by jerryfane · Agent Tool · ★ 52
Gitmoot Local-first multi-agent coordination for GitHub pull request workflows. Gitmoot lets humans and AI agents collaborate through the place software teams already audit work: GitHub pull requests. It runs on the user's machine, keeps workflow state in local SQLite, routes PR comments to registered agent runtimes, and writes the agent's work back into the repo and PR discussion. V1 is intentionally local-only. There is no hosted dashboard, webhook receiver, cloud runner, or remote control plane. Why Gitmoot AI agents can already edit code, review diffs, and run local tools.
| Stars | 52 |
| Forks | 43 |
| Language | Go |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 67.5731744340694/100 |
| Open Issues | 17 |
| Last Updated | 2026-07-08 |
| Created | 2026-05-20 |
| Platforms | go |
| Est. Tokens | ~20k |
These tools work well together with gitmoot for enhanced workflows:
Explore other popular agent tool tools:
gitmoot is A local-first control layer for AI agents. It is categorized as a Agent Tool with 52 GitHub stars.
gitmoot is primarily written in Go. It covers topics such as agentic-skill, agentic-workflows, agents.
You can find installation instructions and usage details in the gitmoot GitHub repository at github.com/jerryfane/gitmoot. The project has 52 stars and 43 forks, indicating an active community.
gitmoot is released under the Apache-2.0 license, making it free to use and modify according to the license terms.