{"id":46430780,"url":"https://github.com/protolabsai/protomaker","last_synced_at":"2026-05-04T02:12:12.002Z","repository":{"id":336431145,"uuid":"1149500659","full_name":"protoLabsAI/protoMaker","owner":"protoLabsAI","description":"An autonomous development studio where ideas become shipped software — orchestrated by AI, validated by humans.","archived":false,"fork":false,"pushed_at":"2026-04-05T22:23:13.000Z","size":43582,"stargazers_count":5,"open_issues_count":4,"forks_count":3,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-05T22:24:18.517Z","etag":null,"topics":["agents","ai","claude","claude-code"],"latest_commit_sha":null,"homepage":"https://docs.protolabs.studio","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":"shaal/automaker","license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/protoLabsAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null},"funding":{"github":["mabry1985"],"patreon":null,"open_collective":null,"ko_fi":null,"tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"lfx_crowdfunding":null,"polar":null,"buy_me_a_coffee":null,"thanks_dev":null,"custom":null}},"created_at":"2026-02-04T07:22:32.000Z","updated_at":"2026-04-05T20:47:27.000Z","dependencies_parsed_at":"2026-04-02T12:18:31.588Z","dependency_job_id":null,"html_url":"https://github.com/protoLabsAI/protoMaker","commit_stats":null,"previous_names":["proto-labs-ai/automaker","protolabsai/protomaker"],"tags_count":158,"template":false,"template_full_name":null,"purl":"pkg:github/protoLabsAI/protoMaker","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/protoLabsAI%2FprotoMaker","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/protoLabsAI%2FprotoMaker/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/protoLabsAI%2FprotoMaker/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/protoLabsAI%2FprotoMaker/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/protoLabsAI","download_url":"https://codeload.github.com/protoLabsAI/protoMaker/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/protoLabsAI%2FprotoMaker/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31539229,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-07T16:28:08.000Z","status":"online","status_checked_at":"2026-04-08T02:00:06.127Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agents","ai","claude","claude-code"],"created_at":"2026-03-05T18:09:12.108Z","updated_at":"2026-04-08T04:01:14.927Z","avatar_url":"https://github.com/protoLabsAI.png","language":"TypeScript","funding_links":["https://github.com/sponsors/mabry1985"],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"apps/ui/public/readme_logo.svg\" alt=\"protoLabs Studio\" height=\"80\" /\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eYour team of AI agents. Your codebase. Fully autonomous.\u003c/strong\u003e\u003cbr/\u003e\n  Describe what you want built. Named agents implement it, create PRs, and ship — while you hold the merge button.\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/protoLabsAI/protoMaker/actions/workflows/test.yml\"\u003e\u003cimg src=\"https://github.com/protoLabsAI/protoMaker/actions/workflows/test.yml/badge.svg\" alt=\"Build Status\" /\u003e\u003c/a\u003e\n  \u003ca href=\"LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/license-MIT-blue.svg\" alt=\"MIT License\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://discord.gg/3KtfEthCpk\"\u003e\u003cimg src=\"https://img.shields.io/badge/Discord-Join-5865F2?logo=discord\u0026logoColor=white\" alt=\"Discord\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://nodejs.org/\"\u003e\u003cimg src=\"https://img.shields.io/badge/node-%3E%3D22.0.0-brightgreen\" alt=\"Node Version\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://protolabs.studio\"\u003e\u003cimg src=\"https://img.shields.io/badge/docs-protolabs.studio-blue\" alt=\"Docs\" /\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003e **Alpha Software** --- protoLabs Studio is under active development. APIs change, rough edges exist. If you want to shape the future of autonomous development, you're in the right place.