AI DevKit
A local-first control plane that standardizes setup, supervision, memory, and engineering workflows across coding agents.
- Source repo
- codeaholicguy/ai-devkit
- Stars
- ★ 1.6k
- Last updated
- today
- License
- Apache-2.0
- Primary language
- TypeScript
- FA score
- 48/100 · Major gaps
At a glance
- Works with
- Universal · cross-platformCodex · Claude Code
- You'll need
- Typical use
- A development team using Claude Code, Codex CLI, and Gemini CLI that wants one project configuration for skills, rules, and MCP setup.
- Main limitation
- Remote control is not available for every listed tool; the README marks opencode as testing and shows no remote control for several tools.
- Source review
- 48/100 · Major gaps
What does this agent do, and when should you use it?
AI DevKit is a local-first operating layer for AI coding tools. A project-level `.ai-devkit.json` reconciles configuration and can install rules, skills, and MCP settings for the selected tools. Its CLI exposes `ai-devkit agent list`, `agent detail`, `agent console`, and `agent send` for inspecting, supervising, and messaging running sessions. `@ai-devkit/memory` stores project decisions, conventions, and reusable fixes in local SQLite, with retrieval through MCP and the CLI. The package also installs composable skills centered on `dev-lifecycle`, producing requirements, design, planning, implementation, and testing artifacts for teams managing more than one coding agent.
npx ai-devkit@latest init creates .ai-devkit.json, configuration directories for the chosen agents, and a phased docs/ai/ document structure in the project. ai-devkit agent list and ai-devkit agent console expose running sessions, while ai-devkit agent send "..." --id <agent-name> --wait routes a prompt to a session; --stdin accepts piped output and --group targets saved groups where supported. ai-devkit memory store writes titled, tagged, scoped knowledge to local SQLite, and ai-devkit memory search --query "..." retrieves it. dev-lifecycle guides requirements, design, planning, implementation, testing, and review; verify requires fresh test or build output before completion claims.
- A development team using Claude Code, Codex CLI, and Gemini CLI that wants one project configuration for skills, rules, and MCP setup.
- An engineering lead with several local coding sessions who needs a terminal console plus a way to send test logs and follow-up work to a named session.
- A backend team maintaining long-lived conventions, such as returning DTOs from REST handlers, that wants agents to retrieve them when relevant.
- A team building a sensitive feature such as Google OAuth login that wants requirements, design, and planning artifacts before implementation.
- A maintainer who needs agents to support completion claims with current test or build output before release review.
How do you install or deploy this agent?
From a project directory, run npx ai-devkit@latest init. The wizard lets you select agents and workflow components, then writes project-local files intended for review and commit. Source installation is documented as: git clone https://github.com/Codeaholicguy/ai-devkit.git, followed by cd ai-devkit && npm install && npm run build.
How do you use this agent?
After initialization, run ai-devkit agent list to inspect running sessions or ai-devkit agent console for the live terminal UI. To dispatch work and wait for the response, run ai-devkit agent send "run the tests and report back" --id <agent-name> --wait. Store a convention with ai-devkit memory store --title "API handlers return DTOs" --content "REST handlers should return response DTOs instead of domain entities." --tags "api,backend" --scope "repo:codeaholicguy/ai-devkit", then retrieve it with ai-devkit memory search --query "API response convention".
What are this agent's strengths and limitations?
- A single
.ai-devkit.jsonreconciles rules, skills, and MCP setup across multiple supported coding tools. agent console, session inspection, andagent sendprovide an operational surface for live sessions and cross-session prompt or log routing.- Local SQLite memory is retrieved when needed, avoiding the need to carry every project convention in each prompt.
dev-lifecycleandverifyconnect staged engineering artifacts with fresh verification evidence.
- Remote control is not available for every listed tool; the README marks opencode as testing and shows no remote control for several tools.
- Initialization writes agent configuration, skill directories, and
docs/ai/workflow artifacts into the repository, which teams must be willing to review and maintain. - CLI initialization, session control, and memory retrieval require a shell, filesystem access, npm, and a local runtime environment.
- The README declares MIT, while the supplied repository metadata lists the license as unknown; adopters should confirm the license status.
How does this agent compare with similar options?
Compared with static instruction files such as CLAUDE.md, .cursor/rules, and AGENTS.md, AI DevKit adds cross-tool setup reconciliation, live-session visibility and control, session messaging, searchable local memory, and verification gates. It is not presented as a replacement for Claude Code, Codex CLI, Cursor, Gemini CLI, or opencode; it configures and coordinates those tools.
Key facts side by side with the most closely related agents.
| Agent | Source review | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|
| AI DevKit This agent | 48 · Major gaps | ★ 1.6k | today | TypeScript | Codex · Claude Code |
| Foremerge | 77 · Good | ★ 496 | 1d ago | Rust | Codex · Claude Code |
| CORE Personal AI OS | 44 · Major gaps | ★ 2k | 16d ago | TypeScript | Codex · Claude Code |
| Mirafold | 89 · Good | ★ 15 | 5d ago | TypeScript | Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence: README claims local operation, no telemetry, memory is local SQLite, but no code-level verification. init writes project-local files, but no explicit user confirmation mechanism. Dependency management uses npm workspaces, but no dependency audit or lockfile details. External effects include starting local servers and sending messages, but permission boundaries are not explicit. Rollback mechanism not mentioned. Source attribution: author field empty, publisher unverified. Deductions: lack of implementation details to confirm least privilege, user confirmation, data flow transparency, etc.
Evidence: README descriptions align with test files (e.g., memory-dashboard tests), good self-consistency. Dependency availability: uses npm and nx, but no lockfile or mirror info. Failure messages: tests verify error handling (e.g., invalid port, invalid query params), but not all scenarios. Deductions: dependency availability not fully proven, failure message coverage limited.
Evidence: README clearly defines target users (multi-agent developers) and scenarios (multiple terminals, scattered configs). Capability boundaries: explicitly states not an LLM replacement, not a hosted service. Trigger precision: skills rely on agent adherence, but no precise trigger mechanism. Environment fit: supports multiple agents, but no system requirements detail. Deductions: trigger precision and some environment fit details insufficient.
Evidence: README well-structured, provides install instructions (npx init), examples and FAQ (docs link). Naming stability: version 0.47.0, but no naming conventions. Known limitations: explicitly lists 'what it is not'. License: MIT. Versioning: CHANGELOG.md link. Maintenance responsibility: no clear maintainer. Deductions: naming stability and maintenance responsibility info insufficient.
Evidence: Output usability: provides CLI commands and docs, output format not specified. Marginal value: addresses multi-agent management problem, clear value proposition. Cost-benefit: no performance or resource consumption data. Deductions: cost-benefit lacks data support.
Evidence: README claims (e.g., support for multiple agents) not code-verified. Cross-source: only README and test files, no external verification. Fact-inference separation: some claims (e.g., 'done' requires verification) are inferences, not clearly separated. Deductions: lack of traceable verification evidence.
- Publisher identity unverified, source attribution unclear.
- Dependency security lacks audit or lockfile details.
- Permission boundaries for external effects (e.g., starting servers, sending messages) not explicit.
- Rollback mechanism not mentioned.
- Cost-benefit lacks data support.
FAQ
Does it replace my coding agent?
Is project memory hosted remotely?
Can I operate an agent from my phone?
ai-devkit channel start telegram --agent <agent-name> --daemon.