MCP y llamadas a herramientas
astrbotdevs/astrbot
AstrBot is an open-source, all-in-one AI agent chatbot platform and development framework that integrates mainstream instant messaging platforms, large language models, plugins, and agent capabilities for building production-ready conversational AI applications.
★ 38,5K⑂ 2,7KPython
AGPL-3.0Q98
RAG y sistemas de conocimiento
hkuds/lightrag
A lightweight, graph-based retrieval-augmented generation (RAG) framework that uses a dual-layer architecture combining knowledge graphs and vector embeddings to deliver efficient indexing, low-cost incremental updates, and high-quality contextual retrieval.
★ 38,4K⑂ 5,4KPython
MITQ98
Inferencia, implementación y tiempo de ejecución
NVIDIA/Model-Optimizer
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
★ 3,3K⑂ 513Python
Apache-2.0Q86
LLM y modelos fundacionales
PaddlePaddle/PaddleFormers
PaddleFormers is an easy-to-use library of pre-trained large language model zoo based on PaddlePaddle.
★ 13K⑂ 2,2KPython
Apache-2.0Q81
LLM y modelos fundacionales
PaddlePaddle/ERNIE
The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.
★ 7,7K⑂ 1,4KPython
Apache-2.0Q88
LLM y modelos fundacionales
openai/gpt-oss
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
★ 20,3K⑂ 2,1KPython
Apache-2.0Q86
AI multimodal
PaddlePaddle/PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages
★ 88K⑂ 11,2KPython
Apache-2.0Q86
Inferencia, implementación y tiempo de ejecución
PaddlePaddle/FastDeploy
High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle
★ 3,7K⑂ 755Python
Apache-2.0Q98
LLM y modelos fundacionales
zai-org/GLM-5
GLM-5: From Vibe Coding to Agentic Engineering
★ 6,8K⑂ 848—
Apache-2.0Q95
RAG y sistemas de conocimiento
pathwaycom/llm-app
Application templates for RAG, search and AI pipelines using live data sources.
★ 58,9K⑂ 1,5KJupyter Notebook
MITQ90
Inferencia, implementación y tiempo de ejecución
MoonshotAI/checkpoint-engine
Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
★ 982⑂ 100Python
MITQ83
LLM y modelos fundacionales
PaddlePaddle/PaddleNLP
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
★ 13K⑂ 3KPython
Apache-2.0Q95