\n\n---\n\n## The Idea\n\nMost AI coding tools give you a single agent in a single file. protoLabs gives you a **team**.\n\nSpecialized agents — frontend, backend, infrastructure, DevOps — each with domain expertise, memory, and their own isolated workspace. They read your codebase, follow your coding standards, and produce real PRs against real branches.\n\nYou describe features on a Kanban board. Agents pick them up, implement them in isolated git worktrees, run verification, and create pull requests. CodeRabbit reviews the code. CI runs the tests. You merge when ready.\n\nNo copy-pasting prompts. No babysitting context windows. You set the rules once in context files, and every agent follows them every time.\n\n![protoLabs UI](https://i.imgur.com/tsj0Bjw.png)\n\n## Get Started\n\n_Desktop releases coming soon. Run from source to try now._\n\n### Run from Source\n\n```bash\ngit clone https://github.com/protoLabsAI/protoMaker.git\ncd protoMaker\nnpm install\nnpm run dev                 # Interactive launcher (choose web or docker)\nnpm run dev:full            # Web mode — starts UI (localhost:3007) AND server (localhost:3008)\n```\n\nRequires **Node.js 22+** and an [Anthropic API key](https://console.anthropic.com/).\n\n## What Makes It Different\n\n### Named Agent Teams\n\nNot \"Agent 1\" and \"Agent 2\" --- real personas with domain expertise. Matt handles React, Tailwind, and component architecture. Kai builds Express routes, services, and API design. Frank manages Docker, CI, and infrastructure. Each agent accumulates memory from prior work, getting better at your codebase over time.\n\n### Worktree Isolation\n\nEvery feature runs in its own git worktree. Three agents working simultaneously on different features --- zero conflicts. Each produces a clean, reviewable PR from an isolated branch. Main stays untouched until you merge.\n\n### Context Files = Your Rules\n\nDrop coding standards, architectural patterns, and project conventions into `.automaker/context/`. Every agent loads them before writing a single line. Your team, your rules --- enforced automatically across every agent session.\n\n### Auto-Mode\n\nQueue features with dependencies. Auto-mode resolves execution order and runs agents in parallel where possible. A 10-feature project with a dependency chain (DB schema -\u003e API routes -\u003e frontend) executes in the right order, maximizing throughput.\n\n### Real-Time Streaming\n\nWatch agents think and code in real time. Send instructions mid-flight --- \"also add TypeScript types\" or \"use Tailwind instead\" --- and agents adjust without starting over.\n\n### Full Project Orchestration\n\nFor larger work: describe an idea, get a SPARC PRD, break it into milestones with sized phases, generate board features with dependencies, and launch. Research -\u003e plan -\u003e execute -\u003e review -\u003e merge -\u003e done.\n\n### Claude Code Plugin\n\n159 MCP tools for full control from your terminal. Manage boards, start agents, set dependencies, review output --- without leaving Claude Code.\n\n```\n/board              View and manage your Kanban board\n/auto-mode          Start/stop autonomous feature processing\n/orchestrate        Manage feature dependencies\n/plan-project       Full project lifecycle pipeline\n/ava                Autonomous operator mode\n```\n\n## How It Works\n\n```\nYou describe a feature --\u003e Agent claims it --\u003e Works in isolated worktree --\u003e Creates PR --\u003e You review \u0026 merge\n```\n\n1. Add a feature to the board with a natural language description\n2. Auto-mode assigns the right agent based on domain and complexity\n3. Agent works in a git worktree --- reads codebase, implements, runs verification\n4. PR created with full diff, agent output, and CI checks\n5. CodeRabbit reviews. CI passes. You merge. Feature moves to done.\n\nFor complex projects, protoLabs runs a full pipeline: idea -\u003e codebase research -\u003e SPARC PRD -\u003e human review -\u003e milestones -\u003e parallel agent execution -\u003e PR review -\u003e ship.\n\n## Trust Architecture\n\nAutonomous agents writing code sounds risky. It is --- if you skip the discipline.