⬢github JavaScript · 718 ★ +11 since we first saw it · pushed 1 d ago · MIT
LockedinLabs-AI/agent-console
Local-first observability for AI coding agents. Every Claude Code and Codex session's tokens, cache, models and cost, on this machine and every machine you connect through a self-hosted team hub. Presenting mode, policy hooks, Apple-signed and notarized macOS builds, attested releases. MIT.
Agent Console is an open-source, local-first observability tool for AI coding agents. It reads Claude Code and Codex transcripts on your machine to show token usage, cache activity, models, and estimated costs, and can connect multiple machines via a self-hosted team hub. It includes presenting mode, Prometheus/Grafana integration, and verifiable, signed releases.
Why now: It's trending among newly starred repos, riding interest in tracking and governing the costs of AI coding agents like Claude Code and Codex; the v0.4.1 release adds supply-chain hardening like SBOMs and attestations.
Who it is for: Developers and teams using Claude Code or Codex who want to monitor and budget their AI token spending locally.
ai-agentsanthropicclaude-codecodexdeveloper-toolsfinopsllm-observabilitylocal-firstobservabilityopenai
Stars over our 36 snapshots: 707 to 718, since 8 h ago.
Where people talked about it
- ⬢github new repos, most starred 12 min ago
API: https://socialmediatrends-api.osmike.com/v1/repos/LockedinLabs-AI/agent-console