claw-insights and costclaw-telemetry
One tool provides open-source agent observability with session replay and metrics, while the other offers real-time LLM cost tracking specifically for OpenClaw agents, making them complements that can be used together to monitor both the performance and expenditure of AI agents.
About claw-insights
LucaL6/claw-insights
Open-source agent observability — session replay, metrics, and shareable snapshots for AI agent workflows
Operates as a zero-intrusion read-only sidecar that tails logs and CLI output without SDK integration, storing data locally in SQLite and exposing observability through GraphQL APIs and Server-Sent Events. Built with an adapter architecture for extensibility beyond OpenClaw, it includes structured AI agent skills for autonomous setup and snapshot capture via REST API or CLI. Tech stack spans Express, GraphQL Yoga, SQLite, Satori rendering, and a React 19 frontend with real-time ECharts dashboards for token analytics and error tracking.
About costclaw-telemetry
Aperturesurvivor/costclaw-telemetry
Reduce your OpenClaw agent costs. Free real-time LLM cost tracking + dashboard. Installs in 60 seconds.
Captures LLM calls via OpenClaw's native event hooks and stores usage breakdowns (by model, source, session) in local SQLite with PII redaction, then serves insights through a dashboard with per-source cost analysis (user messages vs. heartbeat vs. cron vs. subagents) and auto-generated optimization recommendations. Supports 30+ models across Anthropic, OpenAI, Google, xAI, and Meta with customizable pricing tables, and provides agent-callable tools to query spend and retrieve cost breakdowns programmatically.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work