Açık kaynak radarı

Havuz

Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.

113

repo · sayfa 1 / 3

Sırala

Yıldız/gün (hız)Son gün (★/gün)Son hafta (★/gün)Son ay (★/gün)Toplam yıldız AI önem skoru Bana uyum Commit (28g)Yazar (28g)En yeni

Konu

Tümü AI / LLM18 Veri9 Geliştirici araçları13 Diğer3 SaaS altyapı13 Web11

Süz

Yalnız hareketli Yalnız analizli≥ 0 ≥ 100 ≥ 500 ≥ 2.000

Yalnız hareketli, son 28 günde commit almamış repoları gizler (yıldızı olan ama bırakılmış projeler). Commit sayısı henüz ölçülmemiş repolar da gizlenir.

EtiketTüm GitHub etiketleri — repo sahiplerinin koyduğu topic'lergöster

Sırala:

Etiketler yükleniyor…

Aktif mlx

1
MacHatter1/ContainerDesk 38
Native macOS workspace for Apple's container runtime. Browse, run, build and clean up Linux containers with live resource gauges, a built-in
7,6/gün ort. +4 son gün 16 commit 1 yazar Swift 29 Eki 2026 güncellendi 2 gün önce
apple-container apple-silicon buildkit container-management containers developer-tools linux-containers local-llm
38
2
zhangshuibai/molten 23
Run a coding model at 300+ tok/s on your Mac. Native Rust + Metal inference engine for LiquidAI LFM2.5-24B-A2B (MLX 4-bit) on Apple Silicon.
2,6/gün ort. +0 son gün — commit Metal 25 Eki 2026 güncellendi 6 gün önce
apple-silicon gpu-kernels inference-engine inference-optimization lfm2 liquid-ai llama-cpp llm
23
3
Nhahan/Xevn 13
A 4B decision model built for Korean.
1/gün ort. +0 son gün — commit 21 Eki 2026 güncellendi 12 gün önce
calibration decision-model jev korean llm mlx quantization qwen
13
4
BobClawblaw/deepseek-v41-flash-mlx-m5-ultra 14
DeepSeek-V4.1-Flash-1017 on one 256 GB M5 Ultra: 1M context, 70.7-104.9 tok/s decode with DSpark drafts, 1,739-1,867 tok/s cold prompts (8k-
0,9/gün ort. +1 son gün — commit Python 19 Eki 2026 güncellendi 12 gün önce
apple-silicon deepseek deepseek-v4 llm llm-inference long-context m5-ultra metal
14
5
kanaworksai-hue/audio-studio-mcp 570
Local AI BGM and sound effects for Claude Code and any MCP client. Stable Audio 3 on Apple Silicon (MLX) and Windows NVIDIA GPUs (PyTorch).
35,6/gün ort. +8 son gün 48 commit 1 yazar Python 18 Eki 2026 güncellendi 11 gün önce
apple-silicon audio-generation claude-code game-audio mcp mcp-server mlx music-generation
570
6
kingcharleslzy-ai/dsh-qwen-studio 37
Qwen Image 2.1 for DeepSeek Harness: native image editing on Apple Silicon MLX/MFLUX or self-hosted CUDA, LoRA, ControlNet, inpainting, pres
2,1/gün ort. +0 son gün — commit TypeScript 16 Eki 2026 güncellendi 13 gün önce
apple-silicon deepseek-harness image-generation mflux mlx qwen-image controlnet dsh-plugin
37
7
navthings/airgpt 25
train your own chatbot from scratch on a mac
1,1/gün ort. +0 son gün — commit Python 12 Eki 2026 güncellendi 16 gün önce
apple-silicon chatbot from-scratch gpt llm macbook mlx tokenizer
25
8
EXistenz-78/dt-hub 19
A native macOS companion for Draw Things: always-visible image and Moodboard inputs, a canvas you can draw on from an iPad (Sidecar), a loca
0,7/gün ort. +0 son gün — commit Swift 07 Eki 2026 güncellendi 4 gün önce
apple-silicon draw-things flux macos mlx plugins prompt-engineering stable-diffusion
19
9
StartLuxLabs/StartLux-Decision 1.644
Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine f
