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 ★
- Hivemind — Hivemind turns your traces into reusable skills across agents 1.6k ★
- Cost Xray — See what Claude Code and Codex actually send to the API — and what each part costs 586 ★
README
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
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
MiniMax M2 Interleaved Thinking
Interactive demo showcasing MiniMax-M2's interleaved thinking for agentic workflows, demonstrating adaptive st
Ashlr Brief
Toggle response-shortening (caveman-inspired, ashlr-flavored) with three intensity levels. Trims filler from C
Cc Wire Analyzer
Local Claude Code HTTP traffic inspector with a desktop GUI and agent API. Capture prompts, tools, SSE, errors
AgentPlayback
Are you running too few agents, or too many? AgentPlayback visualizes your coding agents so you can see when e
Related Agents
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
Part 16: autoDream — Automatic Memory Consolidation
Note: OpenClaw 2026.4+ has a built-in dreaming system (Part 22) inside memory-core. If you're on 2026.4+, use