LLM-as-a-Verifier
用 LLM-as-a-Verifier 框架为 Agent 轨迹提供细粒度反馈,实现 Best-of-N 筛选、进度追踪和测试时扩展
共 37487 条已上架资产
用 LLM-as-a-Verifier 框架为 Agent 轨迹提供细粒度反馈,实现 Best-of-N 筛选、进度追踪和测试时扩展
用Whisper CLI本地语音转文字,免API Key,创意设计领域专用(社区下载版)
LLM Prompt 工程铁律 — Python 格式化转义/JSON mode 容错/heredoc 避坑
Unified LLM Gateway - One API for 70+ AI models
Persistent wiki manager based on Karpathy's LLM-Wiki pattern
Create and maintain a persistent LLM-maintained knowledge base (wiki) following Andrej Karpathy's pattern
Expert LLM architect specializing in large language model architecture, deployment, and optimization
Inspired by a public workflow shared by Andrej Karpathy (@karpathy)
LLM paper and project researcher
AI agent for call deepseek v3 llm tasks
Send requests to the dr
Routes LLM requests to a local model (Ollama, LM Studio, llamafile) before falling back to cloud APIs
Use when building or maintaining a self-contained personal knowledge base (an LLM wiki) in plain markdown
Local LLM model router for Llama, Qwen, DeepSeek, Phi, Mistral, and Gemma across multiple devices
Delegate precise, formalizable computations and factual lookups to Wolfram|Alpha via its LLM API (HTTP) to get verified …
个人知识库构建系统 — 基于 Karpathy LLM-Wiki 方法论,结合 obsidian-cli 实现高效的 Obsidian vault 管理
USE FOR RAG/LLM grounding
Auto-detect PC hardware (CPU/GPU/RAM/VRAM) -> Determine max LLM parameters -> Recommend models (3B/7B/8B/13B/34B/70B) + …
Use AIsa for model routing, provider setup, and Chinese LLM access
Applies fixes from a prior review-llm-artifacts run, with safe/risky classification