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

3,265–3,288 of 4,152

linguo2625469

workbuddy2api-panel

★ 491

把腾讯WorkBuddy账号变成 OpenAI 兼容 API 的多账号网关，同时自动完成任务中心全部任务，附 Web 管理面板（账号池可视化 / 积分任务 / 配置热更新）。基于 Sliverkiss/workbuddy2api 的增强分支

Littlesheepxy

zhigeng

★ 491

知更 — 本地 AI 的上下文与记忆层。Mac 上用语音输入、情境代回并调度 Codex / Claude Code；iOS 正在成为随身记忆终端和本地 Agent 遥控器。Local-first · BYOK.

TypeScript

MORTEN-BUUR

nordef-matrix-open-control

★ 491

NORDEF Matrix Open Control: model-independent AI safety belt with 0/1/2 decisions, Ed25519 root gate, replay protection, evidence chain, and incident-pattern eval bank

Python

quchangle1

LLM-Tool-Survey

★ 491

This is the repository for the Tool Learning survey.

statewright

★ 491

State machine guardrails for AI agents

Rust

TeleAI-UAGI

telemem

★ 491

TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.

Python

operand

agency

★ 490

A fast and minimal framework for building agentic systems

Python

paulrobello

parllama

★ 490

TUI for Ollama and other LLM providers

Python

livecontext-ai

livecontext-ce

★ 489

The AI automation platform, self-hosted. Describe the job in chat and LiveContext builds it: readable workflows, scoped AI agents, and small apps your team uses. Chat, Workflow, Agent and App on one canvas.

Java

Bytedesk

bytedesk

★ 488

Open Souce IM with AI powered live-chat, email, ticket support, omni-channel customer service，alternative to slack + zendesk/intercom/hubspot/ada/decagon/sierra

Java

mxyhi

ok-skills

★ 488

Curated AI coding agent skills and AGENTS.md playbooks for Codex, Claude Code, Cursor, OpenClaw, and other SKILL.md-compatible tools.

HTML

ServiceNow

ServiceNowDocs

★ 488

ServiceNow AI Platform documentation for LLM consumption.

AIScientists-Dev

Flowtrace

★ 487

Run a task with AI as a flow of steps you keep, reuse, and refine, not a one-off chat.

TypeScript

Annyfee

agent-craft

★ 487

AI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体

Python

clawplays

ospec

★ 487

Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable specs and evidence in your repo. Works with Claude Code, Codex, Gemini, OpenCode, and plain CLI.

JavaScript

KinetiNode

claude-fable-5-system-prompt-clean

★ 487

the optimized, token-efficient version of the leaked Claude Fable 5 / Mythos 5 system prompt. Re-engineered into clean Markdown for universal execution on Gemini 3.1 Pro, ChatGPT 5.6, and advanced LLM agents.

mehmetkahya0

AI-Catalog

★ 487

Huge AI models catalog. A curated list of AI tools, platforms, and resources across various domains.

Shell

Orkas-AI

Orkas-VideoStudio

★ 487

Turn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file.

TypeScript

Vasco0x4

AIDA

★ 487

Turn any LLM into an autonomous pentester. You define the scope, the agent does the work, you review the findings.

JavaScript

yi1108

printfilm

★ 487

PRINTFILM：AI 科普视频与漫剧创作平台

Python

aws-samples

bedrock-engineer

★ 486

Universal AI Agent using Amazon Bedrock, capable of customize to create/edit files, execute commands, search the web, use knowledge base, use multi-agents, generative images and more.

TypeScript