and npm.

npm --prefix frontend ci
npm --prefix desktop ci
npm --prefix desktop run dev

Before distributing a build:

npm --prefix frontend test
npm --prefix frontend run build
npm --prefix frontend run build:desktop
npm --prefix desktop test

Current boundary

Meldwork is a local Electron app, not a hosted Agent fleet or a general Agent framework. The current preview does not provide remote/cloud/channel Agent execution, automatic participant selection, enterprise SSO/RBAC/governance, or an Outcome Network. Local-first does not mean fully offline: a selected Agent may send prompts, attachments, or Skills to its configured Provider. Workspace writes are opt-in workflow controls, not an operating-system sandbox.

Docs

License

Meldwork is licensed under the Apache License 2.0. You may use, modify, and redistribute the repository under its terms; third-party Agent products, models, dependencies, and brand assets remain subject to their own licenses and notices.

Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.

agent-collaboration agent-orchestration agent-workforce ai-agent ai-agent-workspace human-in-the-loop local-ai multi-agent-collaboration multi-agent-system

Readme Apache-2.0

71 MiB

0 Stars 1 Watchers 0 Forks