Show HN: Lazyagent – Preserve what your AI agents doing and analyze usage
TL;DR
Once subagents start spawning other subagents, basic questions get hard to answer: what is running right now, what tool did it just call, did the child agent actually do what the parent asked. I wanted a way to verify that each agent is doing the work that fits its role, and to spot when a run goes off track. Lazyagent is a terminal TUI that collects events from Claude Code, Codex, and OpenCode and shows them in one place.
Nauti's Take
Observability for AI agents is a genuine blind spot — anyone who has debugged complex multi-agent workflows knows how quickly things get opaque. Lazyagent tackles this head-on with a pragmatic terminal UI.
The tool is early-stage, so keeping pace with rapidly evolving agent runtimes is the real challenge, but the core idea is exactly what the ecosystem needs.
Sources