yamlgraph 0.4.34

YAML-first framework for building LLM pipelines with LangGraph

YamlGraph

A YAML-first framework for building LLM pipelines using:

• YAML Graph Configuration - Declarative pipeline definition with schema validation
• YAML Prompts - Declarative prompt templates with Jinja2 support
• Pydantic Models - Structured LLM outputs
• Multi-Provider LLMs - Anthropic, Google/Gemini, Mistral, OpenAI, Replicate, xAI, LM Studio
• LangGraph - Pipeline orchestration with resume support
• Human-in-the-Loop - Interrupt nodes for user input
• Streaming - Token-by-token LLM output (prompt-level and graph-level)
• Async Support - FastAPI-ready async execution
• Checkpointers - Memory, SQLite, and Redis state persistence
• Graph-Relative Prompts - Colocate prompts with graphs
• JSON Extraction - Auto-extract JSON from LLM responses
• LangSmith - Observability and tracing
• JSON Export - Result serialization

What is YAMLGraph?

YAMLGraph is a declarative LLM pipeline orchestration framework that lets you define complex AI workflows entirely in YAML—no Python required for 60-80% of use cases. Built on LangGraph, it provides multi-provider LLM support (Anthropic, Google/Gemini, OpenAI, Mistral, Replicate, xAI, LM Studio), parallel batch processing via map nodes (using LangGraph Send), LLM-driven conditional routing, graph-level streaming, and human-in-the-loop interrupts with checkpointing. Pipelines are version-controlled, linted, and observable via LangSmith. The key insight: by constraining the API surface to YAML + Jinja2 templates + Pydantic schemas, YAMLGraph trades some flexibility for dramatically faster prototyping, easier maintenance, and built-in best practices—making it ideal for teams who want production-ready AI pipelines without the complexity of full-code frameworks.

Installation

From PyPI

pip install yamlgraph

# With Redis support for distributed checkpointing
pip install yamlgraph[redis]

From Source

git clone https://github.com/sheikkinen/yamlgraph.git
cd yamlgraph
pip install -e ".[dev]"

Quick Start

1. Create a Prompt

Create prompts/greet.yaml:

system: |
  You are a friendly assistant.

user: |
  Say hello to {name} in a {style} way.

2. Create a Graph

Create graphs/hello.yaml:

version: "1.0"
name: hello-world

nodes:
  greet:
    type: llm
    prompt: greet
    variables:
      name: "{state.name}"
      style: "{state.style}"
    state_key: greeting

edges:
  - from: START
    to: greet
  - from: greet
    to: END

3. Set API Key

export ANTHROPIC_API_KEY=your-key-here
# Or: export MISTRAL_API_KEY=... or OPENAI_API_KEY=...

4. Run It

yamlgraph graph run graphs/hello.yaml --var name="World" --var style="enthusiastic"

Or use the Python API:

from yamlgraph import load_and_compile

graph = load_and_compile("graphs/hello.yaml")
app = graph.compile()
result = app.invoke({"name": "World", "style": "enthusiastic"})
print(result["greeting"])

With tracing (when LangSmith is configured via .env or env vars):

from yamlgraph import load_and_compile, create_tracer, get_trace_url, inject_tracer_config

graph = load_and_compile("graphs/hello.yaml")
app = graph.compile()
tracer = create_tracer()  # None if LangSmith not configured
result = app.invoke({"name": "World"}, config=inject_tracer_config({}, tracer))
print(get_trace_url(tracer))  # https://smith.langchain.com/o/.../r/...

---

More Examples

# Content generation pipeline
yamlgraph graph run examples/demos/yamlgraph/graph.yaml --var topic="AI" --var style=casual

# Sentiment-based routing
yamlgraph graph run examples/demos/router/graph.yaml --var message="I love this!"

# Self-correction loop (Reflexion pattern)
yamlgraph graph run examples/demos/reflexion/graph.yaml --var topic="climate change"

# AI agent with shell tools
yamlgraph graph run examples/demos/git-report/graph.yaml --var input="What changed recently?"

# Web research agent (requires: pip install yamlgraph[websearch])
yamlgraph graph run examples/demos/web-research/graph.yaml --var topic="LangGraph tutorials"

# Show LangSmith trace URL (requires LANGCHAIN_TRACING_V2=true + LANGSMITH_API_KEY)
yamlgraph graph run examples/demos/yamlgraph/graph.yaml --var topic="AI" --share-trace

📂 More examples: See examples/README.md for the full catalog including:

• Parallel fan-out with map nodes
• Human-in-the-loop interview flows
• Code quality analysis pipelines
• FastAPI integrations