47/gün ort. +10 son gün 22 commit 2 yazar Python 29 Eyl 2026 güncellendi 12 gün önce
agents calibration classification decision-making gguf inference llama-cpp llm
1.644
10
manjunathshiva/opendecider 37
Open, calibrated System 1 decision models: typed choice / score / yes-no answers with a probability for every option. 400M to 80B; CPU, NVID
1/gün ort. +0 son gün — commit Python 27 Eyl 2026 güncellendi dün
apple-silicon calibration classification decision-model gguf huggingface llm mlx
37
11
rinste/turbo-mlx 21
Local AI image & video generation for Apple Silicon: a native macOS app with an MLX Swift engine. FLUX.2 Klein, Z-Image Turbo, Qwen-Image 25
0,6/gün ort. +0 son gün — commit Swift 27 Eyl 2026 güncellendi dün
apple-silicon generative-ai macos mlx swiftui text-to-image text-to-video
21
12
B0yko/taskdistill 3
Distil an expensive LLM API call on a narrow task into a small local model: capture traffic, curate, LoRA fine-tune with MLX on Apple Silico
0,1/gün ort. +0 son gün — commit Python 27 Eyl 2026 güncellendi 9 gün önce
apple-silicon calibration cost-optimization fine-tuning information-extraction knowledge-distillation llm llm-evaluation
3
13
deskmind-ai/deskmind 127
Small enough to run on your Mac. Smart enough to ask. An open-source computer use agent for macOS, with local models (MLX) that see, decide
3,3/gün ort. +0 son gün 374 commit 2 yazar Swift 26 Eyl 2026 güncellendi 8 gün önce
agents ai-agent apple-silicon computer-use computer-use-agent gui-agent local-llm macos
127
14
nyosegawa/asist 32
A realtime assistant for Mac and Windows. Talk to it and it answers aloud, shows your schedule and mail as cards, and hands longer work to a
0,8/gün ort. +2 son gün — commit TypeScript 25 Eyl 2026 güncellendi dün
ai-agent cuda electron llm macos mlx speech-recognition typescript
32
15
lawrence3699/jev-style 24
Local classification, routing, and scoring for AI agents, with option probabilities. Text + images, Python, MCP and agent skills.
0,6/gün ort. +0 son gün — commit Python 25 Eyl 2026 güncellendi dün
agent-skills calibration claude-code decision-model gguf guardrails jev llm-routing
24
16
caiovicentino/eikos 43
Open, calibrated, single-pass typed-decision models (4B & 27B) for finance and trading
1/gün ort. +0 son gün — commit Python 23 Eyl 2026 güncellendi 02 Eki 2026
calibration decision-making finance llm mlx trading vllm
43
17
ChenneyZhuang/laya-browser-agent 25
Local, open-source Jev alternative: browser agent decisions with Laya (System One model) on your own machine. No cloud, no API key. Playwrig
0,6/gün ort. +0 son gün — commit Python 21 Eyl 2026 güncellendi 01 Eki 2026
agent ai-agents apple-silicon browser-agent browser-automation computer-use decision-model jev
25
18
OuincheWinch/DiffusionBear 23
A free, local AI image generation studio for Apple Silicon Macs. Run FLUX.2, Krea 2, Z-Image-Turbo, Qwen-Image-2.1-Turbo and SDXL offline on
0,5/gün ort. +0 son gün — commit JavaScript 21 Eyl 2026 güncellendi 3 gün önce
apple-silicon fibo fibo2 flux flux2 flux3-klein generative-ai image-generation
23
19
HenryZ838978/VoxWeft 15
On-device simultaneous interpretation on Apple Silicon — VoxCPM2 on MLX at the core, streaming TTS in ~170 ms, voice clone, any-pair transla
0,3/gün ort. +0 son gün — commit Python 20 Eyl 2026 güncellendi 22 Eyl 2026
