Açık kaynak radarı

Havuz

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

135

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 gguf

1
vladimirrott/mojo-dllm 303
Local inference for diffusion language models (LLaDA, Dream), written in Mojo
9,8/gün ort. +48 son gün 182 commit 5 yazar Mojo 04 Eki 2026 güncellendi bugün
cpu diffusion-models gguf inference llada llm mojo
303
2
wici-ai/inferssd 297
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
22,8/gün ort. +32 son gün 188 commit 3 yazar C++ 22 Eki 2026 güncellendi bugün
apple-silicon cuda gguf inference llama-cpp llm metal mixture-of-experts
297
3
leonxger/deepseek-colab 47
Uncensored DeepSeek-V4.1-Flash IQ2_XS on Google Colab
9,4/gün ort. +23 son gün 1 commit 1 yazar Python 30 Eki 2026 güncellendi 5 gün önce
colab cuda deepseek deepseek-v4 gguf google-colab gpu llama-cpp
47
4
sgaofen/humanizer-local-model 721
Rewrites AI drafts so they read like a person wrote them — runs locally, keeps the facts
13,4/gün ort. +18 son gün 51 commit 4 yazar Python 11 Eyl 2026 güncellendi 16 gün önce
gguf humanizer llama-cpp llm local-llm rewriting
721
5
prabanta-dev/janas 601
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cp
13,4/gün ort. +18 son gün 62 commit 1 yazar C 20 Eyl 2026 güncellendi bugün
avx2 c cpu-inference gguf inference-engine linux llm local-llm
601
6
lawrence3699/jev-style 36
Local classification, routing, and scoring for AI agents, with option probabilities. Text + images, Python, MCP and agent skills.
0,9/gün ort. +12 son gün — commit Python 25 Eyl 2026 güncellendi dün
agent-skills calibration claude-code decision-model gguf guardrails jev llm-routing
36
7
ciddwd/overlay-translator önem 43gpt6-luna uyum 92gpt6-luna 1.201
Screen Translator, Android ekranındaki yazıları OCR ile tanıyıp çeviren ve sonucu ekranın üzerine yerleştiren bir uygulamadır.
Neden yükseliyor · 97 günde 906 yıldız alması, özellikle oyun ve manga çevirisi gibi belirgin bir kullanım alanına hitap ettiğine işaret ediyor. Ancak son 28 günde 2 commit ve 1 farklı yazar bilgisi, ilginin sürdürülebilir geliştirme faaliyetiyle desteklendiğine dair sınırlı kanıt sunuyor.
8,9/gün ort. +9 son gün 2 commit 1 yazar Kotlin 22 Haz 2026 güncellendi 5 gün önce
android android-app game-translation gguf kotlin llama-cpp llm manga
1.201
8
AtomicBot-ai/Atomic-Chat 1.929
Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer. Join our Discord: https
8,8/gün ort. +8 son gün 164 commit 3 yazar TypeScript 31 Mar 2026 güncellendi dün
ai-chat ai-tools apple-silicon chatgpt deepseek desktop-app gemma gguf
1.929
9
jegly/Box 972
The most advanced, fully offline client-side AI suite on Android today.
4,8/gün ort. +6 son gün 60 commit 2 yazar Kotlin 17 Nis 2026 güncellendi dün
artificial-intelligence box gguf litert llamacpp local-ai litert-lm android-ai-app
972
10
AtomicBot-ai/atomic-agent önem 48gpt6-luna uyum 34gpt6-luna 3.497
Atomic Agent, yerel veya cloud modellerle çalışan ve browser, dosya, onaylı shell komutları ile MCP araçlarını kullanabilen bir AI agent uygulamasıdır.
Neden yükseliyor · 159 günlük bir repoda 2.505 yıldız ve son 28 günde 648 commit dikkat çekiyor; yerel modellerle çalışan kapsamlı bir agent vaadi ve README'deki GAIA L1 karşılaştırması ilgiyi artırmış olabilir. Ancak commitlerin yalnızca 2 farklı yazardan gelmesi aktivitenin geniş bir katkıcı tabanına yayıldığını göstermiyor; yükselişin kesin nedeni bilinmiyor.
