staso 0.1.17

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

Staso Python SDK

See what your AI agents actually do. Every tool call, LLM interaction, token count, latency, and error — on your Staso dashboard.

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()

Open your dashboard. Full execution tree — agents, tools, LLM calls, tokens, timing, errors.

Auto-Instrument LLM Calls

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

st.integrations.patch_anthropic()
# Every Anthropic SDK call is now traced automatically — tokens, model, latency, errors.

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

Both sync and async clients. Streaming fully supported.

Claude Code Integration

Trace Claude Code CLI sessions — every turn, tool call, LLM interaction, subagent — automatically.

pip install staso
staso setup --target claude-code \
  --api-key ak_... \
  --workspace my-workspace \
  --environment production \
  --agent-id my-agent

Start a Claude Code session. Traces flow automatically.

Codex Integration

Trace OpenAI Codex CLI sessions — every turn and tool call.

pip install staso
staso setup --target codex \
  --api-key ak_... \
  --workspace my-workspace \
  --environment production \
  --agent-id my-agent

Docs

• Quickstart — 5 minutes to first trace
• Tracing — @agent, @tool, @trace, st.span()
• Conversations — Group traces by conversation
• Integrations — Anthropic, OpenAI, Claude Code, Codex
• Configuration — All options and env vars
• Troubleshooting — Common issues

Python 3.11+ · Apache 2.0