Deployment

pip (recommended)

pip install peaky-peek-server
peaky-peek --open

Docker

docker build -t peaky-peek .
docker run -p 8000:8000 -v ./traces:/app/traces peaky-peek

Quick Start

Option 1: Decorator (simplest)

pip install peaky-peek-server
peaky-peek --open   # launches API + UI at http://localhost:8000

from agent_debugger_sdk import trace

@trace
async def my_agent(prompt: str) -> str:
    # Your agent logic here — traces are captured automatically
    return await llm_call(prompt)

Option 2: Context Manager

from agent_debugger_sdk import trace_session

async with trace_session("weather_agent") as ctx:
    await ctx.record_decision(
        reasoning="User asked for weather",
        confidence=0.9,
        chosen_action="call_weather_api",
        evidence=[{"source": "user_input", "content": "What's the weather?"}],
    )
    await ctx.record_tool_call("weather_api", {"city": "Seattle"})
    await ctx.record_tool_result("weather_api", result={"temp": 52, "forecast": "rain"})

Option 3: Zero-Config Auto-Patch (no code changes)

```bash

Set env var, then run your agent normally

PEAKY_PEEK_AUTO_PATCH=true python my_agent.py ```

Works with PydanticAI, LangChain, OpenAI SDK, CrewAI, AutoGen, LlamaIndex, and Anthropic — no imports or decorators needed.

---

OpenAI SDK

No code needed — just set the environment variable:

PEAKY_PEEK_AUTO_PATCH=true python my_openai_agent.py

Or use the simplified decorator:

from agent_debugger_sdk import trace

@trace(name="openai_agent", framework="openai")
async def my_agent(prompt: str) -> str:
    client = openai.AsyncOpenAI()
    response = await client.chat.completions.create(
        model="gpt-4o", messages=[{"role": "user", "content": prompt}]
    )
    return response.choices[0].message.content

Framework Integrations

Session Comparison

<p> <img src="./docs/assets/gifs/demo-comparison.gif" alt="Session comparison demo" width="640" /> </p>

Compare two agent runs side-by-side. See diffs in turn count, speaker topology, policies, stance shifts, and grounded decisions.

---