Split work by responsibility
The lead proposes assignments for implementation, tests and docs. Review the members, their files and models before execution.
The lead splits the job. You approve the assignments and choose each member's model. Compatible with DeepSeek Harness plugins.
Windows · Linux · English and Chinese · Apache-2.0
Add pagination to the order API and test boundary cases.
The lead proposes assignments for implementation, tests and docs. Review the members, their files and models before execution.
Independent members work concurrently. Tasks with dependencies wait for predecessor reports. You choose the concurrency limit.
File ownership and path locks coordinate writes. The scheduler reuses running assignments when the lead dispatches them again.
Enabled dsh plugins supply tools to the lead and members. Plugin settings and interface components live in the same workspace.
Install DeepSeek Harness plugins in Micro-Multi and share their tools across the team. Manage plugin settings in the app, and add Skills or MCP services when you need them.
See supported plugins and setup →Use one agent for a small edit. Use multiple agents when a job includes implementation, tests and documentation, or spans several parts of a project.
| Problem | A single loop / uncoordinated agents | Micro-Multi |
|---|---|---|
| Waiting | Implementation, tests and docs run in sequence. | Independent tasks run together; dependent tasks wait. |
| Shared files | Concurrent edits need manual coordination. | Declared ownership and path locks coordinate writes. |
| Model choice | One model often handles every role. | Choose individual member models in the plan. |
| Retries | An assignment may be dispatched again. | Reuse running or completed assignments. |
More agents can cost more. This is an execution comparison, not a speed or price benchmark. Use only the members the job needs.
Design choices and tradeoffs →You supply the model endpoint and credentials. The app handles the conversation and workspace; your project keeps its own build tools and dependencies.
In Settings → Models, add the API base URL, model ID and key. Test the connection before starting.
Add your project and choose whether to link the original directory. Check the path before confirming.
Choose team mode, describe the job, and inspect the proposed members, files, dependencies and models.
Confirm the plan in chat. Follow each member, then check the combined diff and test output.
An Electron desktop shell runs a local Python backend. Node.js hosts the agent and plugin runtimes, while the interface shows their work and records.
Folder selection and desktop integration.
Local APIs, conversations and task execution.
The main workspace; React for native plugin components.
Native tools, services and plugin contributions.
Local records and OS-backed model credentials.
API calls, streamed replies and plugin subscriptions.
Choose a package for your system. Python and Node.js are included; install Git for repository work and any external tools your extensions require.
SHA256SUMS · Installation and Linux requirements · Run from source
Check the troubleshooting guide when something fails. You can report bugs, discuss ideas or contribute code and documentation on GitHub.