Run transformers directly on Apple's Neural Engine in Swift bypass coreml entirely
☆176Sep 12, 2026Updated 2 months ago
Alternatives and similar repositories for Espresso
Users that are interested in Espresso are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers☆30May 19, 2026Updated 6 months ago
- Local AI runtime for training & running small LLMs directly on Apple Neural Engine (ANE). No CoreML. No Metal. Offline, on-device fine-tu…☆134Aug 23, 2026Updated 2 months ago
- 🚀 LLM inference Engine in Swift/Metal, Load GGUF and safe tensors modes, no conversion, no cpp, pure swift☆51May 19, 2026Updated 6 months ago
- Deterministic graph runtime for agent workflows in Swift. Same input, same output, every time — golden-testable, checkpoint-resumable, an…☆26May 17, 2026Updated 6 months ago
- Research MIL-to-HWX compiler for the M4 Apple Neural Engine☆19Sep 3, 2026Updated 2 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆30Oct 31, 2026Updated 2 weeks ago
- ☆17Apr 17, 2026Updated 7 months ago
- Swift SDK for running chat, vision and speech models on iPhone and Mac with Apple's Core AI. Model download and caching, FoundationModels…☆126Updated this week
- ☆14Jun 17, 2026Updated 5 months ago
- An on device Agent Runtime☆23May 13, 2026Updated 6 months ago
- Debug On Device AI, Capture Hardware state and AI Output☆19Jun 16, 2026Updated 5 months ago
- Apple Neural Engine (ANE) LLM inference engine — reverse-engineered private APIs, Metal GPU shaders, hybrid ANE+GPU+CPU on Apple Silicon.…☆34Oct 2, 2026Updated last month
- MiniMax H3 text-to-video on the Apple Neural Engine — every DiT block as a raw MIL graph on a base 24GB M4☆14Aug 12, 2026Updated 3 months ago
- Use MetalPerformanceShadersGraph to measure the Apple Neural Engine compute capacity of Apple SoC☆14Nov 12, 2026Updated last week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆86Mar 3, 2026Updated 8 months ago
- Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API.…☆814Updated this week
- Type-safe tools, on-device inference, multi-agent workflows, memory, and guardrails, in one Swift-native runtime☆588Updated this week
- Run Time Series Foundation Models on Apple Silicon☆36Feb 27, 2026Updated 8 months ago
- LLM inference on Apple Neural Engine (ANE)☆147Mar 4, 2026Updated 8 months ago
- ☆20Apr 12, 2026Updated 7 months ago
- Run ops on Apple ANE in NPU register with pure python on M1 Asahi Linux. No Espresso, No CoreML, no metal, no .mlmodels file, no .hwx fil…☆22Oct 8, 2026Updated last month
- Reverse engineered the Apple Neural Engine, with working Python and Objective C samples☆41Feb 1, 2026Updated 9 months ago
- Tool for exporting Apple Neural Engine-accelerated versions of transformers models on HuggingFace Hub.☆18Jun 25, 2026Updated 4 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Pure Swift CLI to sync, search, and classify your X/Twitter bookmarks locally. Uses Safari session cookies, SQLite FTS5 for full-text s…☆14Apr 8, 2026Updated 7 months ago
- ☆229Mar 24, 2026Updated 7 months ago
- Artificial Neural Engine Machine Learning Library☆1,709Oct 31, 2026Updated 2 weeks ago
- Playwright for Swift is a browser automation library to control Chromium, Firefox and WebKit with a single API.☆95May 8, 2026Updated 6 months ago
- ☆47Nov 12, 2026Updated last week
- 🦑 Unified Swift SDK for LLM inference across local and cloud providers☆120Jun 13, 2026Updated 5 months ago
- CLI to demonstrate running a large language model (LLM) on Apple Neural Engine.☆131Dec 27, 2024Updated last year
- DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous acce…☆62Apr 18, 2026Updated 7 months ago
- PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal ac…☆334Nov 2, 2026Updated 2 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A Swift package for typed decisions from language models (probabilities, choices, and scores), with support for local MLX models and the …☆63Updated this week
- Tool for visual profiling Core ML models, compatible with both package and compiled versions, including reasons for unsupported operation…☆39Jun 18, 2024Updated 2 years ago
- Zoni is a comprehensive, production-ready RAG framework built with Swift 6.0 🦝☆45Jun 2, 2026Updated 5 months ago
- Downloadable models and conversion recipes for Apple's Core AI on iPhone and Mac. Chat, vision, speech and generative models with per-mod…☆466Updated this week
- Build your own NSVisualEffectView☆15Oct 4, 2020Updated 6 years ago
- A minimal, un-opinionated agent library for Swift providing conversation and tool calling☆17May 20, 2026Updated 5 months ago
- Flash-MoE sidecar slot-bank runtime for large GGUF MoE models on Apple Silicon — llama.cpp fork☆135Oct 7, 2026Updated last month
Are these results useful?