Open-source LLM apps and frameworks

LHRLAB

Graph-R1

★ 601

[ICML 2026] Official resources of "Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning".

MMMU-Benchmark

MMMU

★ 601

This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"

sleekdotdesign

agent-skills

★ 601

Official Sleek agent skill for creating and editing mobile app designs through the REST API. Includes account setup, screenshots and screen HTML.

smallnest

goclaw

★ 601

An open-source AI assistant framework like openclaw

hewliyang

office-agents

★ 600

Agent plugins for Microsoft Office but BYOK for any model and provider

lucienhuangfu

eLLM

★ 600

eLLM: Run Long-Horizon Inference Faster on CPUs Than on GPUs

MIV-XJTU

JanusVLN

★ 600

[ICLR2026] Official implementation for "JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation"

0xjeffro

astroclaw

★ 599

Cloud-native agent-as-a-service framework with one-click IaC deployment.

doclang-project

doclang

★ 599

DocLang spec and reference toolkit

Karovia

fullstack-ai-agent-roadmap

★ 599

From zero to full-stack AI Agent engineer: 110 detailed tutorials, 580,000 words, 400+ curated GitHub projects, Obsidian-friendly, in Chinese.

Mixar-AI

mixar-app

★ 599

AI-powered 3D suite built on Blender, with an integrated agent, moodboard, generation tools and layer-based painting

strongdm

leash

★ 599

Leash by StrongDM - take your AI agents for a walk

vladikk

modularity

★ 599

Claude Code plugin for designing modular systems from functional requirements and reviewing existing codebases for modularity problems with actionable improvement recommendations. Based on the Balanced Coupling model.

ZyhSechub

chinese-thesis-workbench-skill

★ 599

An undergraduate thesis-writing skill that engineers your project's source code, database, screenshots and references into a traceable, continuable, reviewable thesis, following your school's template and sample style.

CapeAga

bai-it

★ 598

掰it — Chrome extension for English reading comprehension. Break long sentences into chunks, learn vocabulary in context.

elmohq

elmo

★ 598

Open-source Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) platform. Track how ChatGPT, Claude, Perplexity, Gemini, Copilot, Grok, and Google AI Overviews mention and cite your brand in AI search. MIT-licensed, self-hostable, every metric auditable in code.

hatayama

unity-cli-loop

★ 598

Let AI Drive Unity, from Editor to Play Mode.

Maneek21

Deft

★ 598

Self-hostable AGPL workspace where humans and AI agents share chat, tasks, knowledge, approvals, and MCP context.

f

agentlytics

★ 597

Comprehensive analytics dashboard for AI coding agents — Cursor, Windsurf, Claude Code, VS Code Copilot, Zed, Antigravity, OpenCode, Command Code

morpheuslord

GPT_Vuln-analyzer

★ 597

Uses ChatGPT API, Bard API, and Llama2, Python-Nmap, DNS Recon, PCAP and JWT recon modules and uses the GPT3 model to create vulnerability reports based on Nmap scan data, and DNS scan information. It can also perform subdomain enumeration to a great extent

normal-computing

fuji-web

★ 597

Fuji is an AI agent that lives in your browser's sidepanel. You can now get tasks done online with a single command!

skygazer42

MimirQ

★ 597

A Chinese-first enterprise RAG knowledge base with controllable parsing, governance, chunking, hybrid retrieval, reranking, citations, knowledge graphs, evaluation and Dify integration.

FradSer

dotclaude

★ 596

A comprehensive development environment with specialized AI agents for code review, security analysis, and technical leadership.

google

seqio

★ 596

Task-based datasets, preprocessing, and evaluation for sequence models.