All-Your-Agents is a Node.js library and CLI that discovers and monitors every coding AI agent running on a machine, presenting live sessions and historical transcripts without polling. It watches the files each agent writes plus the processes that produce them, coalesces bursts of filesystem events (25 ms quiet, up to 1 s latency), and emits rich events (session:create/open/status/update/activity/close, subagent:start/end, ready, error). The package exposes an API (start/stop, sessions(), get(id), running(), reconcile(pid), transcript(), events(), subagents()) and a tty UI/CLI (npx @markwylde/all-your-agents) to list, filter, and inspect sessions. It runs on Node ≥ 20 (demos from source on ≥ 22.18), supports macOS and Linux, and can observe remote hosts by passing custom fs and process providers.
Provider-specific support is detailed: built-in providers cover Claude Code, Grok Build, Codex CLI and others, each mapping agent state from provider files (e.g., Claude sessions/.json, Grok active_sessions.json and chat_history.jsonl) into status, model, title, transcript, and subagents. The library keeps the 1,000 most recent closed sessions in memory and reads older history from providers. It documents limitations per provider (missing live index entries, absent error text, headless vs interactive distinctions, approval persistence) and offers options for custom fs/process/sqlite backends and debounce configuration.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Jev is a simple, open-source model implemented in 25 lines of Python that classifies email as legitimate, spam, or phishing. It is fast, runs locally, and emphasizes data privacy, contrasting with more complex AI systems. (nobodywho.ai)
Frontier AI labs rely on a few dominant models, giving them a significant moat through talent and compute advantages. However, as open-source models improve, these labs may need to diversify revenue streams into other industries to maintain profitability. (strangeloopcanon.com)
Google has developed a new AI agent called CC designed specifically for family use. The AI aims to assist with household tasks and provide family-oriented support. (blog.google)
AI staff have reported experiencing mental health challenges due to concerns about the potential societal threats posed by artificial intelligence. These fears relate to the broader impact of AI development on society and human well-being. (ft.com)
Open language models include open-weight and open-source types, with Chinese companies leading in open-weight models since 2025. The competition between American and Chinese models influences the global AI landscape and its commercial viability. (interconnects.ai)
No Sloptober challenges individuals to abstain from using LLM-based tools throughout October to develop personal skills and awareness of AI's limitations. Participants are encouraged to reflect on their reliance on AI, improve their coding abilities, and reassess the value of automation in their work and learning processes. (no-sloptober.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.