LLM apps

Open-source LLM apps and frameworks

This is the broadest group: chat interfaces, SDKs and frameworks, prompt and evaluation tools, and applications built on large language models. Many work with models from several providers, and some can run models on your own hardware.

How to choose

For anything you plan to ship, check three facts first: the licence, because some popular projects restrict commercial use; whether it supports the model provider you already use; and whether it is still maintained. The At a glance box on every project page answers the licence and maintenance questions from GitHub data.

Most-starred projects

2,257–2,280 of 4,627

ipa-lab

hackingBuddyGPT

★ 1,250

Helping Ethical Hackers use LLMs in 50 Lines of Code or less..

Python

nethical6

conversation-steganography

★ 1,250

Use LLMs to hide messages inside normal looking conversations

ChristopherKahler

paul

★ 1,249

Plan-Apply-Unify Loop — Structured AI-assisted development for Claude Code. Quality over speed-for-speed's-sake.

JavaScript

Arize-ai

openinference

★ 1,248

OpenTelemetry Instrumentation for AI Observability

Python

sums001

Windows-Copilot-API

★ 1,248

Reverse engineered Windows Copilot into an OpenAI-compatible API. Access GPT-4 and GPT-5 models through a simple REST interface without API keys or billing.

Python

tintinweb

pi-subagents

★ 1,245

Claude Code like Sub-Agents & Workflow Orchestration for Pi — parallel execution, live widget, fleet view, custom agent types, mid-run steering, claude compatible dynamic workflows and more ...

TypeScript

xllm-go

bypass

★ 1,244

集成了openai-api、coze、deepseek、cursor、windsurf、qodo、blackbox、you、grok、bing 绘画多款AI的聊天逆向接口适配到 OpenAI API 标准接口服务端。

mozilla-ai

any-agent

★ 1,242

A single interface to use and evaluate different agent frameworks

Python

michaelshimeles

skills

★ 1,241

Agent skills and an AGENTS.md workflow template — isolate in worktrees, build to a service layer, prove with evidence, ship with before/after proof and Greptile review loops. For Claude Code, Cursor, and Codex.

Python

Taewan-P

gpt_mobile

★ 1,241

Chat app for Android that supports answers from multiple LLMs at once. Bring your own API key AI client. Supports OpenAI, Anthropic, Google, and Ollama. Designed with Material3 & Compose.

Kotlin

NVlabs

kda

★ 1,239

Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.

chen0416ccc-cpu

codex-windows-fast-patch-skill

★ 1,238

此skills用于指导智能体在 Windows 上恢复 Codex Desktop 升级后失效的本地补丁和能力开关。（Computer Use，插件，破限，codex强制汉化，fast mode，手机远控，会话消失等问题）支持每次使用前自动将skills更新到最新版。/These skills are designed to guide the agent in restoring local patches and feature toggles that have been disabled or invalidated following a Codex Desktop upgrade on Windows. Supports auto-updating translations.

PowerShell

thClaws

★ 1,236

Open-source AI agent harness in native Rust, GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.

Rust

hoangnb24

repository-harness

★ 1,234

Turn any repo into an agent-ready workspace for Claude Code, Codex, Cursor, and other coding agents.

Rust

lobehub

lobe-chat-agents

★ 1,233

🤖 / 🏪 Agent Index - This is the agent index for LobeChat. It accesses index.json from this repository to display a list of available agents for LobeChat to the agent market.

TypeScript

MyoHub

myosuite

★ 1,233

MyoSuite is a collection of environments/tasks to be solved by musculoskeletal models simulated with the MuJoCo physics engine and wrapped in the OpenAI gym API.

Python

gooseworks-ai

goose-skills

★ 1,232

Library of Growth & GTM skills + data APIs for Claude Code, Codex, Cursor to run ads, social, content, lead gen, seo and data scraping

Python

Ataraxy-Labs

opensessions

★ 1,231

tmux sidebar for coding agents — Amp, Claude Code, Codex, OpenCode. Per-thread markers, local HTTP API, live session state.

Rust

modu-ai

moai-adk

★ 1,231

Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Single Go binary, 16 languages, zero deps.

uezo

ChatdollKit

★ 1,230

ChatdollKit enables you to make your 3D model into a chatbot

wanxingai

LightAgent

★ 1,229

LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing, lifecycle hooks, multi-agent collaboration, and workflows.

Python