clawmetry and openclaw-nerve
These two tools are complementary, with A providing real-time observability into the agent's thought processes and B offering a comprehensive web-based cockpit for controlling and visualizing agent interactions, file control, and sub-agent sessions within the OpenClaw ecosystem.
About clawmetry
vivekchand/clawmetry
See your agent think. Real-time observability dashboard for OpenClaw AI agents.
Provides live animated message flows across 18+ channels (Telegram, Discord, Slack, WhatsApp, Signal, Matrix, etc.), token/cost tracking by model and session, and workspace memory browsing—all auto-detected from `openclaw.json` with zero configuration. Built on Flask, it runs locally on port 8900 and streams real-time logs, cron job status, and agent event traces through a unified dashboard UI.
About openclaw-nerve
daggerhashimoto/openclaw-nerve
Real-time web cockpit for OpenClaw: voice conversations, agent automated kanban board, workspace/file control, sub-agent sessions, inline charts, and usage visibility.
Builds on WebSocket proxying to OpenClaw Gateway while adding real-time file watching via SSE and rich UI rendering for agent outputs—charts, diffs, syntax-highlighted code, and structured tool results rendered natively rather than as text. Supports multi-agent fleet orchestration with per-agent workspaces, memory, and identity management, plus operational primitives like cron scheduling, kanban boards, and session trees that extend beyond conversational interfaces. Frontend uses React 19 with Tailwind and shadcn/ui; backend is Hono on Node.js with optional password auth, local-by-default binding, and Tailscale integration for private remote access.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work