Metadata-Version: 2.5
Name: parlot
Version: 0.1.1
Summary: Production voice AI observability — MIT OpenTelemetry instrumentation for LiveKit Agents
Project-URL: Homepage, https://parlot.ai
Project-URL: Documentation, https://parlot.ai/docs
Project-URL: Repository, https://github.com/parlot-ai/sdk
Author-email: Parlot AI <hi@parlot.ai>
License-Expression: MIT
License-File: LICENSE
Keywords: agents,ai,observability,opentelemetry,parlot,telemetry
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: System :: Monitoring
Requires-Python: >=3.11
Requires-Dist: parlot-core>=0.1.0
Provides-Extra: all
Requires-Dist: parlot-instrumentation-langgraph>=0.1.0; extra == 'all'
Requires-Dist: parlot-instrumentation-livekit>=0.1.0; extra == 'all'
Provides-Extra: langgraph
Requires-Dist: parlot-instrumentation-langgraph>=0.1.0; extra == 'langgraph'
Provides-Extra: livekit
Requires-Dist: parlot-instrumentation-livekit>=0.1.0; extra == 'livekit'
Description-Content-Type: text/markdown

# Parlot

**Production voice AI observability** — MIT OpenTelemetry instrumentation for LiveKit Agents (and LangGraph when you already run voice).

Know if your voice agent is actually working. Install the sidecar, call `configure()` once, and Parlot models each call as **turns**: timeline, multi-agent handoff graph, pipeline waterfall, and goal completion with an evidence trail to the proving turns and audio.

Works with LiveKit Cloud, self-hosted media, and [LiveKit on Telnyx](https://telnyx.com/products/livekit-on-telnyx).

## Install

```bash
# LiveKit Agents (recommended)
pip install "parlot[livekit]"

# LangGraph / LangChain (same debugger for text agents alongside voice)
pip install "parlot[langgraph]"

# Both
pip install "parlot[all]"
```

Or install an instrumentation package directly:

```bash
pip install parlot-instrumentation-livekit
# or
pip install parlot-instrumentation-langgraph
```

## Instrument (LiveKit)

```python
from parlot.instrumentation.livekit import configure

configure()
```

Call `configure()` before constructing `AgentSession`, then `await ctx.connect()` before `session.start()`. Set `PARLOT_ENDPOINT` and `PARLOT_API_KEY` (mint in Settings → API Keys).

Full checklist: [LiveKit guide](https://parlot.ai/docs/guides/livekit) · [Quick Start](https://parlot.ai/docs/quick-start)

## Documentation

[parlot.ai/docs](https://parlot.ai/docs) · [parlot.ai](https://parlot.ai) · [GitHub](https://github.com/parlot-ai/sdk)
