Announcing CRUX-in-a-box: open-source infrastructure for running and monitoring…
This is a dev post classified by AGK Intelligence as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.
Announcing CRUX-in-a-box: open-source infrastructure for running and monitoring weeks-long agent evaluations. We built it over six months of long-horizon evaluations in CRUX, to keep runs repeatable, secure, and monitored. AI evaluators can now use it to: - Run agents on VMs for weeks - Use LLMs to flag risky actions for human review - Inspect tool calls, tokens, and spend - Set time and cost budgets - Chat with agents mid-run to give feedback or answer their questions If you run long-horizon agent experiments, we might have solved some of the problems you will come across. GitHub: https
Posted by Sayash Kapoor (16.3k followers) 2 h ago · 21 likes · 862 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: crux-in-a-box.
More dev work like this
- TensorFold 1.2.3 is out. 🚀 — @ashxhart
- 这款翻译工具被不少人直接封神，如今总算开源了！ — @bkdgiffug
- NEAR co-founder Illia Polosukhin opens a public contest to improve AI models — @BSCNews
- Agentic AI For Platform Engineering: Rethinking Developer Platforms With Agentic AI,… — @gp_pulipaka
- Agentic Architectural Patterns for Building Multi-Agent Systems: Proven Design Patterns… — @gp_pulipaka
- SGD and #DeepLearning Optimizers! #BigData #Analytics #DataScience #AI #MachineLearning… — @gp_pulipaka
- AI Agents and Applications: With LangChain, LangGraph, and MCP! #BigData #Analytics… — @gp_pulipaka
- Vals AI is hosting its first-ever hackathon, and for one weekend, benchmaxxing is the… — @ValsAI
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.7k posts from 5k X accounts over the last 21 days, 9.4k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-05 21:22 UTC. Full method.