
agtrace provides a unified timeline and analysis layer for fragmented AI agent logs. Use the CLI for instant visualization, or build custom monitoring tools with the SDK.
🌟 Core Value
- Universal Normalization: Converts diverse provider logs (Claude, Gemini, etc.) into a standard
AgentEventmodel. - Schema-on-Read: Resilient to provider updates. No database migrations needed.
- Local-First: 100% offline. Privacy by design.
🚀 Quick Start (CLI)
The reference implementation of the agtrace platform.
🛠️ Building with the SDK
Embed agent observability into your own tools (vital-checkers, IDE plugins, dashboards).
[]
= "0.2"
use ;
let client = connect_default.await?;
let sessions = client.sessions.list?;
if let Some = sessions.first
See also: SDK Documentation | Examples | SDK README
📚 Documentation
- Why agtrace? - Understanding the problem and solution
- Getting Started - Detailed installation and usage guide
- Architecture - Platform design and principles
- SDK Documentation - Building custom tools
- Full Documentation - Commands, FAQs, and more
🔌 Supported Providers
- Claude Code (Anthropic)
- Codex (OpenAI)
- Gemini (Google)
📦 Architecture
graph TD
CLI[agtrace-cli] --> SDK[agtrace-sdk]
YourApp[Your Tool] --> SDK
SDK --> Core[Core Engine & Providers]
- Core SDK:
agtrace-sdk,agtrace-engine,agtrace-providers - Applications:
agtrace-cli(Reference Implementation)
License
Dual-licensed under the MIT and Apache 2.0 licenses.