Lists (3)
Stars
Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).
Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding
Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme
AgentEvolver: Towards Efficient Self-Evolving Agent System
HunyuanVideo-1.5: A leading lightweight video generation model
A general memory system for agents, powered by deep-research
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
Implementation for OAgents: An Empirical Study of Building Effective Agents
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
A Datacenter Scale Distributed Inference Serving Framework
A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.
[ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring
LlamaIndex is the leading framework for building LLM-powered agents over your data.
An open-source, self-hosted note-taking service. Your thoughts, your data, your control — no tracking, no ads, no subscription fees.
verl: Volcano Engine Reinforcement Learning for LLMs
Train your AI self, amplify you, bridge the world
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL