Havuz

audio.cpp, ggml tabanlı ortak bir C++ runtime üzerinden farklı ses modellerinde yerel inference çalıştırmayı sağlayan bir framework’tür.

Neden yükseliyor · 96 günlük yaşına rağmen 3067 yıldızın yanı sıra son 28 günde 272 commit ve 18 farklı yazar görünüyor; bu, README’deki geniş model desteğinin yanında kayda değer bir geliştirme hareketliliğine işaret ediyor. README performans iyileştirmeleri ve yeni model desteği bildiriyor, ancak bu kıyasların bağımsız doğrulaması verilen bilgilerden anlaşılamıyor.

Needle, küçük cihazlarda tool calling, structured extraction ve embedding çalıştırmayı hedefleyen kompakt bir model ve yazılım paketidir.

Neden yükseliyor · Küçük cihazlarda yerel tool calling ve extraction ihtiyacına odaklanması, 216 günde 12.730 yıldıza ulaşması ve son 28 gündeki 36 commit ile 15 farklı yazarın katkısı dikkat çekiyor. Yıldızlar ilginin göstergesi; model performansının bağımsız doğrulaması değil.

Oído, ESP32-S3 üzerinde cloud veya NPU olmadan open-vocabulary speech recognition çalıştırmayı hedefleyen C tabanlı bir ASR motorudur.

Neden yükseliyor · Düşük maliyetli bir mikrodenetleyicide open-vocabulary ASR çalıştırma iddiası ve README’de verilen LibriSpeech sonuçları dikkat çekiyor. Repo 1 günlük ve 46 yıldız almış olsa da son 28 gündeki 6 commit’in tek yazardan gelmesi, ilginin henüz bağımsız benimseme veya sürdürülebilir geliştirme kanıtı olmadığını gösteriyor.

Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimiz

On-device AI SDKs for iOS, macOS, Android, and the web. Small, focused models that run fully offline in Swift, Kotlin, and JavaScript with C

Private on-device AI chat for Android — runs any GGUF model locally via llama.cpp with ARM-optimised SIMD. Zero network permissions, encry

Whistle speech-to-text running fully on an ESP32-S3: hold a button, say a colour in one of 7 languages, the LED does it. No network.

Your car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI. CodeWatch's sibling for the garage.

A multi-model Muse: personal AI voice assistant on ESP32 - wake word or knob, any OpenAI-compatible brain (STT/chat/TTS mix-and-match), stre

On-device, ComfyUI-style node graph for image/video diffusion on Android. Run MiniMax H3 and WAN 2.2 14B on the Qualcomm Hexagon NPU. SD1.5,

OAK, C++ ile cihaz üzerinde AI agent çalıştırmayı hedefleyen, bazı agent özelliklerini açık kaynak modüller olarak sunan alpha aşamasındaki bir projedir.

Neden yükseliyor · 48 günde 1170 yıldız almış; on-device AI, gizlilik ve Qualcomm NPU desteği ilgi çekici bir konumlandırma. Ancak yükselişin özel nedenini mevcut veriden belirlemek mümkün değil. Son 28 günde commit ve farklı yazar sayısı sıfır; README’deki performans ve karşılaştırma iddiaları da burada bağımsız doğrulanmış kanıt sunmuyor.

Ultralytics YOLO26 quickstart for detection, instance and semantic segmentation, depth estimation, classification, pose, OBB, and tracking.

Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully offline.

A ternary, zero-heap tiny language model that runs inside a $2 microcontroller — bit-exact Python <-> C99 <-> Cortex-M3 (QEMU) parity. Apach

CPU-first LLM inference server on llama.cpp. Runs useful models on free-tier ARM boxes; rewriting the input made it ~6x faster and more accu

The 30 MB open-source edge AI agent runtime. Run AI agents offline on Linux (Raspberry Pi, Jetson). GPIO, UART, MQTT as first-class nodes. I

600 KB WASM runtime for Cactus Compute's Needle AI tool-calling models, Needle 3, 2 and 1 from one build. Browser, Cloudflare Workers, Node.

