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

3,601–3,624 of 4,156

tianjiangqiji

nova-image-studio

★ 417

自托管的 AI 视频/图像生成工作台 · 自定义模型 · 多模式 · PWA · 实时任务支持Agent模式，UI设计模式，工作台模式，无限画布，反推提示词，提示词广场，GIF生成。前后端任务机制轻量后端；三端兼容 UI：桌面端、平板端、移动端自适应布局

TypeScript

unitagain

WenShape

★ 417

WenShape文枢(原NOVIX写作):深度上下文感知的智能体小说创作系统/A Deep Context-Aware Agent-Based Novel Creation System

Python

vivekchand

clawmetry

★ 417

See your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons.

Python

webcoyote

sandvault

★ 417

Run AI agents isolated in a macOS user account and sandbox-exec. Configured to run Claude Code, OpenAI Codex, Cursor Agent, Google Gemini.

Shell

GizClaw

flowcraft

★ 416

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.

lobehub

lobe-cli-toolbox

★ 416

🪀 Lobe CLI Toolbox - AI CLI Toolbox, enhancing git commit and i18n workflow efficiency

TypeScript

asdecided

WayfinderRouter

★ 415

Simple CLI tool for deterministic routing of queries between local and hosted LLM models

Rust

gbasin

agentboard

★ 415

Web GUI for tmux optimized for AI agent TUIs, with support for iOS safari and mac w/ keyboard shortcuts

TypeScript

smithersai

smithers

★ 415

Agent workflows with full observability and time travel: watch every step live, rewind, fork, replay any run. Claude Code, Codex, Gemini, any model or harness. The same workflow runs across Claude Code, Codex, Pi, AI SDK models, and remote sandboxes.

JavaScript

Yacey

agnes-ai-generation-skill

★ 415

Agent Skill for Agnes AI text, image, and video generation APIs.

Python

agent-sh

agnix

★ 414

The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plugin for all major IDEs included, with autofixes.

Rust

aiblueprinthq

ai-blueprint

★ 413

A file-backed, spec-driven AI coding workflow framework for building real software while staying in control.

TypeScript

eleiton

ollama-intel-arc

★ 413

Make use of Intel Arc Series GPU to Run Ollama, StableDiffusion, Whisper and Open WebUI, for image generation, speech recognition and interaction with Large Language Models (LLM).

Dockerfile

erpipe-org

mcp-odoo

★ 413

Odoo MCP for AI agents — gated writes, multi-instance. Hosted product: https://erpipe.com

Python

feder-cr

resume_render_from_job_description

★ 413

Resume_Builder_AIHawk is a powerful Python tool that allows you to automatically customize your resume based on a job URL, ensuring it perfectly aligns with the job requirements and skills. With an interactive command-line interface, this tool makes it easy to navigate through options and select from various pre-defined styles

Python

gotalab

skillport

★ 413

Bring Agent Skills to Any AI Agent and Coding Agent — via CLI or MCP. Manage once, serve anywhere.

Python

bybren-llc

safe-agentic-workflow

★ 412

SAW — SAFe Agentic Workflow AI Agent Harness for Multi-Agent Team Workflows Built on SAFe methodology (Scaled Agile Framework), adapted for AI agent teams (Now With AI-DLC!) Works for any team with repeatable processes: Software, Marketing, Research, Legal, Operations.

Shell

traceloop

openllmetry-js

★ 412

Sister project to OpenLLMetry, but in Typescript. Open-source observability for your LLM application, based on OpenTelemetry

TypeScript

TheDesignFounder

DreamLayer-Eval

★ 411

DreamLayer Eval: open-source benchmarking for image and video diffusion models. Automate prompts, seeds, and metrics for reproducible results. A research project from DreamLayer AI (dreamlayer.io).

Python