Privacy and advertising choices

Git-Stars uses essential storage for site operation. Optional analytics and ad-measurement scripts stay disabled unless you accept them; partners such as Google may then use cookies or similar identifiers where required. Privacy Policy

LogoGit-Stars
Top StarsTrendingAI AgentsDaily PicksViral ReposInsights
LogoGit-Stars

Discover top GitHub projects with real rankings and AI insights

GitHub
Built withLogo of Git-StarsGit-Stars
Rankings
  • Top Stars
  • Trending
  • AI Agents
  • Daily Picks
  • Explore
Resources
  • Insights
  • Editorial Policy
About
  • About
  • Contact
Legal
  • Privacy Policy
  • Terms of Service
© 2026 Git-Stars. All Rights Reserved.
FI

kunchenguid/firstmate

AI Agent

Talk to one agent. Ship with a crew.

3.4k Stars1.1k Forks834 Open Issues3.4k WatchersShellMIT
AI AgentUI Framework
Review Readiness

This repository page has enough original analysis, source evidence, and comparison context to be treated as an indexable Git-Stars review.

100

review score

Indexable review
Decision Snapshot

Problem solved

It solves the coordination and supervision problem of running multiple coding agents in parallel, which typically requires manual session management, context copying, and risk of collisions. By centralizing communication through one agent and using disposable worktrees, it enables safe concurrent work on a single repo without developer babysitting.

Deployment reality

The available setup signal starts with: git clone https://github.com/kunchenguid/firstmate && cd firstmate. Treat this as a starting point, then ask Codex or Claude to inspect the README, environment variables, runtime version, and deployment target before production use.

Commercial use

The recorded license is MIT. This is a useful commercial-use signal, but teams should still verify license text, dependencies, model/API terms, and trademark constraints.

Capability ceiling

Developers can build and manage fleets of autonomous coding agents for parallel tasks such as bug fixes, code reviews, feature development, and research reports. The system supports multiple project modes (no-mistakes, direct-PR, local-only), optional persistent secondmates on remote hosts, and integration with social platforms via Relay. The ceiling includes orchestrating large-scale, multi-repo, multi-agent workflows with strict project boundaries and restart-proof state management.

Source and compliance noteLast synced: Aug 13, 2026

Git-Stars is independent and not affiliated with GitHub or this project. Analysis may be AI-assisted and based on public repository metadata plus short README-derived summaries. We do not mirror full README files, docs, issues, or social comments.

Original GitHub sourceMethodologyEditorial Policy
Editorial Evaluation

kunchenguid/firstmate is tracked as a Shell project in the AI Agent, UI Framework area. This evaluation combines public GitHub metadata, category signals, short source summaries, and Git-Stars editorial rules rather than copying project documentation.

Momentum check: the repository has 3.4k total stars, with +0 today, +0 this week, and +2.2k this month. These growth windows help distinguish durable adoption from short-lived visibility spikes.

Maintenance check: current activity is Moderate; the latest push was 62 days ago, and the open issue queue is 834, about 24.57% of total stars. Treat this as an adoption signal, not a substitute for engineering due diligence.

Adoption check: 1.1k forks and 3.4k watchers suggest how often the project is reused or followed. License signal: MIT. Always verify license compatibility before commercial or internal use.

Practical fit: this project is most relevant when you need Shell teams evaluating ecosystem-native tooling. Be cautious when you have low tolerance for large unresolved issue queues.

Source check: Git-Stars currently has 2 explicit source reference(s) for this report and a recent growth signal of 2.2k. Follow the original GitHub repository for final install, security, and release information.

Evidence Checklist

Analysis

Ready

Original problem, capability, and verdict guidance are available.

Sources

Ready

Repository metadata and README/source references are attached.

License

Ready

MIT is recorded for review.

Maintenance

Ready

Recent activity is visible in repository metadata.

Alternatives

Ready

Enough nearby projects exist for comparison.