apple-silicon asr edge-ai harness macos mcp mlx on-device
15
20
Micha0827/snapjudge 14
Typed decisions (choice / score / yes-no) from local Qwen models on Apple Silicon. Probabilities come straight from the logits, no text gene
0,3/gün ort. +0 son gün — commit Python 18 Eyl 2026 güncellendi 21 Eyl 2026
apple-silicon classification decision-making fastapi llm llm-evaluation local-llm logits
14
21
webkubor/mlx-vlm-kit 1
Apple Silicon 本地视觉语言模型 CLI：用 MLX/Qwen3-VL 描述图片、图像问答与提示词反推。Offline vision-language CLI for image understanding, visual Q&A and reverse prompt
0/gün ort. +0 son gün — commit Python 14 Eyl 2026 güncellendi 9 gün önce
apple-silicon cli image-understanding local-inference macos mlx offline python
1
22
maximpri/mlxtop 143
A top for local LLMs: memory, paging, GPU and tokens/s for oMLX, Ollama, llama.cpp, vLLM and more
2,7/gün ort. +0 son gün — commit Rust 11 Eyl 2026 güncellendi dün
apple-silicon llama-cpp llm local-llm mlx monitoring ollama rust
143
23
siamcafe/bomllm 43
Self-hosted Thai AI infrastructure — Mac Mini M4 Pro running TURBO-Fable 27B at 18.5 tok/s for $0.54/day. Fleet of 9 machines, GOD CONFIG v7
0,8/gün ort. +0 son gün — commit Python 11 Eyl 2026 güncellendi 2 gün önce
litellm mac-mini mlx ollama comfyui fleet-management flux local-inference
43
24
canivel/dynolab 153
Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interven
2,6/gün ort. -2 son gün 61 commit 1 yazar Python 04 Eyl 2026 güncellendi 5 gün önce
ai ai-interpretability ai-safety aisafety alignment apple-silicon llm mcp
153
25
XHToken/Spark-MLX-LLM 16
Spark-optimized MLX LM for local inference and deployment on Apple Silicon
0,2/gün ort. +1 son gün — commit Python 29 Ağu 2026 güncellendi 2 gün önce
apple-m5 apple-silicon inference llm machine-learning mlx spark sparkllm
16
26
carloslfu/slotstream önem 64gpt6-luna uyum 38gpt6-luna 645
Slotstream, büyük bir MoE modelini SSD’den parça parça yükleyip yoğun kullanılan expert’leri bellekte önbelleğe alarak Apple Silicon Mac’lerde çalıştıran yerel bir inference engine’dir.
Neden yükseliyor · README, 48 GB M5 Pro üzerinde belirli koşullarda 15.86 tok/s ölçümü ve prompt işleme iyileştirmeleri yayımlıyor; son 28 günde 271 commit ve 5 farklı yazar da yoğun geliştirme faaliyetine işaret ediyor. Ancak proje yalnızca 30 günlük ve mevcut sürüm için nitelikli tam yanıt hızı ölçümünün hâlâ beklediği belirtiliyor.
9,6/gün ort. +5 son gün 124 commit 3 yazar Swift 28 Ağu 2026 güncellendi 2 gün önce
apple-silicon claude-code inference-engine llm llm-inference local-ai local-llm macos
645
27
fermionresearch/phonon 327
Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images
4,9/gün ort. +3 son gün 7 commit 1 yazar Python 28 Ağu 2026 güncellendi 7 gün önce
asr cuda docker low-bit mlx pytorch quantization speech-recognition
327
28
XHToken/Spark-X2.6 önem 52gpt6-luna uyum 35gpt6-luna 877
Spark-X2.5, yerel çalıştırma ve agent iş akışları için tasarlanmış 1.7B ve 4B boyutlarında açık dil modelleri serisidir.
Neden yükseliyor · Yeni model serisi; uzun context, küçük model boyutu ve agent/coding yeteneklerini aynı anda öne çıkarıyor. README'de 34 günlük yaş, 386 yıldız ve son 28 günde 9 commit ile 2 farklı yazar bilgisi var; bunlar erken ilgi ve güncel çalışma gösteriyor, ancak model performansını bağımsız olarak kanıtlamıyor.
