.ai-devkit.json
One setup for the whole agent team
Reconcile supported coding agents from one project-local source of truth, then re-run setup as your stack changes.
The future is many AI coding agents
Your AI coding agents are a team now. Give them a way to work together.
AI DevKit is the control plane for Claude Code, Codex, Cursor, Gemini CLI, opencode, Pi, and other coding agents: one shared config, one console, local-first memory, cross-agent communication, and proof before done.
Built for developers already operating more than one coding agent.
Open source on GitHub and available from npm as ai-devkit.
Works with the agents you already use
Configure supported agents clearly. Keep the operating model consistent as your stack changes.
Before and after
One assistant became many agents. Now they need a way to work together.
Scattered terminal tabs
One local console
Duplicated agent rules
One reconciled config
Copy-pasted logs
agent send with stdin
Forgotten project decisions
Local memory retrieval
Done because the agent stopped
Done with verification evidence
The new problem is orchestration
AI DevKit makes them operate as one local system.
Multi-agent coding is powerful, but without shared setup, memory, communication, and verification, it becomes operationally messy. AI DevKit sits above the tools instead of replacing them.
agent console
See every running agent
See what is running, inspect local sessions, and keep long-running agents out of scattered terminal tabs.
agent send
Send work instead of copy-pasting context
Send prompts, logs, test output, and review tasks to the right running agent or saved agent group.
local SQLite
Give agents memory without bloating prompts
Store conventions, decisions, and reusable fixes locally so agents search when context is actually needed.
verify
Make done require proof
Use workflow skills and verification gates so completion claims need fresh build or test output.
Extend this operating model with reusable AI coding agent skills for planning, debugging, memory, verification, documentation, and review.
Start in 30 seconds
Create your agent control plane.
The init flow writes project-local files you can review and commit. Re-run it whenever your agent list, skills, or workflow changes.
npx ai-devkit@latest init --built-in
ai-devkit agent console
ai-devkit agent list
ai-devkit agent send "review this branch for release risk" --group reviewers
npm test 2>&1 | ai-devkit agent send --id codex --stdin
ai-devkit memory search --query "testing convention"