by dmae97 · MCP Server · ★ 122
OMK Run multiple coding agents safely in one repo. OMK turns a coding task into a scoped DAG run: it routes the right model, limits tool access, requires evidence, and saves replayable artifacts before claiming success. Use it when one agent is too loose, too risky, or too hard to audit. 30-second demo OMK should produce a bounded plan before changing files: Executing (not dry-run) adds loop artifacts such as and . Artifact names
| Stars | 122 |
| Forks | 14 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 71.6310197232163/100 |
| Open Issues | 8 |
| Last Updated | 2026-07-08 |
| Created | 2026-04-30 |
| Platforms | claude-code, cli, codex, mcp, node |
| Est. Tokens | ~15k |
These tools work well together with open-multi-agent-kit for enhanced workflows:
Explore other popular mcp server tools:
open-multi-agent-kit is Evidence-gated runner for Codex, Claude Code, OpenCode, and local coding agents. Routes tasks into scoped DAG lanes with replayable artifacts.. It is categorized as a MCP Server with 122 GitHub stars.
open-multi-agent-kit is primarily written in TypeScript. It covers topics such as agent-orchestration, agent-runtime, ai-coding.
You can find installation instructions and usage details in the open-multi-agent-kit GitHub repository at github.com/dmae97/open-multi-agent-kit. The project has 122 stars and 14 forks, indicating an active community.
open-multi-agent-kit is released under the MIT license, making it free to use and modify according to the license terms.