\n\nprotoLabs works because the guardrails are non-negotiable:\n\n- **Context files define the rules.** Your coding standards, architectural decisions, and conventions are injected into every agent session. Agents follow your rules because you wrote them.\n- **CodeRabbit reviews every PR.** Automated code review catches style violations, security issues, and logic errors before any human sees the diff.\n- **CI runs on every push.** TypeScript, linting, formatting, tests --- nothing merges without passing.\n- **You hold the merge button.** Agents create PRs. They do not push to production. Every change goes through your normal review process.\n- **Model tiering matches cost to complexity.** Haiku for formatting fixes. Sonnet for standard features. Opus for architecture. Auto-escalation after failures.\n\nTrust is earned, not assumed. You control the context files agents read, the review gates they pass through, and the branches they can touch.\n\n## Architecture\n\nTypeScript monorepo with a React frontend, Express backend, and 15 shared packages:\n\n```\nprotolabs-studio/\n├── apps/\n│   ├── ui/              # React + Vite + PWA (port 3007)\n│   └── server/          # Express + WebSocket backend (port 3008)\n├── libs/                # 15 shared packages (@protolabsai/*)\n│   ├── types/           # Core TypeScript definitions\n│   ├── utils/           # Logging, errors, context loading\n│   ├── git-utils/       # Git operations \u0026 worktree management\n│   ├── observability/   # Langfuse tracing \u0026 cost tracking\n│   ├── tools/           # Unified tool definition \u0026 registry\n│   ├── flows/           # LangGraph state graph primitives\n│   ├── prompts/         # AI prompt templates\n│   └── ...              # platform, model-resolver, dependency-resolver, etc.\n├── packages/\n│   └── mcp-server/      # Claude Code plugin (159 MCP tools)\n└── site/                # Landing page (protolabs.studio)\n```\n\n**Key Stack**: React 19, Vite 7, Express 5, Claude Agent SDK, TanStack Router, Zustand 5, Tailwind CSS 4, Langfuse, Playwright, Vitest\n\n## Documentation\n\nFull docs at **[protolabs.studio](https://protolabs.studio)**:\n\n- **[Getting Started](docs/getting-started/)** --- Installation, configuration, first feature\n- **[Agent System](docs/agents/)** --- How agents work, teams, prompt engineering\n- **[Self-Hosting](docs/infra/)** --- Docker, systemd, staging deployment\n- **[Integrations](docs/integrations/)** --- Discord, Claude Code plugin, MCP tools\n- **[Development](docs/dev/)** --- Contributing, architecture, shared packages\n\n## Community\n\nJoin builders exploring agentic coding and autonomous development:\n\n**[Discord](https://discord.gg/3KtfEthCpk)** · **[protolabs.studio](https://protolabs.studio)** · **[GitHub](https://github.com/protoLabsAI)** · **[Code of Conduct](CODE_OF_CONDUCT.md)**\n\n## Contributing\n\nprotoLabs uses an **ideas-only contribution model** --- AI agents implement all code.\n\n- **Submit an idea**: [Idea Submission](https://github.com/protoLabsAI/protoMaker/issues/new?template=idea_submission.yml)\n- **Report a bug**: [Bug Report](https://github.com/protoLabsAI/protoMaker/issues/new?template=bug_report.yml)\n- **Join the discussion**: [Discord](https://discord.gg/3KtfEthCpk)\n\n[Contributing Guidelines](CONTRIBUTING.md)\n\n## Security\n\nThis software uses AI agents that access your file system and execute commands. We recommend running in Docker or a VM for isolation. See the [full disclaimer](docs/disclaimer.md).\n\n## License\n\nMIT --- see [LICENSE](LICENSE).\n\nOriginally forked from [Automaker](https://github.com/AutoMaker-Org/automaker) (MIT). We are the actively maintained successor.\n\n---\n\n\u003cp align=\"center\"\u003e\n  Built by \u003ca href=\"https://protolabs.studio\"\u003eprotoLabs\u003c/a\u003e --- an AI-native development agency.\n\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprotolabsai%2Fprotomaker","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fprotolabsai%2Fprotomaker","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprotolabsai%2Fprotomaker/lists"}