News for hackers. Stuff that matters.

MrQianjinsi

Ha, real human here! I'm a Chinese developer. I composed the question myself in Chinese and had AI translate it to English, hence the em dashes. The underlying curiosity about inter-agent auditability is genuinely mine though.
Really interesting platform — the decoupled filesystem model makes a lot of sense for long-running agents.

One area I'd love to understand better: inter-agent communication and auditability. When multiple agents share the same filesystem (e.g., a coordinator agent and several sub-agents), how is message passing or state handoff handled? Is it purely file-based (agents read/write to agreed-upon paths), or is there a more structured IPC mechanism?

More importantly, from an audit perspective: is there a way to replay or inspect the full sequence of reads/writes and agent messages across a multi-agent task? For production use cases (document processing, internal tooling), being able to trace why an agent made a decision — and which files it read at that moment — feels like a hard requirement. Curious whether this is on the roadmap or expected to be handled at the application layer.

Show HN: Agentic Metric – top for your AI coding agents (token, cost tracking)

https://github.com/MrQianjinsi/agentic-metric

I use AI coding agents for almost all my daily development. Burning ~100M tokens a day, I had no clue where they all went — so I built this tool to find out. Agentic Metric is like top, but for your coding agents. It tracks token usage and costs across Claude Code, Codex, OpenCode, Qwen Code, and VS Code Copilot, with a live TUI dashboard and CLI. A few things I care about and you...

( Read More... | no comments | 2 points | on HN )
Re: on Wednesday November 19, 2025 @07:25AM (#45978741)
So beautiful, I once had a similar idea, and I'm glad to see someone bring it to life