urumchi 的 GitHub 收藏

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

通过轨迹驱动优化，为冻结的LLM智能体训练可复用的自然语言技能

This is a repo for studying the application of LLM Agents on Games

研究LLM智能体在游戏中的应用

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

适用于Apple Silicon的LLM推理服务器，支持连续批处理和SSD缓存，通过macOS菜单栏管理

Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active.

增强版ChatGPT克隆，支持多模型、插件和自托管

AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods

AI代理工具包，包含编码代理CLI、统一LLM API、终端/网页UI、Slack机器人和vLLM集群

MultiPriv offers multilingual, multimodal PII entities and prompts for studying privacy risks in LLMs/VLMs. It also supports broader PII-related privacy research in diverse analysis and evaluation settings.

用于研究LLM/VLM隐私风险的多语言、多模态PII数据集和提示词

Lossless abliteration of Qwen3.6-27B with NVFP4 hardware quantization for DGX Spark / Blackwell. BF16 (51 GB) + NVFP4 (26 GB) deployment guide, docker-compose, and QuickStart.

Qwen3.6-27B无损消融，NVFP4量化及Docker部署指南

Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

企业级AI网关，支持自适应负载均衡、护栏和1000+模型

Never give AI companies your secrets! A local LLM-based privacy filter for LLM users. Seamless integration with your existing AI tools as a Python library / OpenAI SDK replacement / API Gatetway / Web Server.

基于本地LLM的隐私过滤器，在发送给AI提供商前脱敏秘密信息

Hundreds of models & providers. One command to find what runs on your hardware.

通过一条命令，在数百种模型和提供商中找出适合你硬件的LLM

Fara-7B: An Efficient Agentic Model for Computer Use

Fara-7B是一个高效的代理模型，用于计算机操作任务

Run LLMs with MLX

使用MLX框架在Apple Silicon上运行大语言模型

SGLang is a high-performance serving framework for large language models and multimodal models.

面向大语言模型和多模态模型的高性能服务框架

Local 4B codebase explorer agent distilled from Qwen3-Coder-Next.

从Qwen3-Coder-Next蒸馏的本地4B代码库探索代理

LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI.

支持多种大语言模型的统一API管理与密钥分发系统

Lightweight distributed LLM gateway w/ web UI for model mgmt & routing. Supports vibe programming, prompt opt., & optimized OpenAI API/Anthropic calls

轻量级分布式LLM网关，支持模型管理、路由和优化的API调用

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

支持100多种LLM API的Python SDK和代理服务器，提供成本跟踪、护栏和负载均衡

AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

集成智能聊天、自主代理和300+助手的AI生产力工作室

LLM驱动的 A/H/美股智能分析：多数据源行情 + 实时新闻 + LLM决策仪表盘 + 多渠道推送，零成本定时运行，纯白嫖. LLM-powered stock analysis system for A/H/US markets.

基于LLM的A/H/美股智能分析系统，集成实时新闻、多数据源行情和推送通知

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

使用KoboldAI界面轻松运行GGUF模型，单文件零安装。