GraphCanon updated 1mo · GitHub synced 1mo
Decision brief
uzi is a CLI tool written in Go that facilitates running multiple AI code generation agents in parallel through the management of Git worktrees.
Good fit when
- When you need to manage and execute multiple coding tasks driven by AI concurrently without manual oversight, uzi's automation capabilities ensure efficient workflow management.
- If your development environment heavily relies on Git for managing branches and you want to leverage parallel execution for AI-driven coding agents, uzi optimizes this by using Git worktrees.
Avoid when
- Avoid using uzi if your project does not benefit from parallel task execution or if the code generation does not require branching through Git; its strength lies in large-scale concurrent operations.
- Do not use uzi if your workflow is more suited to a single-threaded environment or if direct interaction and manual management of AI coding agents are preferred over automated orchestration.
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (416d since push)
- As of 1mo
- Provenance
- Not a fork · Organization account
- As of 1mo
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
go get github.com/devflowinc/uzi pkg.go.devSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
A command-line interface implemented in Go that enables users to manage and run multiple AI code generation tasks concurrently using Git worktrees.
Capability facts
- Languages
- go
Source: github.language · Jul 25, 2026
Categories
Tags
README
Installation
go install github.com/devflowinc/uzi@latest
Make sure that your GOBIN is in your PATH.
export PATH="$PATH:$HOME/go/bin"
For agents
This page has a .md twin and JSON over the API.