12,4/gün ort. -1 son gün 3 commit 2 yazar 24 Ağu 2026 güncellendi 2 gün önce
agent ai ai-agent ai-coding ai-model huggingface llamacpp llm
877
29
raullenchai/rapid-mlx-dsh-provider 70
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
0,9/gün ort. +0 son gün — commit JavaScript 17 Ağu 2026 güncellendi 19 Ağu 2026
apple-silicon coding-agent deepseek-harness dsh dsh-plugin llm local-llm mlx
70
30
ananasDDA/pocket-ai-lab 13
Offline LLM app for iPhone: run open models from Hugging Face on-device with llama.cpp, MLX, Core ML and Apple Foundation Models. No account
0,2/gün ort. +0 son gün — commit Swift 16 Ağu 2026 güncellendi 2 gün önce
apple-foundation-models coreml gemma gguf huggingface ios iphone llama-cpp
13
31
Greninja9257/LabLLM 39
A native macOS lab for teaching tiny language models to think — build the architecture, train the weights, and watch a small LLM emerge from
0,5/gün ort. +0 son gün — commit Swift 15 Ağu 2026 güncellendi 20 Ağu 2026
ai apple-silicon artificial-intelligence deep-learning fine-tuning generative-ai gpt large-language-model
39
32
nanguoyu/minirun-app 64
Run Kimi K3 (2.8 T parameters,1.56 TB) on iPhone 16 Pro? Weights stream from your SSD through a memory budget you set. Free, local, on Mac a
0,8/gün ort. +0 son gün — commit Swift 14 Ağu 2026 güncellendi 12 Eyl 2026
apple-silicon deepseek ios kimi llm local-llm macos mlx
64
33
WestWaters/pollard-weights 33
A tiered-memory system design for workloads that don't fit in RAM: measure the working set, pin the hot tier, stream the cold tier from flas
0,4/gün ort. +0 son gün — commit Python 07 Ağu 2026 güncellendi dün
diagnostics exl3 gguf gptq llama-cpp llm low-resource mac
33
34
Badtheorylabs/Macaw 34
Macaw — on-device AI agent for macOS. 2.7B LFM2.5 fine-tune, MLX 4-bit, 97 macOS tools, no cloud.
0,4/gün ort. +0 son gün — commit Python 05 Ağu 2026 güncellendi 08 Ağu 2026
agent apple-silicon llm macos mlx on-device tool-calling
34
35
appautomaton/mlx-h3 34
Pure MLX MiniMax-H3 text-to-video-and-audio inference for Apple Silicon.
0,4/gün ort. +0 son gün — commit Python 04 Ağu 2026 güncellendi 14 Eyl 2026
apple-silicon audio-generation generative-ai macos minimax-h3 mlx text-to-video video-generation
34
36
shashankswe2020-ux/rigspark 20
Which local LLMs can your computer run? Hardware-aware CLI, TUI and GUI: yes/slow/no verdicts and tok/s from your GPU VRAM and RAM, then ver
0,2/gün ort. +0 son gün — commit Rust 04 Ağu 2026 güncellendi dün
ai apple-silicon cli gpu hardware inference llama-cpp llm
20
37
Bingeljell/image-to-3dlab 1.068
AssetFurnace: the most complete open-source image-to-3D pipeline (Oct 2026). Prompt or picture → textured, rigged, animated game character,
11,5/gün ort. +15 son gün 563 commit 2 yazar Python 02 Ağu 2026 güncellendi dün
3d-generation 3d-models animation apple-silicon auto-rigging blender game-assets gamedev
1.068
38
iannuttall/natter 84
Fast, local-first dictation for macOS
0,9/gün ort. +0 son gün — commit Swift 02 Ağu 2026 güncellendi 31 Ağu 2026
dictation local-first macos mlx speech-recognition swift
84
39
Leo6Leo/whispr-stream 21
On-device streaming speech-to-text for macOS, built on Qwen3-ASR via MLX
0,2/gün ort. +0 son gün — commit Swift 02 Ağu 2026 güncellendi 5 gün önce