Fully local voice AI for iOS

Fastest MoE/LLM inference runtime for consumer and edge Blackwell GPUs. SN74 on Gittensor.

FastCrest Tether: the OSS edge-to-cloud AI deploy CLI. Optimize, verify, deploy across Jetson, RTX, Apple Silicon, AMD. Hybrid edge-cloud in

Local-first AI memory — runs offline on any machine with 8 GB+ RAM (SBC, mini PC, laptop, workstation). Zero-loss verbatim archive, knowledg

GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, depl

Ultralytics YOLOv8 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

Deploys your OS, databases, and SSL on your VPS in just 10 minutes. Orchestrates a team of AI agents for coding, marketing, and sales. The b

Run a 28.9M-parameter TinyLM on ESP32-S3 with an RP2040 OLED display node for fully local embedded AI inference.

edge-dit.cpp — a native C/C++ inference engine for Diffusion Transformers (DiT), designed for local and resource-constrained devices with au

Optimized ESP32-S3/P4 fully offline speech to text and text to speech system for Micropython and AtomVM, featuring a finetuned STT model for

Open Source Brain Platform | AI training and inference in Rust

Deploy streaming ASR + TTS on RK3576/RK3588 — 120ms TTS, 52-language ASR, one Docker command

Offline speech-to-text on the STM32N6 microcontroller: free English speech recognition on the NPU, no cloud

CPU-side action routing, context compression, and causal memory for AI agents — matches an LLM-everything agent at 58% fewer LLM calls and ~

Low-memory C++20 LLM inference runtime for quantized GGUF models on CPU — mmap-backed weights, paged KV cache, Q4/Q8 kernels, and reproducib

Ultralytics YOLO11 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

Lightweight AI agent runtime for homelabs, built around deterministic skills and local LLMs.

[MM' 2026] Light-MER for efficient multimodal emotion recognition with sub-1B MLLMs.

Natural-sounding streaming text-to-speech for the ESP32-S3: 4.4 M params, 4.9 MB, no cloud, no NPU

Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys, b

[Archived] AAOSP, predecessor to JibarOS. Early experiment in OS-level on-device AI (MCP + local LLM on Android 15). See JibarOS for the act

Distributed, peer-to-peer, decentralized network for LLM inference — peers seed & leech completions, metered by BitTorrent-protocol-style up

Offline AI research assistant for Android. Answers from Wikipedia and other reference packs on the phone, with citations. Gemma 4 runs on th

面向智能座舱的云边协同 AI Agent：端侧毫秒级车控，云端声明式 Multi-Agent 与 Skill/DAG 编排，支持 S2S 实时语音、声纹多用户、HMI和Android双端；LLM 只负责理解与规划，VAL 负责确定性安全执行。

🧠 One LLM, split across a Mac (Apple MPS) + a Windows PC (NVIDIA CUDA) — heterogeneous pipeline inference over a framework-neutral wire, bit

Drop-in ggml backend for Rockchip NPUs: offloads llama.cpp/whisper.cpp prefill to the RK3588 NPU

LLM-free, layout-aware PDF chunking for RAG pipelines. Preserves document structure via regex and font heuristics. Written in pure Rust.

Run RKLLM only in one docker command. Already converted models here.

EC2-Bench (EC²-Bench): benchmark for edge-cloud collaboration in long-horizon LLM agents — task performance, resource usage & privacy exposu

Jetson Nano edge AI vision Agent Harness: real-time video analytics, MCP tools, event evidence, DeepSeek online/offline, secure recovery

Face search engine: 100% recall at 96x less memory than HNSW. Register photos, identify people from camera/video/images. AVX-512 + Rust. No

P2P semantic matching for on-device AI agents. No server, no cloud.