What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each subagent on its own context window and its own model, and what the session produced. Local and read-only — your session content never leaves the machine.

The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.

Desktop workbench for Claude Code — live subagent topology, token cost breakdown with drill-down, hook sandbox, config audit. Reads your session files locally. Electron, MIT.

⌥ Coding agent with the IDE wired in

Metis is a coding agent that boosts AI/LLM coding performance by 50%