AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Dev Tooling/
ai-devkit
ai-devkit logo

ai-devkit

Active·★ 1.7k·Apache-2.0·Updated 2026-10-24

AI DevKit targets developers whose setup has grown from one assistant into several, each with its own config file and MCP wiring, terminals with no shared view, and agents that forget yesterday's conventions. It adds a local-first operating layer so those agents share setup, a control surface, memory and communication paths.

A single .ai-devkit.json reconciles the agent files, skills and MCP setup for the tools a team picks, among them Claude Code, Codex CLI, Gemini CLI, opencode, Pi, Cursor and GitHub Copilot. The agent console is a live TUI for supervising running sessions across providers, agent send routes prompts, stdin or logs to a running session or a named group, and a local SQLite memory is exposed over MCP so agents retrieve conventions and fixes only when a task needs them instead of carrying everything in every prompt.

On top of this sit composable engineering skills: a dev-lifecycle skill that walks requirements, design, planning, implementation, testing and review, plus verify, tdd, debugging, security and docs skills. Setup is npx ai-devkit setup once per machine and npx ai-devkit init per project, which writes the per-agent folders and docs/ai structure into the repo.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#coding-agents#claude-code#codex#cursor#agent-memory#cli#skills
$ Install
$ npx ai-devkit@latest setup && npx ai-devkit@latest init
↗ Visit site★ GitHub
01

Features

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
02

Why choose it

+One config reconciles setup across Claude Code, Codex, Cursor and more instead of maintaining each by hand.
+A console plus agent send give running agents a shared control surface and a way to route work between them.
+Local SQLite memory is retrieved over MCP only when useful, so conventions do not bloat every prompt.
03

Trade-offs

!Most valuable only once you juggle several coding agents; overhead for a single-assistant setup.
!Another local layer, config file and set of commands to learn and keep in sync.
!It orchestrates existing agents and models rather than providing any of its own.
04

Maintenance check

ActiveChecked: 2026-10-24
Last commit
2026-10-23
Commits, last 90 days
100+
Releases, last 90 days
30
Latest release
[email protected] (2026-10-23)
Open issues
36
Recent issues with at least one comment
1/19
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 7, 24, 42, 15, 27, 25, 14, 18, 51, 55, 24, 22

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #402 fix(agent): nested agent start loses assigned name — list/send fall back to folder-PID identity1 comments · 2026-10-17
  • #77 Using ai-devkit in multirepository projects1 comments · 2026-04-28
  • #417 fix(devkitd): agent.start allows duplicate names for fallback-registered agents0 comments · 2026-10-23
  • #416 chore(devkitd): drop legacy agents.db bridge after full migration0 comments · 2026-10-23
  • #415 feat(devkitd): migrate channel agent resolution to daemon RPC0 comments · 2026-10-23

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

Claude Code
Config + skills
Verified via docs
Codex
Config + skills
Verified via docs
Cursor
Config + skills
Verified via docs
Gemini CLI
Config + skills
Verified via docs
06

Quick start

1
$ npx ai-devkit@latest setup
2
$ npx ai-devkit@latest init
07

Use cases

↳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
08

Alternatives

⚡Top VS:
VSagentpack★18→VSawesome-gamedev-agent-skills★3.9k→VSkungfu★4.5k→VSoh-my-hermes★3.8k→
agentpack logo
agentpack★ 18
Local task-state ledger for AI coding agents. Preserve decisions, source conclusions, evidence, and checkpoints across Codex, Claude Code, Cursor, and other MCP clients.
VSCompare→
awesome-gamedev-agent-skills logo
awesome-gamedev-agent-skills★ 3.9k
74 game-dev skills for AI coding agents — Godot, Unity, Unreal, Phaser, PixiJS, three.js, Bevy, pygame, LÖVE, Roblox. Portable SKILL.md Agent Skills (the format Anthropic launched as Claude Skills), with a router that loads the right skill for your engine and task. Runs in Claude Code, Cursor, Kiro, Codex, Copilot, Gemini CLI and more.
VSCompare→
kungfu logo
kungfu★ 4.5k
Your agents don’t hand off the work. Kungfu keeps the same Work moving across Codex, Claude, OpenCode, and your own execution surface.
VSCompare→
oh-my-hermes logo
oh-my-hermes★ 3.8k
The packages for Hermes Agent ⚚ skills, coding harness, long-term memory, model optimized subagent & bot team workflows
VSCompare→
xerj logo
xerj★ 15.3k
Local-first search engine and MCP server for AI agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.
VSCompare→
agent-bridge logo
agent-bridge★ 406
A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。
VSCompare→
Graft logo
Graft★ 10.7k
Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
VSCompare→
markplane logo
markplane★ 191
AI-native, markdown-first project management. Your repo is the project manager.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
codeaholicguy /
ai-devkit
↗

One config, one console and shared memory for teams running Claude Code, Codex, Cursor and other coding agents side by side

1.7kApache-2.0
Last commit1d ago
StatusActive
CategoryDev Tooling
Links
Documentation↗Discussion↗Issues↗Releases↗
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
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.