tokenizers

Warp is an agentic development environment, born out of the terminal.

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

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

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.

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

Coding Agent Harness

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..

Spin is the open source developer tool for building and running serverless applications powered by WebAssembly.

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.

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

Inference at the speed of light.

Instant, controllable, local pre-trained AI models in Rust

✨ Agentic chat experience in your terminal. Build applications using natural language.

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

A high-performance inference engine for AI models

A Modern Embedded SQL Database written in Rust

rvLLM: High-performance LLM inference in Rust. Drop-in vLLM replacement.

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

The open source Unity Dev Agent

Pure Rust Inference Engine

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

Anything — 파일을 찾지 말고, 내용을 찾으세요. HWPX · PDF · Office 수천 건의 본문을 1초 만에. 100% 로컬 · 완전 오프라인 · AI Q&A 옵션 (Tauri · React · Rust) | Local content search for Korean PCs — HWP-first, fully offline

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.

A local control plane for AI agents — see what they do, approve what matters, keep secrets out. Rust + Tauri + Chrome MV3.

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

Minne, a read-it-later & personal knowledge management solution

Democratizing large model inference and training on any device.

Build apps powered by on-device AI

Universal LLM API client — 142+ providers, 11 native language bindings, powered by Rust core

A query-system-based static site generator

Pie: Programmable LLM Serving

AI Agent Memory

gproxy is a Rust-based multi-channel LLM proxy that exposes OpenAI / Claude / Gemini-style APIs through a unified gateway, with a built-in admin console, user/key management, and request/usage auditing.

The security agent that fights back. Watches your Linux server from inside, detects threats with kernel-level eBPF, and stops them with on-device AI. Open-source, self-hosted, dry-run by default. Apache-2.0.

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.

A malleable application framework

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

Distribute and run transformer encoders with a single file.

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