Stars
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
Data platform for context engineering. Context data platform that stores, observes and learns. Join the community❤️: https://discord.acontext.io
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
ACE LangGraph: ReAct Agent with Adaptive Learning - Integrating ACE framework with LangGraph for self-improving agents
🚀 Efficient implementations of state-of-the-art linear attention models
Causal depthwise conv1d in CUDA, with a PyTorch interface
fanshiqing / grouped_gemm
Forked from tgale96/grouped_gemmPyTorch bindings for CUTLASS grouped GEMM.
CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning
Optimize prompts, code, and more with AI-powered Reflective Text Evolution
One second to read GitHub code with VS Code.
Agent0 Series: Self-Evolving Agents from Zero Data
OpenCE (Open Context Engineering): A community toolkit to implement, evaluate, and combine LLM context strategies (RAG, ACE, Compression). Evolved from the `ACE-open` reproduction.
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
FlashInfer: Kernel Library for LLM Serving
Defeating the Training-Inference Mismatch via FP16
The code for paper: Decoupled Planning and Execution: A Hierarchical Reasoning Framework for Deep Search
🛠️ DeepAgent: A General Reasoning Agent with Scalable Toolsets
The absolute trainer to light up AI agents.
A simple yet powerful agent framework that delivers with open-source models
slime is an LLM post-training framework for RL Scaling.
MrlX: A Multi-Agent Reinforcement Learning Framework
Bridge Megatron-Core to Hugging Face/Reinforcement Learning
The open source developer platform to build AI agents and models with confidence. Enhance your AI applications with end-to-end tracking, observability, and evaluations, all in one integrated platform.
Kubernetes-native AI serving platform for scalable model serving.