crmne/ruby_llm

Ruby AI 프레임 워크

AI는 루비 방법을 제공합니다 : 모델, 도구, 에이전트, 샌드 박스 코드, 평가, 레일 컨벤션, 함께 설계, 일관적인 API.

웹 사이트 · 시작 · 2.1에서 새로운 기능

에 테스트 전투 - *Fully 개인 작업 AI *

https://github.com/user-attachments/assets/519fcb20-ab8c-4af3-9185-0953b3ba7b81] [T0]] [T0]] [T0]] [T0]] [T0]] [T0]] [T0]] [T0] [T0] [T0]] [T0] [T0] [T0]] [T0]] [T0] [T0] [T0] [T0] [T0]] [T0] [T0]] [T0] [T0] [T0]] [T0]] [T0] [T0] [T0]] https://github.com/user-attachments/assets/519fcb20-ab8c-4af3-9185-0953b3ba7b81] https://github.com/user-attachments/assets/519fcb20-ab8c-4af3-9185-0953b3ba7b81]]] https://github.com/user-attachments/assets/519fcb20-ab8c-4af3-9185-0953b3ba7b81]]]]]] [[https://github.com/user-attachments/assets/519fcb20-ab8c-4af3-9185-0953b3ba7b81]]]]]]] [[[[[[https://github.com/user-attachments/assets/519fcb20-ab8c-4af3-9185-0953b3ba7b81]]]]]]]]]]]]]] [[[[[[[https://github.com/user-attachments/assets/519fcb20-ab8c-4af3-9185-0953b3ba7b81]]]]]]]]]]]]]]]]]] [[[[[[[[[[[[[[[[[[[[[[

[!노트] RubyLLM 사용? 당신의 이야기를 공유! 도보 5분

---

23 공급자. 1개의 API.

당신이 원하는 모델과 빌드. 호스팅 및 로컬 공급자 간의 이동하여 응용 프로그램을 재 작성하거나 OpenAI 호환 엔드포인트를 연결하십시오.

검색 모델 및 가격 · 공급자 연결

Ruby를 위한 완벽한 AI 기구

모델 API에 대한 클라이언트 이상. RubyLLM은 애플리케이션의 컨벤션, 런타임 및 각 조각을 제공합니다. 코드가 안전하고 워크플로우, 평가, 관찰성 및 함께 작동하도록 설계된 데이터를 안전하게 실행하는 에이전트.

*Code 실행 (주): 서버에서 Ruby, Python, JavaScript, shell을 실행하자 with_code_execution

https://github.com/user-attachments/assets/519fcb20-ab8c-4af3-9185-0953b3ba7b81

[!NOTE] Using RubyLLM? Share your story! Takes 5 minutes.

---

23 providers. One API.

Build with the models you want. Move between hosted and local providers without rewriting your application, or connect an OpenAI-compatible endpoint.

Browse models and pricing · Connect a provider

A complete AI framework for Ruby

More than a client for model APIs. RubyLLM gives your application the conventions, the runtime, and every piece in between: agents that run code safely, workflows, evaluations, observability, and the data they need, designed to work together.

• Code execution (main): Let the model run Ruby, Python, JavaScript, and shell in a sandbox on your servers with with_code_execution
• Skills (main): Teach the model your workflows with folders of instructions and scripts in the Agent Skills format with with_skills
• MCP: Connect agents to your systems with server classes in app/mcp, per-user inputs, tool filtering, and OAuth with RubyLLM::MCP
• Agents: Reusable assistants with RubyLLM::Agent
• The agentic loop: Drive it yourself with ask_later, step, and complete?