Opik Openclaw — Development skill for Claude Code
🦞 Official plugin for OpenClaw that exports agent traces to Opik.
How to install Opik Openclaw
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open comet-ml/opik-openclaw and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Opik Openclaw does
🦞 Official plugin for OpenClaw that exports agent traces to Opik. See and monitor agent behaviour, cost, tokens, errors and more.
Alternatives in Development
- Mempalace Mine — Mine projects and conversations into the MemPalace 58.6k ★
- Cost Xray — See what Claude Code and Codex actually send to the API — and what each part costs 586 ★
- Notebooklm — Query and manage Google NotebookLM notebooks with persistent auth, batch/multi queries, source sync, and struc 159 ★
README
🔠OpenClaw Opik Observability Plugin
🔠OpenClaw Opik Observability Plugin
Official plugin for OpenClaw that exports agent traces to
Opik for observability and monitoring.
[](./LICENSE) [](https://www.npmjs.com/package/@opik/opik-openclaw)
Why This Plugin
[Opik](https://github.com/comet-ml/opik) is the open-source LLM observability and evaluation platform, built by [Comet](https://www.comet.com). `@opik/opik-openclaw` adds native Opik tracing for OpenClaw runs:
- LLM request/response spans
- Sub-agent request/response spans
- Tool call spans with inputs, outputs, and errors
- Run-level finalize metadata
- Usage and cost metadata
The plugin runs inside the OpenClaw Gateway process. If your gateway is remote, install and configure the plugin on that host.
Install and first run
Prerequisites:
- OpenClaw
>=2026.3.2
Related Skills
Argus Code
See what Claude Code actually did. Local-first observability for every session: which tools ran, what each sub
Root Cause Tracing
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematical
Go Debug
Debug a Go issue - analyze errors, traces, and behavior
Axguard Debug
Debug / verbose errors — Django DEBUG, Flask debug, stack traces to clients. Usage: /axguard-debug [path]
Langsmith Fetch
Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging ag
MiniMax M2 Interleaved Thinking
Interactive demo showcasing MiniMax-M2's interleaved thinking for agentic workflows, demonstrating adaptive st
Related Agents
Post Debugger
Diagnoses failed Upload-Post uploads, expired social tokens, scheduling errors, and AutoDM monitor failures. R
Execution Monitor
Monitor a running Syntropic137 workflow execution — polls for phase progress, reports status changes, alerts o
ClawPort -- Setup Guide
This guide walks you through getting ClawPort running against your own OpenClaw instance. If you just want the
