Declarative LLM orchestration. Define workflows in YAML — each action gets its own model, context window, schema, and pre-check gate. The framework handles DAG resolution, parallel execution, batch processing, and output validation.

actions:
  - name: extract_features
    intent: "Extract key product features from listing"
    model_vendor: anthropic              # Each action picks its own model
    model_name: claude-sonnet-4-20250514

  - name: generate_description
    dependencies: [extract_features]
    model_vendor: openai                 # Mix vendors in one pipeline
    model_name: gpt-4o-mini
    context_scope:
      observe:
        - extract_features.features      # See only what it needs
      drop:
        - source.raw_html                # Don't waste tokens on noise

pip install agent-actions

agac init my-project && cd my-project                # scaffold a project
agac init --example contract_reviewer my-project     # or start from an example
agac run -a my_workflow                              # execute

You will, until you have 15 steps, 3 models, batch retry, and a teammate asks what your pipeline does.

Switch providers per-action by changing model_vendor.

• Pre-flight validation — schemas, dependencies, templates, and credentials checked before any LLM call
• Batch processing — route thousands of records through provider batch APIs
• User-defined functions — Python tools for pre/post-processing and custom logic
• Reprompting — auto-retry when LLM output doesn't match schema
• Observability — per-action timing, token counts, and structured event logs
• Interactive docs — agac docs builds and serves a visual workflow dashboard

• Full docs — guides, tutorials, reference
• Configuration — YAML schema reference
• CLI — all commands and options

git clone https://github.com/Muizzkolapo/agent-actions.git && cd agent-actions
pip install -e ".[dev]"
pytest

See CONTRIBUTING.md. Report bugs via Issues.

Apache License 2.0