apple-silicon dictation local-ai local-first machine-learning macos mlx offline-ai
21
40
Mesutcydev/ios-local-llm 15
OnDevice Local AI Studio — run LLMs on iPhone offline. SwiftUI workbench with MLX, llama.cpp, whisper.cpp, RAG, and authenticated OpenAI/Ant
0,2/gün ort. +1 son gün — commit Swift 29 Tem 2026 güncellendi 01 Eki 2026
ios local-ai mlx on-device-ai swift swiftui ai-agents coreml
15
41
scouttyg/writekin 22
Writing that's kin to yours
0,2/gün ort. +0 son gün — commit Swift 28 Tem 2026 güncellendi 28 Tem 2026
fine-tuning llm local-llm macos mlx on-device qlora swift
22
42
Tylogi/TyloQuant 95
Get more intelligence from every bit. Better quantization formats and smarter calibration let larger, stronger models run smoothly on the ha
0,9/gün ort. +1 son gün — commit C++ 24 Tem 2026 güncellendi 5 gün önce
apple-silicon cuda deepseek gemma gguf llm llm-inference llm-quantization
95
43
Misfits-Rebels-Outcasts/MLXUI 40
MLXUI is a Local AI Browser for MLX. Run MLX models AI Workflows.
0,4/gün ort. +0 son gün — commit Swift 24 Tem 2026 güncellendi dün
ai ai-tools automation macos-app mlx workflow
40
44
felixrieseberg/language-model-builder 62
An educational macOS app: build and chat with a tiny language model, trained on your Mac
0,6/gün ort. +1 son gün — commit 20 Tem 2026 güncellendi 02 Ağu 2026
ai llm llm-tools machine-learning mlx
62
45
asher/gmlx 46
Local inference platform for K/IQ-quant GGUF models on Apple Silicon
0,4/gün ort. +0 son gün — commit Python 19 Tem 2026 güncellendi 4 gün önce
anthropic-api apple-silicon gguf gguf-model-support gguf-runner inference inference-engine llm
46
46
bitwize-ai/Logue 173
A local-first workspace for documents, tasks and meetings on macOS — nested spaces, typed properties, relations and saved views, with transc
1,6/gün ort. +0 son gün 0 commit 0 yazar Swift 18 Tem 2026 güncellendi 28 gün önce
ai-agent apple-silicon knowledge-base llm local-first macos meeting-notes mlx
173
47
snegireff/meeting-scribe 34
Personal fork of czlonkowski/simple-meeting-scribe (MIT) — local macOS meeting transcriber: Ukrainian support, summary export (Telegram/Obsi
0,3/gün ort. +0 son gün — commit Swift 16 Tem 2026 güncellendi 07 Ağu 2026
local-first macos mcp meeting-notes mlx swift swiftui transcription
34
48
nilava/TabType 52
Free, open-source AI autocomplete for macOS — on-device ghost-text suggestions in every app. A private, local Cotypist alternative built wit
0,5/gün ort. +0 son gün — commit Swift 15 Tem 2026 güncellendi 26 gün önce
ai-autocomplete autocomplete copilot cotypist-alternative ghost-text keyboard llm local-llm
52
49
drmihirbrahme/midge 13
Tiny engine, immense models — run large MoE LLMs (gpt-oss, Mixtral, Qwen3-MoE) on ordinary machines by streaming experts from disk. OpenAI-c
0,1/gün ort. +0 son gün — commit Python 14 Tem 2026 güncellendi 21 Ağu 2026
apple-silicon cpu-inference gpt-oss llm low-memory mixture-of-experts mlx moe
13
50
chayapats/oliv 111
Thai + English voice typing for Mac. Offline speech-to-text that types Thai-spoken tech words in English. Push-to-talk dictation on Apple Si
1/gün ort. +0 son gün — commit Swift 11 Tem 2026 güncellendi dün
apple-silicon code-switching dictation local-ai macos mlx offline on-device-ai
111