Ranked by Attention Score: stars gained over the last 180 complete days
1–100 of 147 by Attention Score · May 8, 2026 – Nov 3, 2026 (UTC)
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
AirLLM 2.8T LLM inference with single 4GB GPU
A high-throughput and memory-efficient inference and serving engine for LLMs
🧠 Train a 64M-parameter LLM from scratch in just 2h!
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
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.
RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
SGLang is a high-performance serving framework for large language models and multimodal models.
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
A fast, helpful, and open-source document parser
Convert PDF to markdown + JSON quickly with high accuracy
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
The LLM Evaluation Framework
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Next Generation Agentic Proxy for AI Agents and MCP servers
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.
TranslatedProduction-grade platform for building agentic IM bots - Agent, knowledge base orchestration, plugin system / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信 (Qiye Weixin, "Enterprise WeChat"), 企微智能机器人 (Qiwei Zhineng Jiqiren, "Enterprise WeChat smart bot"), 公众号 (Gongzhonghao, "official account")) / 飞书 (Feishu, "flying book") / 钉钉 (Dingding, "nail nail") / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Kimi, openclaw / hermes agent, deerflow
Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.
Air-gapped, privacy-focused, open-source NotebookLM alternative. AI agent that researches, transforms, and edits your documents. Join our Discord: https://discord.gg/ejRNvftDp9
A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
Toolkit for linearizing PDFs for LLM datasets/training
The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.
OCR model that handles complex tables, forms, handwriting with full layout.
Structured Outputs
the LLM vulnerability scanner
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
A curated collection of fun and creative examples generated with Nano Banana & Nano Banana Pro🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the community's development of image generation and unified models(click to website to see our blog)
Open-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company.
The Developer Tool for Visual Engineers • An Open-Source AI-First Design tool • Visually build, style, and edit your code with AI • World's best, top-most agent recommended #1 Developer tool for Designers and Visual Engineers to design with Real Code.
LangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot.
Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/
Train transformer language models with reinforcement learning.
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
🤖 AI Gateway | AI Native API Gateway
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
🦍 The API and AI Gateway
TranslatedLangchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain
TranslatedThe official repo of Qwen chat & pretrained large language model proposed by Alibaba Cloud.
Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.
Access large language models from the command-line
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
Go ahead and axolotl questions
Universal LLM Deployment Engine with ML Compilation
BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level System Management, Observability and more.
The Cloud-Native API Gateway and AI Gateway
TranslatedLangGPT: Empowering everyone to become a prompt expert! 🚀 📌 Proposer of Structured Prompt 📌 Initiator of Meta-Prompt 📌 The most popular paradigm for putting prompts into practice | Language of GPT The pioneering framework for structured & meta-prompt design 10,000+ ⭐ | Battle-tested by thousands of users worldwide Created by 云中江树 (Yunzhong Jiangshu, "river and trees amid the clouds")
Manages Unified Access to Generative AI Services built on Envoy Gateway
All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.
State-of-the-Art Embeddings, Retrieval, and Reranking
An open-source RAG-based tool for chatting with your documents.
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
OpenUI let's you describe UI using your imagination, then see it rendered live.
Evidently is an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.
TranslatedMedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. Training medical large models, implementing incremental pre-training (PT), supervised fine-tuning (SFT), RLHF, DPO, ORPO, and GRPO.
Use your Neovim like using Cursor AI IDE!
Build Conversational AI in minutes ⚡️
✨ AI Coding, Vim Style
TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Official JavaScript / TypeScript library for the OpenAI API
The fastest PDF library for Python and Rust. Text extraction, image extraction, markdown conversion, PDF creation & editing. 0.8ms mean, 5× faster than industry leaders, 100% pass rate on 3,830 PDFs. MIT/Apache-2.0.
The repository host gives no description.
The open source codebase powering HuggingChat
Train your AI self, amplify you, bridge the world
The Cloud Native AI Platform
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
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 RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
TranslatedConcurrently chat with ChatGPT, Bing Chat, Bard, Alpaca, Vicuna, Claude, ChatGLM, MOSS, 讯飞星火 (Xunfei Xinghuo, "iFlytek Spark"), 文心一言 (Wenxin Yiyan, "literary mind, one word") and more, discover the best answers
An open-source, tool-augmented conversational language model from Fudan University
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic system, self-hosted dashboard and advanced analytics with timeline and execution graph view
OpenAI, GPT 6.1, GPT-Image-2, Whisper API clients for Go. Zero-dependency.
Unified framework for building enterprise RAG pipelines with small, specialized models
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.
Code and documentation to train Stanford's Alpaca models, and generate the data.
Low-code framework for building custom LLMs, neural networks, and other AI models
Official inference library for Mistral models
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
TranslatedChatGLM-6B: An Open Bilingual Dialogue Language Model
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, DeepSpeed, Axolotl, etc.