AgentIndex icon
AgentIndex
ai-devkit logo
ai-devkit
★ 1.7k
vs
zeroshot logo
zeroshot
★ 2.0k

ai-devkit vs zeroshot

ai-devkit: AI DevKit is a local-first operating layer for teams running several coding agents. One .ai-devkit.json reconciles skills, MCP and setup across Claude Code, Codex CLI, Gemini CLI, opencode, Pi, Cursor, Copilot and others; agent console is a live TUI for running sessions; agent send routes prompts, logs or stdin to a running agent; and a local SQLite memory is searched over MCP when needed. A dev-lifecycle skill guides requirements, design, planning, implementation, testing and review.; zeroshot: zeroshot is a meta-harness that runs coding agents through a workflow graph you define: coding, independent review and repair loops, with review gates and retry limits enforced by the engine rather than by prompts. Each node can use its own model and harness (Pi, Claude Code, Codex or Copilot), runs locally, self-hosted or on its hosted platform.

01

TL;DR

ai-devkit logo
ai-devkitDev Tooling · ★ 1.7k

Keeping one setup across Claude Code, Codex and Cursor in a team repo

Read ai-devkit full review →
zeroshot logo
zeroshotDev Tooling · ★ 2.0k

Enforcing code review before agent work is accepted

Read zeroshot full review →
02

Side-by-Side Comparison

Field
ai-devkit logoai-devkit
zeroshot logozeroshot
Category
Dev Tooling
Dev Tooling
Stars
★ 1.7k
★ 2.0k
License
Apache-2.0
MIT
Install Command
npx ai-devkit@latest setup && npx ai-devkit@latest init
—
Updated
3d ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
coding-agents, claude-code, codex
coding-agents, review-loop, workflow-graph
03

Features

ai-devkit logoai-devkit
01One .ai-devkit.json that writes agent files, skills and MCP setup for each tool you pick
02agent list and agent console to supervise sessions across providers
03agent send with --stdin, --wait and groups to route work to running agents
04Local SQLite memory exposed via MCP and CLI, retrieved only when useful
05dev-lifecycle, verify, tdd, review, debugging and security skills
zeroshot logozeroshot
01Workflow graphs with enforced review gates and retry limits
02Mix Pi, Claude Code, Codex and Copilot harnesses per agent
03Reuses existing harness logins including subscriptions
04Native binaries for Linux, macOS and Windows via npm
05Local, Docker self-hosted or hosted platform runs
04

Use Cases

ai-devkit logoai-devkit
↳Keeping one setup across Claude Code, Codex and Cursor in a team repo
↳Piping test output to a running agent or a group of reviewer agents
↳Giving agents searchable project conventions without bloating every prompt
zeroshot logozeroshot
↳Enforcing code review before agent work is accepted
↳Pairing a cheaper coding model with a stronger reviewer
↳Automating fix-review-repair loops on small issues
FAQ

FAQ

What is the difference between ai-devkit and zeroshot?
Both ai-devkit and zeroshot are in the Dev Tooling category. ai-devkit has 1.7k stars, while zeroshot has 2.0k stars.
Which is better, ai-devkit or zeroshot?
The best choice depends on your use case. Choose ai-devkit if Keeping one setup across Claude Code, Codex and Cursor in a team repo, and zeroshot if Enforcing code review before agent work is accepted.
Is ai-devkit free or open source?
Yes, ai-devkit is open source on GitHub (Apache-2.0).
Is zeroshot free or open source?
Yes, zeroshot is open source on GitHub (MIT).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to ai-devkit →Alternatives to zeroshot →ai-devkit details →zeroshot details →