ai-trains-ai
I RL-trained an agent that trains models with RL (for –$1.3k)
开源项目、精巧工具,还有让人眼前一亮的点子。
从 Hacker News 社区讨论中,找到你的下一份灵感。
I RL-trained an agent that trains models with RL (for –$1.3k)
Docx-CLI: agents read/edit Word docs using 1/2 the time and tokens
Free way to get your data out of ChatGPT Business accounts
Kastor – Terraform-style specs for AI agents
Agent-talk: Enabling coding agents to work together
CLI tool for detecting non-exact code duplication with embedding models
Same model, same Q4_K_M label: 5.02, 5.07 and 5.27 bits per weight
Wrapper – Best Ever Agent Manager
Tarit – Self-host sandbox cloud and hypervisor for AI agents
OpenIngress – agent crawl and navigation checks
Agentty ADE: reliable L2 multi-agent orchestrator
Use After Effects with Claude Code, Cursor and Antigravity
Hibernate and restore Claude Code sessions across reboots
Ingot, evidence-gated optimization and version control for agent skills
Plasma Wiki – a CLI for maintaining agent-edited Markdown wikis
Sigil – compile a SKILL.md the model MUST run, not "might"
A UML drawing skill for your coding agent docs
Let your coding agent iterate by seeing the browser