Understand the project
Practical overview
When it fits
Use Linkwork when AI work needs multiple managed workers, isolated execution environments, scheduled tasks or governed movement from agent output into engineering workflows.
Who it is for
- Engineering teams building coordinated AI worker systems
- Organizations operating agent workloads in containerized or Kubernetes environments
- Teams that need scheduled execution, controlled tool access and traceable deliverables
Documented uses
- Define specialized AI worker roles with responsibilities and permissions
- Package reusable Skills into versioned role images
- Connect external capabilities through an MCP tool gateway
- Schedule and scale agent workloads on Kubernetes
- Send task results into Git or open-source delivery workflows
Before you choose
Requirements & limits
The project is presented as an open-source public GitHub repository under the Apache-2.0 license. The documented platform targets Docker, cloud, self-hosted and server environments.
- A Kubernetes cluster is part of the documented runtime architecture.
- Role capabilities, MCP configuration and security policies are embedded at build time; configuration changes require rebuilding the image.
- MCP is used as the tool integration layer, with a gateway for authentication, health checks and metering.
- The platform separates role, Skill and tool permissions into three capability layers.
- Task outputs can be delivered through Git or open-source modes rather than remaining only as conversational responses.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Evidence and transparency
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 3 October 2026
- Original website title
- momotech/LinkWork · Official homepage title · retained in its source language