17,8/gün ort. +5 son gün 668 commit 1 yazar TypeScript 21 Nis 2026 güncellendi 6 gün önce
agents ai-agent browser-automation cli gguf llama-cpp llm local-first
3.497
11
nyosegawa/speech.cpp 331
Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR,
9,2/gün ort. +4 son gün 128 commit 1 yazar C++ 29 Eyl 2026 güncellendi 3 gün önce
asr cpp ggml gguf irodori-tts metal parakeet qwen3-asr
331
12
danalec/rgx 19
High-performance full-text search across PDFs, Office documents, ZIP archives, email, media metadata and GGUF/LLM model files. ripgrep-compa
2,7/gün ort. +4 son gün — commit Rust 28 Eki 2026 güncellendi bugün
ai-tools archive cli developer-tools email full-text-search gguf grep
19
13
Helldez/BigMoeOnEdge 706
Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimiz
6/gün ort. +3 son gün 155 commit 3 yazar C++ 10 Tem 2026 güncellendi bugün
android cpp edge-ai gemma gguf inference llama-cpp llm
706
14
kayson-39/YishengTranslator-White 24
译声实时翻译（白色新版）— 免费的 Windows 实时日语字幕与翻译工具，支持系统声音、本地 GGUF / Ollama / OpenAI 兼容 API 翻译。
1,4/gün ort. +3 son gün — commit Python 18 Eki 2026 güncellendi 16 gün önce
accessibility desktop-app gguf japanese llama-cpp pyside6 real-time speech-recognition
24
15
JakeATX/llamAmpere 216
llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s
3,7/gün ort. +2 son gün 718 commit 2 yazar C++ 07 Eyl 2026 güncellendi dün
ampere consumer-gpu cuda ggml gguf kv-cache-quantization llama-cpp llm
216
16
HoppouAI/Breeze-TTS-2.cpp 146
Bilingual English and Mandarin text to speech in C++ and GGUF. Voice design, cloning, direction and experimental voice conversion. Vulkan ba
2,1/gün ort. +2 son gün 32 commit 4 yazar C++ 26 Ağu 2026 güncellendi 2 gün önce
breeze-tts cpp ggml gguf inference qwen3 speech-synthesis streaming
146
17
thomas9120/LLama-GUI 136
User friendly GUI for configuring and launching llama.cpp
0,7/gün ort. +2 son gün — commit JavaScript 19 Nis 2026 güncellendi 2 gün önce
gui llama-cpp llamacpp llm-inference localllama gguf llm
136
18
IST-DASLab/GSQ 130
Gumbel-Softmax post-training quantization for LLMs (1–3 bit scalar, INT/GGUF-compatible).
0,7/gün ort. +2 son gün — commit Python 12 May 2026 güncellendi 11 Tem 2026
gguf llm post-training-quantization quantization
130
19
syfr512/SweetrollLM 98
Local-first AI chat client combining SillyTavern-style character cards, LM Studio-style GGUF model management, Ollama/OpenAI-compatible APIs
0,6/gün ort. +2 son gün — commit Python 05 Haz 2026 güncellendi 27 Haz 2026
agentic-ai ai-chat-client character-cards desktop-app fastapi gguf huggingface koboldcpp
98
20
kouhxp/gutsy 83
Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option.
2,4/gün ort. +2 son gün — commit HTML 01 Eki 2026 güncellendi 05 Eki 2026
agents classifier content-moderation cpu-inference decision-model gguf intent-classification jev
83
21
fulvian/engraft-ngram 59
ENGRAFT: write facts into an LLM's n-gram (Engram) memory table as a removable overlay: 100 facts in a 9 MB file, no weights touched, verifi
1/gün ort. +2 son gün — commit Python 05 Eyl 2026 güncellendi 30 Eyl 2026
deepseek engram gguf interpretability knowledge-editing knowledge-injection llama-cpp llm
59
22
midagedev/bloomery 57
Hybrid GPU + CPU inference for mixture-of-experts models, written in Rust down to the CUDA kernels. A drop-in llama-server.
1,2/gün ort. +2 son gün — commit Rust 19 Eyl 2026 güncellendi bugün
cuda deepseek gguf glm inference llama-cpp llm moe
57
23
benmaster82/Pithos 20
A dependency-free C inference engine for Liquid AI's LFM2 / LFM2.5 models. Terminal chat, an OpenAI-compatible server, a web agent and a ter
2,5/gün ort. +2 son gün — commit C 27 Eki 2026 güncellendi dün
ai-agent avx2 c coding-agent cross-platform gguf inference-engine lfm2
20
24
demiralpdev/Caphlon-Model 18
A 6.87 GiB GGUF build of Qwen 3.8 27B — full 27B quality on 8 GB RAM. 96.7% HumanEval, 92.9% MMLU retention, no distillation.
