{"id":49530815,"url":"https://github.com/raphaelbleier/dataiku-ai-context","last_synced_at":"2026-05-02T07:32:22.997Z","repository":{"id":354486677,"uuid":"1223851445","full_name":"raphaelbleier/dataiku-ai-context","owner":"raphaelbleier","description":"Dataiku DSS documentation bundles + Claude Code subagents for every major AI coding tool","archived":false,"fork":false,"pushed_at":"2026-04-28T18:21:20.000Z","size":2436,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-28T20:26:40.899Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/raphaelbleier.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"docs/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":null,"dco":null,"cla":null}},"created_at":"2026-04-28T18:04:19.000Z","updated_at":"2026-04-28T18:21:23.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/raphaelbleier/dataiku-ai-context","commit_stats":null,"previous_names":["raphaelbleier/dataiku-ai-context"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/raphaelbleier/dataiku-ai-context","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raphaelbleier%2Fdataiku-ai-context","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raphaelbleier%2Fdataiku-ai-context/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raphaelbleier%2Fdataiku-ai-context/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raphaelbleier%2Fdataiku-ai-context/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/raphaelbleier","download_url":"https://codeload.github.com/raphaelbleier/dataiku-ai-context/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raphaelbleier%2Fdataiku-ai-context/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32527136,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-02T01:12:54.858Z","status":"online","status_checked_at":"2026-05-02T02:00:05.923Z","response_time":132,"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":[],"created_at":"2026-05-02T07:32:22.257Z","updated_at":"2026-05-02T07:32:22.990Z","avatar_url":"https://github.com/raphaelbleier.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Dataiku AI Context\n\n\u003e Full Dataiku DSS documentation + Claude Code subagents — installable into every major AI coding tool in one command.\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n[![Agents](https://img.shields.io/badge/agents-6-blue)](#claude-code-agents)\n[![Doc bundles](https://img.shields.io/badge/doc%20bundles-87-green)](#documentation-bundles)\n[![Tools supported](https://img.shields.io/badge/tools-7-purple)](#supported-ai-tools)\n\n## What's included\n\n| | |\n|---|---|\n| **6 Claude Code agents** | Domain-specialized subagents for Dataiku development |\n| **87 doc bundles** | Full DSS + Developer docs as markdown, topic-organized |\n| **7 tool installers** | Claude Code, Cursor, Copilot, Windsurf, Aider, Continue, Cline |\n\nDocs scraped from [doc.dataiku.com](https://doc.dataiku.com/dss/latest/) and [developer.dataiku.com](https://developer.dataiku.com/latest/) — 1755 pages bundled into ~400 KB topic files.\n\n---\n\n## Quick install\n\n```bash\ngit clone https://github.com/raphaelbleier/dataiku-ai-context.git\ncd dataiku-ai-context\n./install.sh\n```\n\nThe interactive installer lets you choose:\n- **Claude Code agents** (global or project-local)\n- **Doc bundles** for your AI coding tool\n- **Both**\n\n---\n\n## Claude Code agents\n\nSix specialized subagents, auto-loaded by Claude Code from `~/.claude/agents/`:\n\n| Agent | When to use |\n|-------|------------|\n| `dataiku-developer` | General DSS tasks: Flow, datasets, recipes, project structure |\n| `dataiku-data-engineer` | Pipelines, Spark/SQL, scenarios, automation, metrics |\n| `dataiku-ml-engineer` | Visual ML, AutoML, MLflow, model deployment, monitoring |\n| `dataiku-genai-engineer` | LLM Mesh, AI agents, RAG, Knowledge Banks, GenAI recipes |\n| `dataiku-api-developer` | Python API, REST API, API Node, Project Deployer |\n| `dataiku-admin` | Installation, users, connections, code envs, security, ops |\n\n### Install agents only\n\n```bash\n# Global (all projects)\n./install.sh\n# → choose \"Claude Code agents\" → \"Global\"\n\n# Or copy manually\ncp agents/*.md ~/.claude/agents/\n\n# Or project-local\nmkdir -p .claude/agents\ncp agents/*.md .claude/agents/\n```\n\n---\n\n## Documentation bundles\n\n87 markdown files covering every DSS topic, ready to load as context in any AI tool.