AI 频道
大模型应用

开源大模型应用与框架

这是范围最广的一组:聊天界面、SDK 和框架、提示词与评测工具,以及各种基于大语言模型的应用。很多项目可以接入多家服务商的模型,有些还能在你自己的硬件上运行模型。

怎么选

打算用在产品里的话,先确认三件事:许可证——有些热门项目限制商用;是否支持你正在用的模型服务商;以及它是否还在维护。每个项目页上的「秒懂」卡片会根据 GitHub 数据回答许可证和维护这两个问题。

Star 最多的项目

第 697–720 个,共 864 个
MLGroupJLU

LLM-eval-survey

1,611

The official GitHub page for the survey paper "A Survey on Evaluation of Large Language Models".

koreainvestment

open-trading-api

1,606

Korea Investment & Securities Open API Github

Python
shiwenwen

hope-agent

1,603

🦭 会记忆、能持续推进目标、会动态编排多 Agent 的跨端桌面 AI 助手,也可服务化常驻 NAS / 云端 | A cross-device desktop AI agent with memory, autonomous goals, dynamic workflows, and headless deployment

Rust
1,596

Chat language model that can use tools and interpret the results

Python
Kaelio

ktx

1,593

ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, or other AI agents to query analytical databases accurately and with full context of your company

TypeScript
OpenOSINT

OpenOSINT

1,590

AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 19 tools. Works with Claude, GPT-4, or local models. For authorized security research only.

Python
mex-memory

mex

1,585

Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.

TypeScript
AIScientists-Dev

academic-humanizer

1,580

Strip AI-writing tells from papers and grant proposals (NSF/NIH), while keeping scholarly voice and tying claims to evidence. A skill for Claude Code, Codex, and MorphMind.

BAI-LAB

MemoryOS

1,579

[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.

Python
1,577

Claude reads its own source code — 17-chapter architectural deep-dive into Claude Code v2.1.88. EN/ZH bilingual.

1,577

Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

Python
waybarrios

vllm-mlx

1,575

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

Python
MLSysOps

MLE-agent

1,572

🤖 MLE-Agent: Your intelligent companion for seamless AI engineering and research. 🔍 Integrate with arxiv and paper with code to provide better code/research plans 🧰 OpenAI, Anthropic, Gemini, Ollama, etc supported. :fireworks: Code RAG

Python
modelscope

AgentEvolver

1,570

AgentEvolver: Towards Efficient Self-Evolving Agent System

Python
google

mantis

1,565

A modular, stack-agnostic toolkit of security review skills for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.

Python
amitshekhariitbhu

llm-internals

1,555

Learn LLM internals step by step - from tokenization to attention to inference optimization.

1,554

Nvidia GPU exporter for prometheus using nvidia-smi binary OR using NVML

Go
allenai

dolma

1,545

Data and tools for generating and inspecting OLMo pre-training data.

Python
GitHamza0206

simba

1,541

OpenSource Production ready Customer service with built in Evals and monitoring

TypeScript
1,530

An official Qdrant Model Context Protocol (MCP) server implementation

Python
WecoAI

aideml

1,528

AIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.

Python
fim-ai

fim-one

1,513

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

Python
ggml-org

llama.vscode

1,509

VS Code extension for LLM-assisted code/text completion

TypeScript
vanloctech

youwee

1,500

A beautiful, cross-platform downloader for YouTube, TikTok, Instagram, and 1800+ sites (yt-dlp GUI) with AI video summaries and post-processing

TypeScript