{"data":{"slug":"rohitg00-ai-engineering-from-scratch","name":"ai-engineering-from-scratch","tagline":"Learn, build, and deploy AI engineering skills from scratch.","github_url":"https://github.com/rohitg00/ai-engineering-from-scratch","owner":"rohitg00","repo":"ai-engineering-from-scratch","owner_avatar_url":"https://avatars.githubusercontent.com/u/48523873?v=4","primary_language":"Python","stars":54935,"forks":9649,"topics":["agents","ai","ai-agents","ai-engineering","computer-vision","course","deep-learning","from-scratch","generative-ai","llm","machine-learning","mcp","nlp","python","reinforcement-learning","rust","swarm-intelligence","transformers","tutorial","typescript"],"archived":false,"github_pushed_at":"2026-09-07T11:42:35+00:00","maintenance_label":"Active","stars_delta_30d":8073,"url":"https://www.graphcanon.com/tools/rohitg00-ai-engineering-from-scratch","markdown_url":"https://www.graphcanon.com/tools/rohitg00-ai-engineering-from-scratch.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/rohitg00-ai-engineering-from-scratch","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=rohitg00-ai-engineering-from-scratch","description":"Learn it. Build it. Ship it for others.","homepage_url":"https://aiengineeringfromscratch.com","license":"MIT","open_issues":114,"watchers":351,"ai_summary":"A comprehensive course on AI engineering that covers a wide range of topics from foundational math to advanced AI agents and machine learning techniques.","readme_excerpt":"## Getting started\n\nThree ways in. Pick one.\n\n**Option A — learn in your terminal *(recommended)*.** After the Node.js,\n`npx`, host, and scope preflight above, install the learning skills into a\ncompatible agent and let the course drive itself:\n\n```bash\nnpx skills add rohitg00/ai-engineering-from-scratch\n```\n\nUse the host-specific invocation table above. The installed skills provide\n`start-learning`, `learn`, `course-guide`, and the focused\n`learn-mcp` and `learn-agent-skills` routes. Lesson prose can\nstream from this repository without a clone. A local clone is required for\ncopied repository code commands and executable MCP or Agent Skills labs.\nProgress lives in `LEARNING.md`, `MCP-LEARNING.md`, or\n`AGENT-SKILLS-LEARNING.md` in your project, so every session can resume.\n\n**Option B — read.** Open any completed lesson on\n[aiengineeringfromscratch.com](https://aiengineeringfromscratch.com) or expand a phase under\n[Contents](#contents). No setup, no cloning.\n\n**Option C — clone and run.**\n\n```bash\ngit clone https://github.com/rohitg00/ai-engineering-from-scratch.git\ncd ai-engineering-from-scratch\npython3 phases/01-math-foundations/01-linear-algebra-intuition/code/vectors.py\n```\n\nCloning also auto-loads the learning skills in Claude Code, and gives every\nlesson's code to the `learn` tutor for real execution instead of read-along.\n\n---\n\n### Install course skills into your agent\n\nTwo skill sets, two installers:\n\n**The learning skills** (`start-learning`, `learn`, `course-guide`,\n`learn-mcp`, `learn-agent-skills`, `claude-certification`, `find-your-level`, and\n`check-understanding`) live under [`skills/`](skills/) and install into a\nsupported skill-capable host with one command. Installation needs Node.js and\n`npx`, but not a repository clone or Python:\n\n```bash\nnpx skills add rohitg00/ai-engineering-from-scratch\n```\n\n`skills` writes to the host and scope selected during installation, such as\n`.claude/skills/`, `.cursor/skills/`, `.codex/skills/`, or another supported\nskills folder. Verify that the selected host discovers that exact destination.\n\n**The lesson artifacts.** The repo ships 396 skills and 99 prompts under\n`phases/**/outputs/`; install them via `scripts/install_skills.py`. Requires\ncloning the repo. Supports tag filters, dry-runs, and per-agent layouts:\n\n```bash\npython3 scripts/install_skills.py <target>                                 # every skill, default --layout skills (nested)\npython3 scripts/install_skills.py <target> --layout skills                 # same as above, explicit\npython3 scripts/install_skills.py <target> --type all                      # skills + prompts + agents\npython3 scripts/install_skills.py <target> --phase 14                      # one phase only\npython3 scripts/install_skills.py <target> --tag rag                       # filter by tag\npython3 scripts/install_skills.py <target> --layout flat                   # flat files\npython3 scripts/install_skills.py <target> --dry-run                       # preview without writing\npython3 scripts/install_skills.py <target> --force                         # overwrite existing files\n```\n\n`<target>` is the skills directory for your agent (examples:\n`~/.claude/skills/`, `~/.cursor/skills/`, `~/.config/openclaw/skills/`,\n`.skills/`, or any path your agent reads).