{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiemyqwjbeg6sqofrsnqhupv64aisc7py3hu4s2nlrfxvjxphoaaam",
    "uri": "at://did:plc:kfvfl6lsmxg64yzszmfotdq2/app.bsky.feed.post/3mkw2xu5cwpg2"
  },
  "path": "/t/ruby-talk-444809-ann-llm-rb-v5-1-0-released/76763#post_1",
  "publishedAt": "2026-04-25T03:47:13.000Z",
  "site": "https://rubytalk.org",
  "tags": [
    "GitHub - llmrb/llm.rb: Ruby's most capable AI runtime · GitHub",
    "llm.rb | RubyGems.org | your community gem host",
    "File: CHANGELOG — Documentation by YARD 0.9.36",
    "(click for more details)"
  ],
  "textContent": "Hello\n\nllm.rb is the most capable runtime for building AI systems in Ruby.\n\nIt is built on the standard library (zero dependencies) but it can\nstill support advanced features through optional dependencies that\nare loaded on-demand.\n\nFor example, it can integrate with both ActiveRecord and Sequel, and\nsupports persistent connection pools with net-http-persistent.\n\nSince my last email, skill support has been added. It behaves in a similar\nway to Claude or Codex skills, and launches a sub-agent to execute a skill -\nwith a limited tool subset.\n\n[GitHub] GitHub - llmrb/llm.rb: Ruby's most capable AI runtime · GitHub\n[RG] llm.rb | RubyGems.org | your community gem host\n[CL] File: CHANGELOG — Documentation by YARD 0.9.36\n\n··· (click for more details)",
  "title": "[ruby-talk:444809] [ANN] llm.rb v5.1.0 Released"
}