Metadata-Version: 2.4
Name: cogniguardai
Version: 0.1.0
Summary: AgentMonitor — flight recorder for AI agents. Records prompts, tool calls, files, cost, and latency. Local-first dashboard.
Author-email: CogniGuard AI <hello@cogniguardai.com>
License: MIT
Project-URL: Homepage, https://cogniguardai.com
Project-URL: Documentation, https://github.com/cogniguardai/agentmonitor#readme
Project-URL: Repository, https://github.com/cogniguardai/agentmonitor
Project-URL: Issues, https://github.com/cogniguardai/agentmonitor/issues
Project-URL: Changelog, https://github.com/cogniguardai/agentmonitor/releases
Keywords: ai,agents,observability,llmops,monitoring,flight-recorder,openai,anthropic,langchain
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: System :: Monitoring
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: fastapi>=0.110
Requires-Dist: uvicorn[standard]>=0.27
Requires-Dist: pydantic>=2.0
Requires-Dist: httpx>=0.25
Requires-Dist: rich>=13.0
Requires-Dist: PyYAML>=6.0
Requires-Dist: pywebview>=5.0
Provides-Extra: ml
Requires-Dist: torch>=2.1; extra == "ml"
Requires-Dist: transformers>=4.40; extra == "ml"
Requires-Dist: einops>=0.8; extra == "ml"
Provides-Extra: browser
Requires-Dist: playwright>=1.40; extra == "browser"
Provides-Extra: all
Requires-Dist: torch>=2.1; extra == "all"
Requires-Dist: transformers>=4.40; extra == "all"
Requires-Dist: einops>=0.8; extra == "all"
Requires-Dist: playwright>=1.40; extra == "all"
Provides-Extra: dev
Requires-Dist: pytest>=8.0; extra == "dev"
Requires-Dist: ruff>=0.5; extra == "dev"
Requires-Dist: build>=1.0; extra == "dev"
Requires-Dist: twine>=5.0; extra == "dev"
Dynamic: license-file

# AgentMonitor

[![Live](https://img.shields.io/badge/Live-cogniguardai.com-0e8a16?style=flat-square&logo=cloudflare&logoColor=white)](https://cogniguardai.com/) [![PyPI](https://img.shields.io/pypi/v/cogniguardai.svg?style=flat-square&label=PyPI&color=8b5cf6)](https://pypi.org/project/cogniguardai/) [![Status](https://img.shields.io/badge/Status-pre--release-orange?style=flat-square)](https://github.com/cogniguardai/agentmonitor#install)

> *See what your AI agent actually did.*

**Live at <https://cogniguardai.com/>** &mdash; marketing site is up; functional v0.1.0 ships soon.

**AgentMonitor** is a flight recorder for AI agents. It records every
prompt, tool call, file touched and dollar spent &mdash; so when your agent
does something weird, you can rewind and see exactly what happened.

- **Local-first.** Runs as a desktop app on your laptop. Your prompts
  never leave your machine.
- **Free.** No signup, no telemetry, no cloud account. Forever.
- **Works with what you use.** Cursor, Claude Code, OpenAI, Anthropic,
  LangChain, AutoGen, Smolagents, Ollama &mdash; and any custom agent.

Made by [CogniGuard AI](https://cogniguardai.com/).

## Install

> **Status:** the PyPI namespace [`cogniguardai`](https://pypi.org/project/cogniguardai/)
> is reserved (v0.0.1 placeholder). The first functional release lands as
> **v0.1.0**. Until then, the only working install is from source &mdash;
> see _Run from source_ below.

When v0.1.0 ships:

```bash
pip install cogniguardai
agentmonitor   # opens the dashboard at http://localhost:8765
```

### Run from source (works today)

```bash
git clone https://github.com/cogniguardai/agentmonitor.git
cd agentmonitor
pip install -r requirements.txt
python -m agent_monitor.run_server
# then open http://localhost:8765
```

## What it does

1. **Record.** Every agent run is captured automatically &mdash; prompts,
   tool calls, files touched, tokens spent, money burned.
2. **Replay.** Open any past run and scroll through it like a video.
3. **Rewind.** When something goes wrong, you have the receipts.

## Documentation

- **Marketing site & live demo**: <https://cogniguardai.com/>
- **Issues / feature requests**: [GitHub Issues](https://github.com/cogniguardai/agentmonitor/issues)
- **Email**: <hello@cogniguardai.com>

## Repository layout

```
agent_monitor/   Python package (the recorder + dashboard backend)
marketing/       Source for the marketing site at cogniguardai.com
requirements.txt Python dependencies
```

## License

MIT &mdash; see [`LICENSE`](LICENSE).

## Privacy

AgentMonitor does not phone home. Ever. All data lives in a local
SQLite database on your machine. There is no analytics, no telemetry,
no signup, no account.
