ai-devkit

Source#

• Repository: codeaholicguy/ai-devkit
• Last source update: 2026-07-05
• Last verified: 2026-07-05

Tags#

Integration notes#

Repository is focused on tool/server interoperability; wrap in bounded worker contracts for production use.

worker.md example#

Starter worker.md contract mapped from this registry entry. Copy this file and adapt schemas, constraints, and statuses for your task.

---
id: ai-devkit-repo-derived-worker
name: ai-devkit Repo-Derived Worker
version: 1.0.0
source_registry_url: https://worker.md/registry/ai-devkit/
source_repository: https://github.com/codeaholicguy/ai-devkit
repository_default_branch: main
repository_language: TypeScript
repository_license: NOASSERTION
repository_updated_at: 2026-07-05
worker_mode: ui-copilot-worker
derivation_method: github_repository_metadata_plus_raw_readme
derivation_confidence: 0.95
derived_on: 2026-07-05
tags:
  - agent-framework
  - agent-skills
  - ai
  - ai-agents
  - ai-coding
  - antigravity
---

# ai-devkit Repo-Derived Worker

## Repo-derived summary
- Registry summary: The control plane for AI coding agents.
- Repository description: The control plane for AI coding agents.
- Stars (snapshot): 1,543
- Primary language: TypeScript
- Worker mode classification: ui-copilot-worker

## Extracted from
- https://github.com/codeaholicguy/ai-devkit
- https://github.com/codeaholicguy/ai-devkit/blob/main/README.md
- https://img.shields.io/npm/v/ai-devkit.svg
- https://img.shields.io/npm/dt/ai-devkit.svg
- https://img.shields.io/github/stars/Codeaholicguy/ai-devkit.svg?style=social

## Evidence notes (from repository text)
- README summary paragraph: AI DevKit gives Claude Code, Codex CLI, Gemini CLI, opencode, Pi, Cursor, GitHub Copilot, Devin, and other coding agents one local-first operating layer: one config, one console, local memory retrieval, cross-agent communication, and composable engineering skills led by `dev-lifecycle`.
- **The control plane for AI coding agents.**
- - **One config for every agent** — `.ai-devkit.json` reconciles setup across the coding tools your team uses
- - **One console for running sessions** — `agent console` is a live TUI dashboard for supervising local agents across providers
- - **Cross-agent communication** — `agent send` lets you route prompts, logs, and test output to running agents
- - **Memory retrieval without context bloat** — `@ai-devkit/memory` stores decisions, conventions, and fixes in local SQLite so agents search when needed instead of carrying everything in every prompt

## Installation hints found in README
- `npm install && npm run build`

## worker.md contract (derived starter)
Purpose: Run bounded assistant tasks for UI copilots using patterns documented in this repository.

### Input schema
```json
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "session_id",
    "user_prompt",
    "app_context"
  ],
  "properties": {
    "session_id": {
      "type": "string"
    },
    "user_prompt": {
      "type": "string"
    },
    "app_context": {
      "type": "object"
    }
  }
}
```

### Output schema
```json
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "session_id",
    "response",
    "status"
  ],
  "properties": {
    "session_id": {
      "type": "string"
    },
    "response": {
      "type": "string"
    },
    "status": {
      "type": "string",
      "enum": [
        "ok",
        "retryable_error",
        "invalid_request",
        "invalid_output"
      ]
    }
  }
}
```

### Constraints
- timeout_seconds: 30
- max_attempts: 2
- idempotency_key: session_id
- status_enum: [ok, retryable_error, invalid_request, invalid_output]
- notes: adapt to concrete APIs/classes documented in this repository before production use

## How this should be used
1. Treat this file as a repo-derived starter profile, not a claim of an official repository API contract.
2. Replace schemas with exact interfaces from code/docs you adopt.
3. Keep execution bounded and auditable using worker protocol constraints.

How to use#

• Save this as a worker spec file (for example: ai-devkit-my-task.worker.md).
• Replace the input/output schemas and purpose with your real bounded task.
• Enforce schema validation + timeout + retry policy in your runtime before production use.

Citation#

Reference URL: https://worker.md/registry/ai-devkit/

Source URL: https://github.com/codeaholicguy/ai-devkit