Documentation

📚 Start here: reference/README.md - Complete index of all 18 reference docs

Reading Order

Level	Document	Description
🟢 Beginner	Quick Start	Create your first pipeline in 5 minutes
🟢 Beginner	Graph YAML	Node types, edges, tools, state
🟢 Beginner	Prompt YAML	Schema and template syntax
🟡 Intermediate	Common Patterns	Router, loops, agents
🟡 Intermediate	Map Nodes	Parallel fan-out processing
🟡 Intermediate	Interrupt Nodes	Human-in-the-loop
🔴 Advanced	Subgraph Nodes	Modular graph composition
🔴 Advanced	Async Usage	FastAPI integration
🔴 Advanced	Checkpointers	State persistence

More resources:

• Examples - Working demos and production patterns
• Feature Requests - Roadmap and planned improvements
• ARCHITECTURE.md - Internal architecture for core developers

Architecture

🏗️ For core developers: See ARCHITECTURE.md for:

• Module architecture and data flows
• Extension points (adding node types, providers, tools)
• Testing strategy and patterns
• Code quality rules

See ARCHITECTURE.md for detailed module line counts and responsibilities.

Key Patterns

📚 Full guide: See reference/patterns.md for comprehensive patterns including:

• Linear pipelines with dependencies
• Branching and conditional routing
• Map-reduce parallel processing
• LLM-based routing
• Human-in-the-loop workflows
• Self-correction loops (Reflexion)
• Agent patterns with tools

Environment Variables

Variable	Required	Description
ANTHROPIC_API_KEY	Yes*	Anthropic API key (* if using Anthropic)
MISTRAL_API_KEY	No	Mistral API key (required if using Mistral)
OPENAI_API_KEY	No	OpenAI API key (required if using OpenAI)
PROVIDER	No	Default LLM provider (anthropic/mistral/openai)
ANTHROPIC_MODEL	No	Anthropic model (default: claude-haiku-4-5)
MISTRAL_MODEL	No	Mistral model (default: mistral-large-latest)
OPENAI_MODEL	No	OpenAI model (default: gpt-4o)
REPLICATE_API_TOKEN	No	Replicate API token
REPLICATE_MODEL	No	Replicate model (default: ibm-granite/granite-4.0-h-small)
XAI_API_KEY	No	xAI API key
XAI_MODEL	No	xAI model (default: grok-4-1-fast-reasoning)
LMSTUDIO_BASE_URL	No	LM Studio server URL (default: http://localhost:1234/v1)
GOOGLE_API_KEY	No	Google API key (required if using Google/Gemini)
GOOGLE_MODEL	No	Google model (default: gemini-2.0-flash)
LMSTUDIO_MODEL	No	LM Studio model (default: qwen2.5-coder-7b-instruct)
LANGCHAIN_TRACING_V2	No	Enable LangSmith tracing (true to enable)
LANGSMITH_API_KEY	No	LangSmith API key
LANGCHAIN_ENDPOINT	No	LangSmith endpoint URL
LANGCHAIN_PROJECT	No	LangSmith project name

Testing

Run the test suite:

# Run all tests
pytest tests/ -v

# Run only unit tests
pytest tests/unit/ -v

# Run only integration tests
pytest tests/integration/ -v

# Run with coverage report
pytest tests/ --cov=yamlgraph --cov-report=term-missing

# Run with HTML coverage report
pytest tests/ --cov=yamlgraph --cov-report=html
# Then open htmlcov/index.html

See ARCHITECTURE.md for testing patterns and fixtures.

Security

Shell Command Injection Protection

Shell tools (defined in graphs/*.yaml with type: tool) execute commands with variable substitution. All user-provided variable values are sanitized using shlex.quote() to prevent shell injection attacks.

# In graph YAML - command template is trusted
tools:
  git_log:
    type: shell
    command: "git log --author={author} -n {count}"

Security model:

• ✅ Command templates (from YAML) are trusted configuration
• ✅ Variable values (from user input/LLM) are escaped with shlex.quote()
• ✅ Complex types (lists, dicts) are JSON-serialized then quoted
• ✅ No eval() - condition expressions parsed with regex, not evaluated

Example protection:

# Malicious input is safely escaped
variables = {"author": "$(rm -rf /)"}
# Executed as: git log --author='$(rm -rf /)'  (quoted, harmless)

See yamlgraph/tools/shell.py for implementation details.

⚠️ Security Considerations

Shell tools execute real commands on your system. While variables are sanitized:

1. Command templates are trusted - Only use shell tools from trusted YAML configs
2. No sandboxing - Commands run with your user permissions
3. Agent autonomy - Agent nodes may call tools unpredictably
4. Review tool definitions - Audit tools: section in graph YAML before running

For production deployments, consider:

• Running in a container with limited permissions
• Restricting available tools to read-only operations
• Implementing approval workflows for sensitive operations

License

MIT w/ SWC

Remember

Prompts in yaml templates, graphs in yaml, shared executor, pydantic, data stored in sqlite, langgraph, langsmith, venv, tdd red-green-refactor, modules < 400 lines, kiss