hf-hub

A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.

Search infrastructure for AI

Minimalist ML framework for Rust

YC (S26) | AI that knows what you've seen, said, or heard. Records everything you do, say, hear 24/7, local, private, secure

Open-source developer platform to power your entire infra and turn scripts into webhooks, workflows and UIs. Fastest workflow engine (13x vs Airflow). Open-source alternative to Retool and Temporal.

Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Open source Granola AI Alternative

A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 97+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, R, C, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.

Fast, flexible LLM inference

A Datacenter Scale Distributed Inference Serving Framework

Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with more integrations coming..

A blazing fast inference solution for text embeddings models

ML-powered manga translator, written in Rust.

RuVector is a High Performance, Real-Time, Self-Learning Ai, Vector GNN, Memory DB built in Rust.

A portable accelerated SQL query, search, and LLM-inference engine, written in Rust, for data-grounded AI apps and agents.

Drop-in Apache Spark replacement written in Rust, unifying batch processing, stream processing, and compute-intensive AI workloads.

Inference at the speed of light.

Local first semantic and hybrid BM25 grep / search tool for use by AI and humans!

Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.

A Modern Embedded SQL Database written in Rust

Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.

The open source Unity Dev Agent

NextPlaid, ColGREP: Multi-vector search, from database to coding agents.

Models and examples built with Burn

Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing, chat history, tokenization caching, Responses API, embeddings, WASM plugins, MCP, and multi-tenant auth.

Japanese Input Method System for Linux, macOS, Neural Kana-Kanji Conversion Engine

Open coding agent, provider agnositc.

MoFA - Modular Framework for Agents. Modular, Compositional and Programmable.

Build apps powered by on-device AI

Pie: Programmable LLM Serving

A SIP/WebRTC voice agent

Give your agent a proper IDE and OS. The sensorimotor cortex for coding agents (OpenCode + Pi), part of CortexKit: symbol-aware edits, semantic search, code health, fast grep/glob, bash compression, background tasks, PTY.

Autonomous executive assistant with persistent memory and a multi-agent architecture

A machine learning library for Python and Rust, for PyTorch, Tensorflow and SKLearn models

Next Generation Machine Learning, Statistics and Deep Learning in PURE Rust

A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre assembly. Not a wrapper, a ground up storage engine that thinks.

MLX-based experimental inference engine

A fast terminal native app (TUI) and CLI with init wizard for launching local LLMs via llama.cpp with zero overhead

Simple, Composable, High-Performance, Safe and Web3 Friendly AI Agents and LazAI Gateway for Everyone

Local-first AI work memory that compounds: capture decisions, lessons, gotchas in flow, distill into source-backed wiki pages, recall across sessions and any MCP client (Claude Code, Codex, etc...). Plain Markdown you own.

A memory-first AI agent that remembers why decisions were made — not just the last message. Runs local (Ollama), cloud (Claude · OpenAI · Gemini), or decentralized TEE. Graph memory, self-learning skills, multi-model routing, sandboxed tools. MCP · ACP · A2A. One Rust binary.

Open-source streaming SQL engine written in Rust using Apache Arrow and DataFusion. Supports continuous queries, temporal stream joins, tumbling/session windows, and CDC/Kafka connectors. Lightweight, embeddable, and sub-microsecond latency

Uni is a modern, embedded database that combines property graph (OpenCypher), vector search, and columnar storage (Lance) into a single, cohesive engine. It is designed for applications requiring local, fast, and multimodal data access, backed by object storage (S3/GCS) durability.

caro: fast Rust CLI that turns natural‑language tasks into a safe POSIX command. Built for macOS (MLX/Metal) with a built‑in model; supports vLLM/Ollama/LM Studio. JSON‑only output, safety checks, confirmation, multi‑step goals, devcontainer included.

A Blossom/NIP96 server

MCPMate is a progressive MCP management center for organizing servers, clients, profiles, capabilities, and runtime visibility in one local workspace.

为 AI 记忆提供了一种从“容器”到“场”的范式迁移，实现永久记忆。

Local AI image generation CLI — FLUX, SD 1.5, SDXL & Z-Image diffusion models on your GPU