\n\n```\ndocs/\n├── INDEX.md                    ← start here\n├── concepts.md\n├── python-api.md\n├── dev-concepts-examples.md    ← Python API cookbook\n├── machine-learning.md\n├── generative-ai-llm.md\n├── ai-agents.md\n├── code-recipes.md\n├── flow.md\n├── data-preparation.md\n├── automation-scenarios.md\n├── mlops.md\n├── deployment.md\n└── ... (87 total)\n```\n\n---\n\n## Supported AI tools\n\n| Tool | What gets created |\n|------|------------------|\n| **Claude Code** | `.claude/dataiku/` + `CLAUDE.md` snippet |\n| **Cursor** | `.cursor/dataiku/` + `.cursor/rules/dataiku.mdc` |\n| **GitHub Copilot** | `.github/dataiku/` + `.github/copilot-instructions.md` |\n| **Windsurf** | `.windsurf/dataiku/` + `.windsurfrules` |\n| **Aider** | `dataiku-docs/` + `DATAIKU_DOCS.md` |\n| **Continue.dev** | `.continue/dataiku/` + `.continue/config.json` |\n| **Cline** | `.cline/dataiku/` + `.clinerules` |\n\n### Install docs for a specific tool\n\n```bash\n# Interactive\n./install.sh\n# → choose \"AI tool doc bundles\" → pick your tool\n\n# Python CLI (more control)\npython tools/dataiku-docs.py install cursor --target /path/to/your/project\npython tools/dataiku-docs.py install all    --target /path/to/your/project\npython tools/dataiku-docs.py list\n```\n\n---\n\n## Usage in Claude Code\n\nOnce agents are installed, Claude Code automatically delegates Dataiku tasks to the right agent:\n\n```\n# These automatically invoke the matching subagent:\n\"Help me write a Python recipe to join two datasets\"     → dataiku-developer\n\"Set up MLflow tracking for my model\"                    → dataiku-ml-engineer\n\"Build a RAG pipeline with Dataiku Knowledge Banks\"      → dataiku-genai-engineer\n\"Automate this pipeline with a scenario\"                 → dataiku-data-engineer\n\"Create an API endpoint for my model\"                    → dataiku-api-developer\n\"Add a new user and configure LDAP\"                      → dataiku-admin\n```\n\nReference doc bundles directly:\n\n```\n@.claude/dataiku/python-api.md\n@.claude/dataiku/generative-ai-llm.md\n@.claude/dataiku/INDEX.md\n```\n\n---\n\n## Keeping docs up to date\n\nRe-scrape and re-bundle when Dataiku releases a new DSS version:\n\n```bash\npython tools/scrape_docs.py     # re-scrapes ~1755 pages\npython tools/dataiku-docs.py bundle  # rebuilds bundles\n```\n\n---\n\n## Repository structure\n\n```\ndataiku-ai-context/\n├── agents/                 # Claude Code subagent definitions\n│   ├── dataiku-developer.md\n│   ├── dataiku-ml-engineer.md\n│   ├── dataiku-data-engineer.md\n│   ├── dataiku-genai-engineer.md\n│   ├── dataiku-api-developer.md\n│   └── dataiku-admin.md\n├── docs/                   # 87 bundled documentation files\n│   ├── INDEX.md\n│   └── *.md\n├── tools/                  # Maintainer scripts\n│   ├── scrape_docs.py      # Re-scrapes Dataiku docs\n│   └── dataiku-docs.py     # Bundle + install CLI\n├── install.sh              # Interactive installer\n├── LICENSE\n└── README.md\n```\n\n---\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md).\n\nPRs welcome for:\n- New/improved agent prompts\n- Bug fixes in the installer\n- Support for additional AI tools\n\n---\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n\n---\n\n*Docs sourced from [doc.dataiku.com](https://doc.dataiku.com/dss/latest/) and [developer.dataiku.com](https://developer.dataiku.com/latest/) under Dataiku's documentation terms.*\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fraphaelbleier%2Fdataiku-ai-context","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fraphaelbleier%2Fdataiku-ai-context","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fraphaelbleier%2Fdataiku-ai-context/lists"}