\n\nBy default the script refuses to overwrite an existing destination and exits\nwith code 1 after listing every colliding path. Use `--dry-run` to preview\ncollisions or `--force` to overwrite. Every non-dry-run run writes a\n`manifest.json` in the target with the full inventory grouped by type and\nphase. Pick the layout your agent reads:\n\n| `--layout`  | Path written |\n|---|---|\n| `skills`    | `<target>/<name>/SKILL.md` (nested convention, supported by Claude / Cursor / Codex / OpenClaw / Hermes) |\n| `by-phase`  | `<target>/phase-NN/<name>.md` |\n| `flat`      | `<target>/<name>.md` |\n\n---\n\n## License\n\nMIT. Use it however you want — fork it, teach it, sell it, ship it. Attribution appreciated,\nnot requ","github_created_at":"2026-03-18T18:38:02+00:00","created_at":"2026-07-07T17:31:38.909936+00:00","updated_at":"2026-09-20T04:32:17.820639+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"computer-vision","name":"Computer Vision","url":"https://www.graphcanon.com/categories/computer-vision","markdown_url":"https://www.graphcanon.com/categories/computer-vision.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/computer-vision"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"agents","name":"agents"},{"slug":"ai-engineering","name":"ai-engineering"},{"slug":"computer-vision","name":"computer-vision"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"from-scratch","name":"from-scratch"},{"slug":"generative-ai","name":"generative-ai"},{"slug":"llm","name":"llm"},{"slug":"machine-learning","name":"machine-learning"}],"trust":{"provenance":{"is_fork":false,"github_id":1185590488,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:38:24.642Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":3,"days_since_push":10,"last_release_at":"2026-09-07T11:42:35Z","stars_delta_30d":8073,"open_issues_delta_30d":7},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":118,"high_count":0,"last_scan_at":"2026-09-18T08:38:26.916Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:38:23.489Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-18T08:38:23.489Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-18T08:38:23.489Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["when you need a structured course that covers a wide range of AI engineering topics from scratch, including foundational math, deep learning, and reinforcement learning.","if you prefer learning through interactive sessions in your terminal, as the course can be installed and run directly from there.","when you want to learn by doing, as the course provides executable code labs and supports real execution of lessons.","if you are using a skill-capable host like Claude Code, as the course can be installed directly into these environments."],"when_not_to_use":["if you are looking for a tool that focuses solely on theoretical knowledge without practical application, as this course emphasizes hands-on learning.","when you do not have access to Node.js or Python, as these are required for running the course and its interactive components.","if you prefer a more traditional learning approach without the use of terminal-based learning tools, as the course is designed for interactive terminal sessions.","when you are working with a development environment that does not support skill-capable hosts, as the course is optimized for such environments."],"source":"enrich:decision_facts","observed_at":"2026-09-18T11:21:39.502Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"ai-engineering-from-scratch is a comprehensive course that teaches AI engineering skills from foundational math to advanced AI agents and machine learning techniques, using Python and Node.js for interactive learning and"}]}}