codesession-cli and openclaw-trace
These tools are complementary: `openclaw-trace` provides end-to-end tracing and observability specifically for OpenClaw multi-agent systems, while `codesession-cli` offers a broader cost tracking solution for various AI agent frameworks, including OpenClaw, making it ideal to use the two together to gain both deep system insights and comprehensive financial oversight.
About codesession-cli
brian-mwirigi/codesession-cli
Track what your AI agents cost including files, commits, tokens, budgets. CLI , Dashboard+ API. Works with OpenClaw, Claude Code, and any agent framework.
Provides local API interception via an HTTP proxy (listening on localhost only) that captures Anthropic and OpenAI API calls in real-time, storing all metadata in a SQLite database without persisting prompts or keys. Integrates via ClawHub skills, Model Context Protocol, or wraps any script with `cs run`, plus offers a local web dashboard with budget alerts, session timelines, and per-model cost breakdowns—all without cloud dependency or telemetry.
About openclaw-trace
Tell-Me-Mo/openclaw-trace
End-to-end tracing and observability for OpenClaw multi-agent systems
Provides real-time dashboards and REST APIs for tracking token consumption, costs, and tool usage across OpenClaw agent sessions by parsing local JSONL files. Features budget monitoring with daily/monthly limits, 7-day historical trends, A/B heartbeat comparison, and optimization hints like cache hit rates and waste detection. Runs as a standalone Node.js server with no external dependencies, accessible at localhost:3141.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work