Run staged teams of AI agents from a desktop workspace.
Sources and review #
Checked against public documentation on . Suitability guidance is our editorial judgment; this is not a performance benchmark or an endorsement.
People coordinating staged agent work from a desktop while choosing their own model connections.
You need an agent workspace without local hardware requirements or assume connected model usage is included for free.
About Bees #
Bees is a desktop workspace for multi-agent processes, scheduled tasks and local knowledge search. It connects existing agent clients or local and hosted models to MCP tools, with staged work and reviewer roles. Public desktop source is available under a choice of MIT or Apache-2.0, with released desktop installers. Model subscriptions, API usage and local hardware are separate costs; the publisher currently offers cloud coordination without a paid plan. Installation, privacy boundaries and approval enforcement were not tested.
Bees is listed with an open-source pricing classification written primarily in JavaScript, with 13 stars on GitHub. Its latest recorded repository push was in October 2026; that is not an ASE editorial review date.
Make your product part of the discovery. Explore advertising
Bees and related category tools #
| Record | Stars | Pricing | ||
|---|---|---|---|---|
| Beesthis listing | 13 | JavaScript | MIT OR Apache-2.0 | Open source |
| [n8n](https://agentsearchengine.app/agents/n8n) | 207k | TypeScript | — | Open source |
| [dify](https://agentsearchengine.app/agents/dify) | 158k | TypeScript | — | Open source |
| [Langflow](https://agentsearchengine.app/agents/langflow) | 156k | Python | MIT | Open source |
| [Sim](https://agentsearchengine.app/agents/sim) | 30k | TypeScript | Apache-2.0 | Open source |
| activepieces | 25k | TypeScript | — | Open source |