#Large Language Models

vllm-project

vllm

★ 91,844

A high-throughput and memory-efficient inference and serving engine for LLMs.

modelcontextprotocol

servers

★ 90,323

Collection of reference MCP server implementations maintained by the steering group, meant as educational examples for developers building their own MCP servers.

OpenHands

OpenHands

★ 88,015

OpenHands is a self-hosted control center for coding agents, running Claude Code, Codex, or any ACP-compatible agent across local, remote, and cloud backends.

bytedance

deer-flow

★ 82,492

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

lobehub

lobehub

★ 82,468

LobeHub acts as a Chief Agent Operator that organizes your AI agents into round-the-clock operations, handling hiring, scheduling, and reporting while you stay in charge.

rtk-ai

rtk

★ 80,502

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies.

opendatalab

MinerU

★ 79,979

MinerU converts PDFs, Office documents, and images into LLM-ready Markdown or JSON, using a VLM+OCR dual engine that covers 109 languages, formulas, and complex layouts.

shareAI-lab

learn-claude-code

★ 76,864

Hands-on tutorial that builds a minimal Claude Code–style agent harness from scratch around Bash, teaching how model and harness combine into a working agent product.

unslothai

unsloth

★ 76,204

Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.

hiyouga

LlamaFactory

★ 74,791

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024). **Scalable resources**: 16-bit full-tuning, freeze-tuning, LoRA and 2/3/4/5/6/8-bit QLoRA via AQLM/AWQ/GPTQ/LLM.int8/HQQ/EETQ.

666ghj

MiroFish

★ 73,588

MiroFish is a swarm-intelligence engine that builds a parallel digital world from seed materials, letting thousands of interacting agents simulate future trajectories.

ruvnet

ruflo

★ 72,427

Ruflo is an agent meta-harness for Claude Code and Codex, adding 100+ specialized agents, coordinated swarms, self-learning memory, and federation across machines.

headroomlabs-ai

headroom

★ 72,304

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

santifer

career-ops

★ 71,584

career-ops turns AI coding CLIs such as Claude Code into a job-search command center, scanning job portals, scoring listings on an A-F rubric, and tailoring CVs.

openinterpreter

openinterpreter

★ 68,320

Open Interpreter is a terminal coding agent optimized for low-cost open models like Kimi K3, reimplemented in Rust with a Codex-like interface and switchable harnesses.

Mintplex-Labs

anything-llm

★ 66,065

Local-first, all-in-one AI desktop app for chatting with your documents and running AI agents, with multi-user support and no setup friction.

mem0ai

mem0

★ 65,344

Mem0 stores and retrieves user, session, and agent memories so AI applications can carry preferences and context across conversations.

ZhuLinsen

daily_stock_analysis

★ 65,110

LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost-free scheduled runs.

virattt

ai-hedge-fund

★ 63,383

Educational proof of concept in which a team of AI agents modeled on investors like Ben Graham and Bill Ackman makes trading decisions; not intended for real trading.

usestrix

strix

★ 62,604

Autonomous AI penetration-testing agents that run your code, find vulnerabilities, and verify them with real proofs of concept, plugging into CI/CD pipelines.