Argus – VSCode debugger for Claude Code sessions
Analyzes Claude Code sessions, but mostly visualizes what Claude already logs.
VS Code extension that makes your AI coding agents observable. Works with GitHub Copilot and Claude Code
Parses local JSONL session files from Copilot, Claude Code, and Codex and surfaces an interactive DAG, per-agent/token metrics, and session replay directly in the activity bar — immediately useful for spotting which agents and skills actually do the work. The Claude cache-token breakdown and timeline replay are clever, concrete features that show the author dug into provider internals; adoption looks small today, but the concept and implementation give real observability where previously there was opacity.
Developers and engineering teams using AI coding assistants (Copilot, Claude Code, Codex) who want visibility into agent behavior and token usage
Analyzes Claude Code sessions, but mostly visualizes what Claude already logs.
250K users on OSS plugin, now measuring AI coding ROI for teams.
Debugger for Claude Code session costs—step-by-step breakdown of tokens and tool calls.
Claude Code inspector, but Cursor and Continue already expose token metrics natively.
AGENTS.md with retrieval discipline — Cursor rules and Continue.dev already provide similar context.
They promise more than autocomplete: autonomous workflows that plan an issue, implement, debug and open a PR, plus whole-codebase context and automatic test-suite generation. The privacy pitch — "we never store your code" via Google’s enterprise API — is the clearest differentiator, but it’s a claim that demands proof (audit logs, on-prem options, or clear data flows). Interesting product-market fit for teams, but the space is crowded and I’d want to see demos of real PRs and safety/rollback controls before betting on it.