staso 0.1.16

Python SDK for Staso – observe, enforce, evaluate, and debug AI agents in production

Staso Python SDK

You're shipping AI agents to production. You need to know what they're actually doing — which tools they called, what the LLM returned, where they failed, and how much it cost. Staso gives you that.

pip install staso

import staso as st

st.init(api_key="ak_...", agent_id="my-agent")

@st.agent(name="support-agent")
def handle_request(message: str) -> str:
    context = search_kb(message)
    return call_llm(context, message)

@st.tool(name="search_kb")
def search_kb(query: str) -> str:
    return db.search(query)

with st.conversation("conversation-123"):
    handle_request("How do I reset my password?")

st.shutdown()

That's it. Open your Staso dashboard and you'll see the full execution tree — every agent run, tool call, LLM interaction, token count, latency, and error.

Auto-Instrument LLM Calls

pip install "staso[anthropic]"  # or "staso[openai]"

st.integrations.patch_anthropic()
# Every Anthropic API call is now traced automatically.

st.integrations.patch_openai()
# Every OpenAI API call is now traced automatically.

Claude Code Integration

Trace Claude Code CLI sessions — tool calls, LLM token usage, turn timing — automatically.

pip install staso  # or: uv pip install staso
staso setup-claude-code \
  --api-key ak_... \
  --workspace my-workspace \
  --environment production \
  --agent-id my-agent

Start a Claude Code session and every turn, tool call, and LLM interaction is captured in your Staso dashboard.

Docs

• Quickstart
• Tracing your code
• Conversations
• LLM integrations
• Configuration
• Claude Code
• Troubleshooting

Python 3.11+ · Apache 2.0