KI-Kanal
LLM-Apps

Open-Source-LLM-Apps und -Frameworks

Das ist die breiteste Gruppe: Chat-Oberflächen, SDKs und Frameworks, Werkzeuge für Prompts und Evaluierung sowie Anwendungen, die auf großen Sprachmodellen aufbauen. Viele funktionieren mit Modellen verschiedener Anbieter, manche können Modelle auf Ihrer eigenen Hardware ausführen.

Worauf Sie achten sollten

Wenn Sie etwas produktiv einsetzen wollen, prüfen Sie zuerst drei Fakten: die Lizenz, denn manche beliebten Projekte schränken die kommerzielle Nutzung ein; ob der Modellanbieter unterstützt wird, den Sie bereits nutzen; und ob das Projekt noch gepflegt wird. Der Kasten „Auf einen Blick“ auf jeder Projektseite beantwortet die Fragen zu Lizenz und Pflege anhand von GitHub-Daten.

Projekte mit den meisten Sternen

817–840 von 871
EvolvingLMMs-Lab

LLaVA-OneVision-2

1.202

Fully Open Framework for Democratized Multimodal Training

Python
brainlid

langchain

1.201

Elixir implementation of a LangChain style framework that lets Elixir projects integrate with and leverage LLMs.

Elixir
ngxson

wllama

1.201

WebAssembly binding for llama.cpp - Enabling on-browser LLM inference

TypeScript
superlinear-ai

raglite

1.200

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

Python
cvs-health

uqlm

1.199

[JMLR 2026] "UQLM: A Python Package for Uncertainty Quantification in Large Language Models"

Python
FranciscoMoretti

chat-js

1.199

Production-ready AI chat. Start here and make it your own. Formerly Sparka AI

TypeScript
openvinotoolkit

nncf

1.199

Neural Network Compression Framework for enhanced OpenVINO™ inference

Python
RhythmicWave

NovelForge

1.196

AI辅助长篇小说创作,卡片式创作,支持基于 JSON Schema的结构化 AI 生成与上下文引用,可扩展性强。

Python
polterguy

magic

1.193

Instant SECURE Full Stack Apps and AI Agents

C#
NVIDIA-NeMo

Gym

1.189

Evaluate and improve models and agents using environments

Python
madox2

vim-ai

1.188

AI-powered code assistant for Vim. OpenAI and ChatGPT plugin for Vim and Neovim.

Python
1.181

Agentic SOC Platform: A powerful, flexible, open-source, and agent-centric automated security operations platform (AI SOC)

Python
1.181

A practical lab for building, testing, and evaluating apps with Apple's Foundation Models framework.

Swift
sgl-project

SpecForge

1.176

Train speculative decoding models effortlessly and port them smoothly to SGLang serving.

Python
ENTERPILOT

GoModel

1.157

AI gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, vLLM and more. A LiteLLM alternative with observability, guardrails, streaming, cost tracking, intelligent routing, sticky sessions, failover, real-time logs and usage tracking. Prod ready.

Go
AI-QL

tuui

1.154

A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.

TypeScript
zjunlp

LightMem

1.149

[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation

Python
Rath-Team

OpenRath

1.136

An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.

Python
xuzhougeng

wisp-science

1.136

Open-Source-Workbench für die lokale KI-Desktop-Forschung für wissenschaftliches Rechnen mit Python/R, MCP-Bioinformatik-Tools, SSH/WSL/GPU-Laufzeiten und OpenAI/Anthropic-Modellen.

HTML
codelibs

fess

1.135

Open-source, self-hosted enterprise & site search server built on OpenSearch. Crawls web / file / DB / cloud sources, 20+ languages, REST API, and AI/RAG & semantic search. Apache-2.0.

Java
massgen

MassGen

1.130

🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | Join us on Discord: discord.massgen.ai

Python
NovaSearch-Team

RAG-Retrieval

1.130

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

Python
1.130

Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 15 agents, 33 skills working with /goal, agent-team, & workflow on autopilot loops with 0 need for human gate. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack

JavaScript