Item detail

vivekchand/clawmetry

ClawMetry is an MIT-licensed observability dashboard for AI agent runtimes including Claude Code, Codex, Hermes, Aider, and OpenClaw. It auto-detects supported runtimes and surfaces live cost, token, tool, log, memory, and transcript views from one local interface.

Score8.7
Popularity57.0
Riskconditional
TierGold
Score breakdown
Usefulness9.0
Novelty8.0
Momentum7.0
Maturity7.9
Open-source/build8.4
Evidence7.2
Workflow potential10.0
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for teams running multiple coding-agent shells and tired of debugging from scattered logs: install it on one non-sensitive workstation first, then decide whether the unified traces and usage views actually shorten review and incident time.

Who should use it

developers running multiple coding agentsAI platform teamsagent observability buildersteams reviewing cost and tool traces

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

Observability traces can capture prompts, tool outputs, code, and other sensitive session data, so scrub or scope what you ingest before using it on private work.

Evidence links

Closest alternatives / related signals

agent-observabilitycoding-agentslogstool-traceslocal-dashboard