Banteg Agent Workflows
Isolate Codex and Claude coding tasks with worktrees, sandboxes, and devcontainers.
- Source repo
- banteg/agents
- Stars
- ★ 371
- Last updated
- 5mo ago
- Primary language
- Python
- FA score
- 47/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformCodex · Claude CodeChatGPT · Claude.ai (Partial support)
- Cost
- Free software; you pay for model usage
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- A developer running several coding assistants concurrently can assign each task its own worktree so their changing files do not interfere.
- Not a fit if
- Teams that need one entry point, a config contract, or a stable API
- Users off macOS who want a ready cross-platform sandbox
- Anyone unwilling to assemble Git, Homebrew, Docker, and GitHub CLI themselves
- Source review
- 47/100 · Major gaps
What does this agent do, and when should you use it?
This repository is a personal collection of workflows and helper scripts for coding assistants such as Codex and Claude Code, not a standalone general-purpose agent. Its central pattern is to create a separate Git worktree for each task, commit the result there, and then either discard the branch or open a pull request. It also documents macOS Seatbelt sandboxing, unattended devcontainer execution, archive-based code review, Telegram control, and completion notifications. The interfaces are command-line tools including Git, git-wt, Worktrunk, GitHub CLI, devc, and takopi, with outputs such as commits, branches, pull requests, ZIP archives, Git bundles, and notification messages. Its deployment boundary is primarily a local repository and shell, with Docker available for isolation; each workflow has its own dependencies rather than a single installation entry point.
A typical flow starts from a local Git repository and uses git wt feat/branch or wt switch -c -x codex feat/branch to create and enter an isolated worktree where a coding assistant edits files. The user can then run wt step commit to prepare a commit from the diff and prior commit style, or gh pr create to open a pull request. Afterward, wt merge can squash, rebase, merge into master, and remove the worktree and branch; git wt -d, git wt -D, and wt remove provide other cleanup paths. Claude Code can be placed inside the macOS Seatbelt sandbox through ~/.claude/settings.json, limiting writes outside the project and restricting network access. For unattended work, the included devcontainer/install.sh installs devc, which opens a tmux environment with Claude and Codex. Review inputs are produced with git archive as ZIP files or git bundle create repo.bundle --all when commit history is needed; takopi supplies Telegram control and resumable sessions, while the Codex notify script provides completion messages.
- A developer running several coding assistants concurrently can assign each task its own worktree so their changing files do not interfere.
- A macOS Claude Code user facing repeated permission prompts can enable Seatbelt and automatically allow Bash commands that are already sandboxed.
- A developer who wants Codex or Claude to run unattended can place the session in the documented Docker devcontainer and tmux environment.
- A maintainer requesting architecture, refactoring, debugging, or next-fix analysis from GPT, Claude, or Gemini can upload a Git-generated ZIP or bundle.
- A user who wants to monitor and resume coding sessions from a phone can adopt takopi, while someone needing only completion alerts can use the Telegram notify script.
How do you install or deploy this agent?
There is no single package, global installer, or complete dependency manifest for the repository; each workflow is configured separately. For the lightweight worktree option on a Homebrew system, run brew install k1LoW/tap/git-wt, add .worktrees to ~/.gitignore_global, and run git config wt.basedir .worktrees. Relative worktree paths require Git 2.48 or newer: enable them with git config --global worktree.useRelativePaths true and migrate existing worktrees with git worktree repair. The devcontainer path requires Docker—the author prefers OrbStack—and installs devc from the repository with ./devcontainer/install.sh self-install. Full Telegram control is installed with uv tool install takopi. The supplied material does not give a unified installation procedure for Worktrunk, the Codex notify script, or every runtime dependency.
How do you use this agent?
Run git wt feat/branch to create or switch to an isolated task, then clean it up with git wt -d feat/branch for a soft deletion or git wt -D feat/branch for a hard deletion of the worktree and branch. With Worktrunk, use wt switch -c -x codex feat/branch to create the worktree and launch Codex, wt step commit to prepare a commit, wt merge to merge and clean up, or wt remove to remove and prune. After installing the devcontainer helper, invoke devc /path/to/repo to enter tmux with Claude and Codex. For model review, create a repository snapshot with git archive HEAD -o code.zip, limit it to src with git archive HEAD:src -o src.zip, or preserve history with git bundle create repo.bundle --all. A pull request can be opened with gh pr create; this requires GitHub access and authentication, although credential setup is not documented in the supplied material.
What are this agent's strengths and limitations?
- Separate Git worktrees give concurrent coding tasks concrete filesystem isolation and reduce collisions between assistants.
- It offers both the small git-wt wrapper and the more complete Worktrunk lifecycle covering creation, commits, merging, and cleanup.
- The workflows span local sandboxing, container isolation, remote Telegram control, and simple notifications, allowing different levels of automation.
git archiveandgit bundleprovide compact, Git-native ways to deliver either a tracked snapshot or repository history for review.
- This is a personal workflow collection rather than a cohesive agent with one entry point, configuration contract, or stable API.
- Different features depend on Git, Homebrew, Docker, GitHub CLI, uv, takopi, or third-party worktree wrappers that adopters must assemble themselves.
- The Seatbelt setup is specific to Claude Code on macOS and is not a cross-platform sandbox solution.
- The supplied material documents no test coverage, compatibility matrix, release policy, or failure-recovery procedure.
- Commands such as
git wt -D,wt merge, and cleanup operations remove worktrees or branches, so uncommitted work must be handled carefully.
How does this agent compare with similar options?
git-wt is presented as a simple wrapper for common worktree operations, while Worktrunk is the fuller option aligned with the create → pull request → merge → cleanup cycle and adds features such as install hooks and commit generation through the llm CLI. For repository review, the workflow favors native git archive or git bundle output over large XML or Markdown exports from repomix or code2prompt. For notifications, takopi provides streamed progress and resumable remote sessions, whereas the Codex notify script only sends a simple completion message.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Banteg Agent Workflows This agent | 47 · Major gaps | CLIFree + model costs | ★ 371 | 5mo ago | Python | Codex · Claude Code |
| SWE-AF Engineering Factory | 55 · Major gaps | CLIFree + model costs | ★ 1.1k | 4d ago | Go | ChatGPT · Codex · Claude Code · OpenAI API · Claude API |
| Alas Agent Workspace | 79 · Good | Desktop appFree + model costs | ★ 24 | today | Swift | Codex · Claude Code |
| dev-3.0 | 76 · Good | Desktop app | ★ 329 | today | TypeScript | Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
The README says Seatbelt sandboxing limits writes to the project directory and restricts network access, and mentions devcontainer isolation. It also recommends auto-approving bash, unattended operation, and full Telegram control, without explaining sensitive-data handling, confirmation for external effects, or rollback. Those gaps lower the related scores. Git worktree, GitHub CLI, Telegram, and other tools are named, supporting source attribution.
The README is broadly consistent across its worktree, sandbox, devcontainer, planning and review, and notification workflows. However, key capabilities depend on external tools, with no version pinning, availability guarantees, or failure guidance, so dependency availability and failure messages score lower.
It targets developers using coding agents such as Codex and Claude, and gives scenarios for isolated work, unattended runs, code review, and notifications, with concrete commands and configuration. It says little about capability boundaries or compatibility limits across environments.
The README is organized by workflow and includes installation, configuration, and command examples. Naming and maintenance responsibility have only limited clues; there is no license information or version and change history, and platform and version limits appear only incidentally.
Commands, configuration snippets, and recommendations are directly usable in common agent development workflows. Worktree isolation and packaging repository context also offer concrete value. Benefits are mostly stated as the author's experience, with no outcome evaluation or cost comparison, so full marks are not justified.
Several recommendations can be traced to named tools and concrete configuration. The supplied evidence is only a README, however, so other source files do not corroborate its functional claims. The document distinguishes personal preference from actionable steps and does not present experience as a test result.
- The README recommends auto-approval and unattended operation; verify that the sandbox's limits on project data, network access, and external actions fit the intended use.
- Some workflows remove worktrees and branches or control agents through Telegram; the README does not describe recovery steps or sensitive-data protections.
Maintain this project? Add the FARS badge to your README
[](https://followagents.com/en/agents/banteg-agents)<a href="https://followagents.com/en/agents/banteg-agents"><img src="https://followagents.com/badge/banteg-agents.svg" alt="FARS review"></a>FAQ
Is this a deployable autonomous agent?
Is Docker mandatory?
Which steps require network access or accounts?
gh pr create requires GitHub access and authentication, while takopi and the notify script communicate through Telegram. Local worktree, archive, and bundle operations can run against the local repository.Will these workflows work on Windows or Linux?
What is the main operational risk?
git wt -D path. No automatic backup or recovery mechanism is documented.Thanks — we use this to improve the page.