1,8/gün ort. +2 son gün — commit HTML 25 Eki 2026 güncellendi 7 gün önce
27b edge-llm gguf iq2s layer-pruning lightweight-llm llama-cpp llm
18
25
RustingStudio/RustingStrata 16
Pure-Rust MoE inference engine for Qwen3.5/3.6 GGUF. CPU+GPU hybrid experts, NVRTC CUDA kernels, OpenAI-compatible server. 2x llama.cpp pref
0,6/gün ort. +2 son gün — commit Rust 10 Eki 2026 güncellendi dün
cuda gguf inference llama-cpp llm local-llm mixture-of-experts moe
16
26
crosswk/SayIt 468
Open-source voice typing for Windows and macOS — a Wispr Flow / Superwhisper alternative. Press a shortcut, speak, and AI-polished text land
2,6/gün ort. +1 son gün 34 commit 3 yazar TypeScript 09 May 2026 güncellendi dün
asr qwen3-asr self-hosted speech-recognition speech-to-text tauri voice-input voice-typing
468
27
Entrpi/ds4-on-spark 413
Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark,
2,3/gün ort. +1 son gün 0 commit 0 yazar Shell 12 May 2026 güncellendi 27 Ağu 2026
benchmark cuda deepseek-v4-flash dgx-spark gb10 gguf inference llm
413
28
hogeheer499-commits/strix-halo-guide 368
Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.
1,5/gün ort. +1 son gün 1 commit 1 yazar Python 11 Mar 2026 güncellendi 14 gün önce
amd benchmark gfx1151 llama-cpp llm local-llm rocm ryzen-ai-max
368
29
mohitsoni48/TurboLLM 286
Run any local LLM engine, auto-tuned to your GPU — polished web UI + OpenAI/Anthropic-compatible API. Point Claude Code at your own machine
2/gün ort. +1 son gün 517 commit 5 yazar TypeScript 12 Haz 2026 güncellendi 4 gün önce
ai anthropic-api claude-code gguf gpu inference llama-cpp llama-server
286
30
rongxinzy/RongxinAI 162
Open-source desktop AI agent: built-in free model, local GGUF models via llama.cpp, dispatch tasks from WeChat/Feishu/DingTalk. Files, brows
0,9/gün ort. +1 son gün — commit TypeScript 11 May 2026 güncellendi bugün
agentic-ai context-engineering ai ai-agent ai-agents ai-assistant browser-automation computer-use
162
31
amurgola/LumaBrowser 131
Local AI desktop app: a Chromium browser with a GPU-aware llama.cpp runtime, OpenAI-compatible API, AI chat and agents, Stable Diffusion ima
5/gün ort. +1 son gün 15 commit 1 yazar JavaScript 09 Eki 2026 güncellendi 2 gün önce
ai-agents ai-browser browser-automation chatgpt-alternative desktop-app electron gguf llama-cpp
131
32
akivet/Mica 85
A 4B decision model: calibrated probabilities for yes/no, choice and score questions over long inputs.
2,1/gün ort. +1 son gün — commit Python 25 Eyl 2026 güncellendi 6 gün önce
agents decision-making decision-model gguf jev llama-cpp llm-as-a-judge qwen
85
33
gianlucamazza/xllama 78
Local LLM inference on Xbox Series S in Developer Mode: llama.cpp (GGUF) + ONNX Runtime GenAI, an OpenAI-compatible LAN endpoint (off by def
0,5/gün ort. +1 son gün — commit C++ 19 May 2026 güncellendi dün
cpp llm local-inference onnxruntime uwp xbox directml game-console
78
34
jceronch1/Clonar-voz 75
Clonación de voz y texto a voz 100% local con Qwen3-TTS y llama.cpp. Funciona en CPU y GPU, 10 idiomas, interfaz web en español.
