LLM 模型排行

Interview questions and prep for AI Engineer, LLM Engineer, and Applied AI roles. Built for software engineers breaking into AI and ML practitioners levelling up: company-specific question sets, role-based study maps, worked answers, and from-scratch coding challenges.

一份来自2026年的AI精神病理学诊断报告 / A Pathological Diagnosis of AI Civilization

Multi-Agent Debugger: An AI-powered debugging system using CrewAI to orchestrate specialized agents that analyze logs, trace code, and uncover root causes across your stack — powered by LLM providers.

Latxa: An Open Language Model and Evaluation Suite for Basque

Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed execution, and multi-agent workflows. Web and desktop.

Tool to automatically generate text descriptions for images using Ollama vision models (LLaVA, Qwen3-VL, Llama Vision)

Build use cases with VideoDB

Native iOS app for talking to your OpenClaw agents by voice or text. On-device speech recognition, streaming responses, multi-agent channels.

From-scratch C++23/CUDA inference engine for the NVIDIA RTX 5090 (sm_120a). The best single-GPU backend for agentic AI: tool calling, long-context loops, reasoning and concurrent sub-agents. Decode beats llama.cpp b9976 by 42-48% on dense GGUF (measured 2026-07-12), at-or-ahead of vLLM on NVFP4. 100% written by Claude Code.

A family of highly efficient, lightweight yet powerful optimizers.

One GPU. Full LLM workflow. Real benchmarks. No cloud required.

12 Vibe Coding Factors · 10x Engineer Efficiency

ChatGPT, related application + prompt engineering list

Make AI text sound human - rules + a Claude Code skill, built for Russian, works for English too.

Professional-grade skills for Claude Code & Claude AI - Transform Claude into a domain expert in seconds

RAMen is a fast in-memory data store like Redis, but built for AI: drop-in Redis protocol, native vector search, semantic caching, and a built-in MCP server for agents. Single Go binary, BSD-3.

Your intelligent ally for effortless information retrieval and seamless browsing across documents and the web.

Private, on-device AI desktop app — GGUF (llama.cpp) & MLX, with Qwen3.8's native reasoning-effort ladder wired in as a real control. Local coding agent, RAG knowledge base, Deep Research, vision and voice. 100% offline, no account, no telemetry. Windows & macOS.

A continuously-verified dataset of free-tier & trial-credit LLM APIs for developers. Every entry dated, sourced to the provider's own docs, and machine-readable. No hype, no dead links.

Plug-and-play, dependency-free web command center for DGX Spark fleets (and any GPU boxes): live per-node GPU/CPU/mem/temps/power, optional RouterOS switch monitoring, and per-model decode/prefill/TTFT/KV cards. Point it at your own hardware.