abacaj

docling

Get your documents ready for gen AI

aider

aider is AI pair programming in your terminal

agno

Multi-agent framework, runtime and control plane. Built for speed, privacy, and scale.

litellm

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

Qwen3-VL

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

bullmq

BullMQ - Message Queue and Batch processing for NodeJS and Python based on Redis

ART

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

baml

The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible)

ell

A language model programming library.

Liger-Kernel

Efficient Triton Kernels for LLM Training

torchtitan

A PyTorch native platform for training generative AI models

flashinfer

FlashInfer: Kernel Library for LLM Serving

optillm

Optimizing inference proxy for LLMs

Grounded-SAM-2

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Magma

[CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents

Nanoflow

A throughput-oriented high-performance serving framework for LLMs

Spider2

[ICLR 2025 Oral] Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

swe-rl

[NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"

torch-profiling-tutorial

LongCite

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA

gpt-oss-recipes

Collection of scripts and notebooks for OpenAI's latest GPT OSS models

RLAIF-V

[CVPR'25 highlight] RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness

finetune-Qwen2-VL

syncode

Efficient and general syntactical decoding for Large Language Models

vitale

TypeScript notebook for developers

TouchNet

A native-PyTorch library for large scale M-LLM (text/audio) training with tp/cp/dp.

small-doge

Doge Family of Small Language Models

datago

A natively parallel dataloader for Python, written in Rust. Serving data at GB/s speeds, while covering aspect ratio bucketing, crop and resize for image ML workloads.

fewshot

mini-r1-zero