a plugin that records everything your OpenClaw agents actually do
Summary
Trovis is a plugin for OpenClaw that records all agent actions, costs, and deviations, presenting them in plain English for better observability.
Similar Articles
I built an agent that records everything your agents actually do
Built Trovis, a tool that records and explains agent actions in production, showing deviations from expected behavior.
Your OpenClaw agent probably shouldn't be polling for everything
This article discusses the inefficiency of polling in OpenClaw agents and introduces a plugin that moves event detection outside the agent loop, resulting in significant reductions in source calls and token usage.
I built a little "police department" for my Claude Code subagents
A logging hook and CLI tool that records all tool calls and permission events from Claude Code agents into a session log, then replays the log to audit for misbehavior like unauthorized file reads or permission escalation. It is a catch-and-report flight recorder, not a blocker.
Roughly 3 month running OpenClaw as my daily agent system. What worked, what broke, what still annoys me.
A 13-week recap of using OpenClaw as a daily AI agent on a Raspberry Pi, highlighting strengths like cron-based automation and memory curation, and pain points like model config issues and subagent orchestration.
I made a small open-source benchmark runner for testing OpenClaw agents on my own real workflows
A developer shares a personal open-source benchmark runner for testing OpenClaw agents on real, messy workflows. The tool allows users to define private evaluation cases, run agents in their actual workspace, and generate reports, aiming to provide more relevant signals than public benchmarks.