CLI appSoftware development
agenttrace
Trace coding-agent session costs, failures, and slow runs locally
- Stars
- 96
- Forks
- 2
- Updated
- Updated Jul 7, 2026
MIT
Trace coding-agent session costs, failures, and slow runs locally
AgentTrace reads local session logs from Claude Code, Codex CLI, Gemini CLI, Cursor, OpenCode, and other agent tools, then surfaces token usage, estimated cost, elapsed time, failures, latency, context pressure, and anomalies in a terminal UI. It can compare against a local baseline, export JSON, Markdown, or HTML reports, and fail CI on unhealthy runs. The inspection is local-first, with no hosted backend required for prompts, code, or logs.
Resource types
Use cases
Platforms
Package any website as a desktop app through a CLI or online build.
Run coding agents through task lists and monitor every iteration from a terminal UI.
Runtime
Capabilities
Audience
Public GitHub facts last synced Jul 10, 2026.
Use natural-language chat with Amazon Q for development tasks in the terminal.
Set up Windows SDKs, app identity, signing, and MSIX packaging from one CLI.