Lists (1)
Stars
A Deep Thinking RAG Pipeline to Solve Complex Queries
VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
AgentFlow: In-the-Flow Agentic System Optimization
A collaborative note taking, wiki and documentation platform that scales. Built with Django and React.
A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
Get your documents ready for gen AI
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.
Source code for paper "ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance"
Google Research
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
Official implementation for the paper "KG-Infused RAG: Augmenting Corpus-Based RAG with External Knowledge Graphs"
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
This is the code repo for the paper "Learning to Route Queries Across Knowledge Bases for Step-wise Retrieval-Augmented Reasoning".
A Survey of Personalization: From RAG to Agent
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
Source code and demo for memory bank and SiliconFriend
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
No fortress, purely open ground. OpenManus is Coming.
Profile-Based Long-Term Memory for AI Applications. Memobase handles user profiles, memory events, and evolving context — perfect for chatbots, companions, tutors, customer service bots, and all ch…
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
[COLM’25] DeepRetrieval — 🔥 The First Search Agent Trained by On-Policy Reinforcement Learning
🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]
🤗 smolagents: a barebones library for agents that think in code.