#7272nd of 143 in Coding agents and AI editors
zeroshot
Runs coding agents through enforced review-and-repair graphs you define
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 2k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Rust
1,355 on 31 Mar 20262,019 on 20 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
zeroshot runs a worker agent, independent reviewers and repair loops as a graph with engine-enforced review gates and retry limits. Each node can use its own model and harness (Pi, Claude Code, Codex or Copilot), and graphs plus runtime settings can be saved as reusable profiles. Runs are logged to a SQLite ledger, and delivery can stay local or push, open a PR, or merge.
Who it is for: Engineers running coding agents who want enforced review and repair loops
Strengths
- Review gates and retry limits are enforced by the engine, not by prompts
- Per-node model and harness choice across Pi, Claude Code, Codex and Copilot
- Events go to a durable SQLite ledger; failed runs can be restarted or resumed
- Delivery levels: local, --push, --pr, --ship; self-hostable Docker target
Weaknesses
- Needs an installed, signed-in harness CLI such as Codex or Claude Code
- PR and ship delivery supports GitHub only; local runs also need gh
- Docker and cloud runs require an exact Git source
- A passing run only means the configured checks accepted the work
What it needs
- no GPU
- Docker
- Needs Node.js 18+, Codex, Claude Code, GitHub Copilot or Pi CLI, GitHub CLI (gh) for local PR and ship runs
- Models: Anthropic, OpenAI, Codex, GitHub Copilot, Pi
- port 4173
Also in Coding agents and AI editors
See all 143| Rank | Project | Score |
|---|---|---|
| 1 | ArchonYAML workflow engine that runs AI coding agents through fixed dev steps | 84 out of 100 |
| 2 | claw-codeRust CLI coding agent harness using Anthropic and OpenAI-compatible APIs | 83 out of 100 |
| 3 | Open SWEAgent that turns issues into pull requests, reviews PRs and monitors CI | 83 out of 100 |
| #4 | piTerminal coding agent with extensions, skills, and an SDK | 80 out of 100 |
| #5 | oh-my-openagentTerminal coding agent with multi-model orchestration and git-backed memory | 80 out of 100 |