English · 简体中文

Meldwork builds the organization layer for AI agents.

Most tools help humans run more agents. Meldwork is built for a different job: make multi-agent work legible, accountable, and reusable.

The current preview is a local work cell for supported Agent CLIs. It keeps participants explicit, context scoped, collaboration bounded, run state inspectable, and human review in the loop. Selected Agents can now respond concurrently or move through independent proposals, peer negotiation, responsibility-based work, single-writer integration, and independent verification around one goal.

Download Meldwork V1.0.4 for Apple silicon macOS · Architecture · 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

1. Select the local Agents and participants.
2. Scope the goal, working directory, context, and permissions.
3. Run Direct, Concurrent Responses, or Auto Discussion V4.
4. 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	The first round runs concurrent proposals. Later turns follow the discussion: one Agent can route the next turn with @Agent, or several Agents can be selected for a concurrent response. Native Agent sessions continue across rounds.	Multi-round work that benefits from discussion, flexible routing, and review.

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

How Meldwork differs

Meldwork is a local-first AI Agent workspace for multi-Agent review and decision traceability, not a terminal, cloud Agent fleet, communication network, or programmable orchestration framework. It connects the local Agent tools you already use to a decision-ready review workflow and keeps independent findings, evidence, responsibility, and the human adoption decision visible in one local work cell.

Project	Category	What it focuses on	Meldwork's difference
Buzz	Agent communication network	Identity, channels, events, and persistent collaboration.	Case-scoped independent judgments with evidence-backed Decision and Disposition.
Pragma	Method and workflow runtime	Reusable Expert, Flow, Memory, Evaluation, and DSL assets.	Keeps disagreement, re-checks, and adoption records visible before a workflow is fixed.
Munder Difflin	Visual Agent company	Boss -> Manager -> Workers, with task and activity status.	Tracks Finding -> Evidence -> Decision -> Disposition without hiding dissent behind a central manager.
Superset / Conductor / Vibe Kanban	Parallel coding workspaces	Parallel coding Agents, isolated workspaces, diffs, and merges.	Local-first review across heterogeneous CLIs, not terminal count, worktree throughput, or cloud sandboxes.
cmux	Agent-native terminal	Low-friction terminals, notifications, and multitasking.	Adds frozen context, independent results, and a human adoption gate.
Nimbalyst	Agent and artifact workspace	Parallel Agents with Markdown, mockups, and diagrams.	Places evidence and accountable decisions alongside artifacts.
Paperclip	Agent organization management	Companies, roles, budgets, approvals, and org charts.	Grounds responsibility in real findings and outcomes, not a virtual company.
MCP Agent Mail	Agent communication infrastructure	Identity, inboxes, threads, and advisory file leases.	Preserves Case and review semantics above the transport layer.
LangGraph / CrewAI / AutoGen / OpenAI Agents SDK / Google ADK	Programmable multi-Agent frameworks	Graphs, roles, routing, tools, and approvals for developers.	Delivers a desktop review workflow without requiring teams to build an orchestration framework.
Warp Oz / Devin / Factory / OpenHands Cloud	Cloud Agent control planes	Hosted sandboxes, remote execution, and Agent fleets.	Runs in the user's local Electron work cell with existing CLIs and local data boundaries.

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	Hermes	OpenClaw	WorkBuddy	Pi Agent	Kimi Code
MiMo Code	Claude Code	Gemini CLI	OpenCode	Qwen Code	OpenCodeReview

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-0.1.4-arm64.dmg from the official V1.0.4 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

• Architecture and product boundary
• Desktop setup and Agent matrix
• Agent Connector SDK
• AI discoverability index
• Contributing
• Security policy

License

Meldwork is source-available under the Meldwork Non-Commercial Source License 1.0. You may inspect, run, modify, and share it for non-commercial purposes. Commercial use requires prior written permission; see COMMERCIAL_USE.md.