Recipes for wiring Unsiloed's document AI — parse, extract, classify, split — into the AI provider, agent framework, or runtime of your choice.

The cookbook stays agnostic by design: each recipe is scoped to a single provider or skill family, so adding a new model, SDK, or agent runtime is a self-contained drop-in.

• Unsiloed API key — sign up at unsiloed.ai
• Python 3.13+ for the notebook-based recipes (skill recipes need only curl and jq)

git clone https://github.com/Unsiloed-AI/cookbook.git
cd cookbook

# Create your .env file
cp .env.example .env
# Edit .env and add your API keys

# For Python recipes
pip install -e .

Recipes built around a specific model, SDK, or agent framework.

Runtime-agnostic SKILL.md files — YAML frontmatter plus bash instructions — that plug into any skill-capable agent: Claude Code, Claude.ai, OpenClaw, custom runtimes.

cookbook/
├── claude/         # Claude-specific recipes (tool use, agents, etc.)
├── openai/         # OpenAI-specific recipes (CLI, agents, etc.)
├── skills/         # Portable SKILL.md files for skill-capable runtimes
└── <provider>/     # Add new provider folders as siblings (gemini/, langchain/, ...)

We welcome contributions! Pick the directory that matches what you're adding:

• Provider-specific recipe (uses a particular SDK or API) → <provider>/<recipe-name>/. Example: openai/responses-api/, gemini/function-calling/, langchain/extraction/.
• Portable agent skill (a SKILL.md that works across runtimes) → skills/<skill-name>/.
• General guide that isn't tied to one provider → top-level directory with a clear name.

For every recipe:

1. Include a README.md explaining what it does, prerequisites, and how to run it.
2. Use .env and python-dotenv (or shell export for skill recipes) for API keys — never hardcode them.
3. Clear notebook outputs before committing.
4. Open a PR with a description of what the example demonstrates and add it to the relevant table above.

• Unsiloed Documentation
• API Reference
• Claude Integration Guide
• Support

MIT