2,394 dependents
| Package | Description | Downloads/month |
|---|---|---|
| MTEB: Massive Text Embedding Benchmark | 2.7M | |
| Open WebUI | 1.3M | |
| Minimal keyword extraction with BERT | 699K | |
| llama-index embeddings huggingface integration | 523K | |
| Retrieval and Retrieval-augmented LLMs | 425K | |
| Leveraging BERT and c-TF-IDF to create easily interpretable topics. | 381K | |
| Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls) | 270K | |
| Efficient few-shot learning with Sentence Transformers | 214K | |
| This is an open-source version of the representation engineering framework for s... | 167K | |
| Late Interaction Models Training & Retrieval | 71K | |
| Your AI second brain. Self-hostable. Get answers from the web or your docs. Buil... | 61K | |
| Semantic memory layer for AI applications. REST API + MCP transport + knowledge ... | 54K | |
| Easily use and train state of the art late-interaction retrieval methods (ColBER... | 50K | |
| Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns ag... | 39K | |
| A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your ... | 39K | |
| 🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents. | 39K | |
| The Superlinked vector computing library | 37K | |
| 🤗 AutoTrain Advanced | 34K | |
| 一个为多人交互场景设计的 Python LLM 编排框架。构建具有真实情感表达能力、能提供帮助与情绪价值的核心引擎。 | 33K | |
| Embedding Atlas is a tool that provides interactive visualizations for large emb... | 28K | |
| CLI-first semantic code search with MCP integration. Modern, fast, and intellige... | 25K | |
| A Python library for parsing and solving OPL-like mathematical programming model... | 25K | |
| A package for detail image caption evaluation. | 19K | |
| Colony intelligence sidecar — harness-agnostic cognition server | 19K | |
| World's first local-only AI memory to break 74% retrieval and 60% zero-LLM on Lo... | 18K | |
| The context development platform. Store, enrich, and retrieve structured knowled... | 18K | |
| One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio T... | 16K | |
| Local Deep Research achieves ~95% on SimpleQA benchmark (tested with Qwen 3.6). ... | 15K | |
| General-purpose open-source RAG engine with multi-LLM, hybrid retrieval, GraphRA... | 13K | |
| 轻松玩转LLM兼容openai&langchain，支持文心一言、讯飞星火、腾讯混元、智谱ChatGLM等 | 13K | |
| Repository for JAAT: efficient and accurate analysis of job ads for task matchin... | 12K | |
| Find informative examples to efficiently (human)-evaluate NLG models. | 12K | |
| Queryable concept map of a codebase for LLM coding agents | 12K | |
| Personal knowledge base CLI - aggregate content from multiple sources | 11K | |
| Slash LLM costs with intelligent context compression, smart routing, and cost tr... | 11K | |
| Python SDK for Galileo's NLP and CV Studio. | 11K | |
| llama-index finetuning | 11K | |
| Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall th... | 11K | |
| Un chatbot pour les ludothèques | 11K | |
| PixlStash is a Python-based image management, tagging and editing web app levera... | 10K | |
| Super-Brain: Your codebase's working memory. Local graph + vector intelligence f... | 10K | |
| AI Framework for fast integration of Private Data and LLM, Agent Ochestration Pl... | 10K | |
| Optimum Habana is the interface between the Hugging Face Transformers and Diffus... | 10K | |
| Persistent memory for AI agents — local, portable, zero config. Works with Curso... | 10K | |
| OpenCompass is an LLM evaluation platform, supporting a wide range of models (LL... | 10K | |
| Synthetic Dialog Generation and Analysis with LLMs | 10K | |
| A unified python SDK supports OceanBase or OceanBase seekdb, more efficient and ... | 9K | |
| Build and Search a knowledge base for your projects—bringing together code, PDFs... | 9K | |
| Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns ag... | 9K | |
| OpenDsStar is an open-source implementation of the DS-Star agent that replaces f... | 9K |