1,3/gün ort. +1 son gün — commit Python 08 Eyl 2026 güncellendi 09 Eyl 2026
espanol fastapi gguf llama-cpp local-ai qwen3-tts text-to-speech tts
75
35
synchopate/llama-modchip 72
♟️ llama-modchip v2.1: Run 30B Sparse MoE LLMs on Pure CPU (0 GPUs) at 20–60.4 tok/s with a 256K Context Window via a 1.64MB Stockfish-PVS +
12/gün ort. +1 son gün 29 commit 1 yazar Python 29 Eki 2026 güncellendi bugün
avx512 cpu-inference hpc llama-cpp mamba2 mixture-of-experts nemotron speculative-decoding
72
36
shifulegend/project-zero 55
CPU-optimized LLM inference engine (C)
0,4/gün ort. +1 son gün — commit C 06 Haz 2026 güncellendi 5 gün önce
avx512 bitnet c99 cpu cpu-inference deepseek gguf inference
55
37
asher/gmlx 47
Local inference platform for K/IQ-quant GGUF models on Apple Silicon
0,4/gün ort. +1 son gün — commit Python 19 Tem 2026 güncellendi bugün
anthropic-api apple-silicon gguf gguf-model-support gguf-runner inference inference-engine llm
47
38
notwitcheer/llm-bench-rig 47
Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publishable
0,3/gün ort. +1 son gün — commit Python 27 May 2026 güncellendi dün
benchmarking cuda fastapi gguf llama-cpp llm lm-evaluation-harness machine-learning
47
39
anthony-chaudhary/fak 46
Agentic Runtime
0,3/gün ort. +1 son gün — commit Go 21 Haz 2026 güncellendi bugün
agent-kernel agentic-ai ai-agents ai-gateway claude-code context-compression gguf golang
46
40
MADEVAL/FerryAI 38
Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embe
0,3/gün ort. +1 son gün — commit PHP 04 Tem 2026 güncellendi 17 gün önce
ai embeddings ffi generative-ai gguf inference llama-cpp llm
38
41
manjunathshiva/opendecider 38
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. +1 son gün — commit Python 27 Eyl 2026 güncellendi bugün
apple-silicon calibration classification decision-model gguf huggingface llm mlx
38
42
lifeidle/qwen3.8-flash-next-5090-laptop-24gb-strata 27
Qwen3.8-Flash-Next 177B MoE (IQ3_S 3.44bpw) on RTX 5090 Laptop 24GB: full-model quality @ 97.7 tok/s · dual-lane 256K full-context unlocked
0,5/gün ort. +1 son gün — commit Python 10 Eyl 2026 güncellendi 7 gün önce
256k-context flash-next gguf iq3-xxs local-llm moe mtp quantization
27
43
lifeidle/qwen3.8-27b-5090-laptop-24gb-coder390-ninfer 21
Qwen3.8-27B on RTX 5090 Laptop 24GB — TWIN-TURBO NVFP4 (native llama.cpp) vs Coder390 Q3 LynnStyle (.ninfer + NInfer engine in WSL2/Docker):
0,4/gün ort. +1 son gün — commit Python 10 Eyl 2026 güncellendi 19 gün önce
benchmark llama-cpp local-llm mtp nvfp4 rtx-5090 blackwell long-context
21
44
System64fumo/kappai 16
High performance inference engine
0,2/gün ort. +1 son gün — commit C 17 Ağu 2026 güncellendi dün
ai arm64 llm vulkan high-performance-computing gguf
16
45
andrei-borcea/liyab 15
🔥 Run large open language models on your phone. A C++20 GGUF inference engine that streams models larger than RAM from flash, paces itself b
0,5/gün ort. +1 son gün — commit C++ 07 Eki 2026 güncellendi 3 gün önce
edge-ai gguf inference-engine inference-optimization llm llm-inference local-llm on-device-ai
15
46
emnlmn/snap 9
Typed decisions from unstructured state: one forward pass, zero generated text. Local, deterministic, Jev-compatible. Not affiliated with ty
0,2/gün ort. +1 son gün — commit Rust 23 Eyl 2026 güncellendi 27 gün önce
decision-engine gguf llamacpp llm llm-inference local-llm rust structured-outputs
9
47
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
45,7/gün ort. +0 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
48
zhongkaifu/TensorSharp 652
A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interf
3/gün ort. +0 son gün 194 commit 5 yazar C# 03 Nis 2026 güncellendi bugün
gemma inference inference-engine llm qwen transformers gemma4 gguf
652
49
quantumaikr/quant.cpp 405
LLM inference with 7x longer context. Pure C, zero dependencies. Lossless KV cache compression + single-header library.
1,8/gün ort. +0 son gün 0 commit 0 yazar C 28 Mar 2026 güncellendi 26 Nis 2026
delta-compression embeddable gguf kv-cache llm llm-inference pure-c quantization
405
50
raketenkater/ggrun 283
llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.
1,2/gün ort. +0 son gün 242 commit 2 yazar Go 11 Mar 2026 güncellendi 2 gün önce
cuda gguf llama-cpp llm metal moe multi-gpu golang
283