Best For
  • Shell teams evaluating ecosystem-native tooling
Avoid When
  • you have low tolerance for large unresolved issue queues
  • you need a legal review, security audit, or production SLA
Adoption Signals

Momentum

3.4k Stars

Reuse

1.1k Forks

Attention

3.4k Watchers

Maintenance

moderate

License

MIT

Open issues

834

Overview

firstmate is an agent distro for running a crew of coding agents. You talk to a single agent (the first mate) that spawns and supervises autonomous agents in visible session backends, each with clean git worktrees, and delivers finished PRs, local merges, or investigation reports. It is not a model or CLI but a portable directory of instructions, skills, and policies that turns a general-purpose agent into a specialized one.

Key Features

- One liaison: you talk only to the first mate, which dispatches and supervises crewmates. - Visible crew: each crewmate runs in its own tmux window, herdr/zellij tab, cmux workspace, or Orca terminal. - Disposable worktrees: each task runs in a clean git worktree to avoid collisions. - Two task shapes: ship tasks deliver changes; scout tasks produce investigation reports. - Explicit project modes: no-mistakes, direct-PR, or local-only, with optional +yolo autonomy flag. - Optional secondmates: persistent agents with isolated homes, locally or on SSH hosts. - Event-driven supervision: a bash watcher wakes the first mate only when needed. - Optional Relay: integrates with X and Discord for public mentions. - Strict project boundary: first mate is read-only except for guarded operations. - Restart-proof: state on disk and in session backend; sessions can be killed and reconciled.

Tool Positioning

AI Agent

Agent frameworks, autonomous workflows, and tool-use systems

UI Framework

Frontend frameworks, design systems, and interface libraries

Quick Start
git clone https://github.com/kunchenguid/firstmate && cd firstmate
View on GitHub
Project Activity

63

Health Score

Moderate

Commit Activity

Jun 12, 2026

Created

Aug 12, 2026

Last push

Source Trail

GitHub repository metadata

metadata

GitHub README

readme_summary

Star History

Star history will appear after daily syncs accumulate data.

Community Health
1.1k

Forks

834

Open

3.4k

Watchers

Owner
FI

kunchenguid

GitHub profile
Topics & Language
Shell
Ecosystem & Usage
GitHub Repository
Alternatives & Comparison

codecrafters-io/build-your-own-x

Master programming by recreating your favorite technologies from scratch.

540k

sindresorhus/awesome

😎 Awesome lists about all kinds of interesting topics

496k

freeCodeCamp/freeCodeCamp

freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

454k

EbookFoundation/free-programming-books

:books: Freely available programming books

394k

nilbuild/developer-roadmap

Interactive roadmaps, guides and other educational content to help developers grow in their careers.

365k
License
MIT
CreatedJun 12, 2026
Last pushAug 12, 2026
Last syncedAug 13, 2026
Repository Standards

✓

License

✓

Forked

~ Moderate

Maintained

AI AnalysisAnalyzed by Git-Stars

Problem Solved

It solves the coordination and supervision problem of running multiple coding agents in parallel, which typically requires manual session management, context copying, and risk of collisions. By centralizing communication through one agent and using disposable worktrees, it enables safe concurrent work on a single repo without developer babysitting.

Capabilities

Developers can build and manage fleets of autonomous coding agents for parallel tasks such as bug fixes, code reviews, feature development, and research reports. The system supports multiple project modes (no-mistakes, direct-PR, local-only), optional persistent secondmates on remote hosts, and integration with social platforms via Relay. The ceiling includes orchestrating large-scale, multi-repo, multi-agent workflows with strict project boundaries and restart-proof state management.

Bottom Line

This is for developers who need to scale their coding agent usage beyond single tasks and want a structured, supervised way to run parallel agents without constant manual oversight. It is not for those who prefer a simple CLI or who are uncomfortable with complex orchestration layers. The key trade-off is the learning curve and setup complexity in exchange for significant productivity gains in multi-agent workflows.

Full AI Analysis