Claudectl-local LLM brain that learns to auto-pilot ClaudeCode sessions
Budget control with auto-kill saves money when agents go rogue on long runs.

Catches the moment you stop thinking and accept AI output without question.
Knowledge workers and researchers concerned about AI dependency
Glasp · Merlin
Budget control with auto-kill saves money when agents go rogue on long runs.
Daily philosophy reflection app, but unclear if enough to open daily vs. once.
The repo does one painful thing well: it inspects SESSION_ID.jsonl, pinpoints where streaming/interleaving corrupted 'thinking' blocks, and offers diagnose, fix (with auto-backup), and nuke fallbacks. It's pragmatic and ruthless — small CLI commands, clear recovery workflow, and rescue-first guidance — but it's narrowly targeted to Claude Code users and won't matter to most people.
Yet another stand reminder app, but with heart-rate monitor verification.
Cross-session visibility Claude Code should have built in.
Single dashboard view for parallel Claude Code and Codex agent sessions.