Açık kaynak radarı

Havuz

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

202

repo · sayfa 1 / 5

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 llama-cpp

1
DevDock-AI/Speedy 25
Qwen3.8-Flash-Next (125B MoE) up to 1M context on one or two RTX cards (tuned on 3080 10gb). A measured, tuned and benchmarked fork of Str
25/gün ort. 54 commit 7 yazar C++ 01 Kas 2026 güncellendi dün
cuda inference llm long-context mixture-of-experts multi-gpu qwen rtx-3080
25
2
Aevonix/FlashAlign 115
ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenC
57,5/gün ort. +27 son gün 7 commit 1 yazar Python 31 Eki 2026 güncellendi 2 gün önce
abliteration hermes inference llama-cpp llm model-alignment openclaw sglang
115
3
leonxger/deepseek-colab 14
Uncensored DeepSeek-V4.1-Flash IQ2_XS on Google Colab
4,7/gün ort. 1 commit 1 yazar Python 30 Eki 2026 güncellendi 4 gün önce
colab cuda deepseek deepseek-v4 gguf google-colab gpu llama-cpp
14
4
synchopate/nemotron-30b-cpu-256k 69
Running a 30B MoE LLM on CPU at 30-50+ tok/s with a 256K Context Window via Hybrid Mamba-2 SSM, L3 NTA Slicing, AVX-512 VNNI Tile Repacking
17,3/gün ort. +2 son gün 4 commit 1 yazar Python 29 Eki 2026 güncellendi dün
avx512 cpu-inference hpc llama-cpp llm mamba2 mixture-of-experts nemotron
69
5
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.
2,9/gün ort. +0 son gün 7 commit 1 yazar Metal 25 Eki 2026 güncellendi 5 gün önce
apple-silicon gpu-kernels inference-engine inference-optimization lfm2 liquid-ai llama-cpp llm
23
6
aymen94/NeuronDump 16
Look inside any local LLM (GGUF from Ollama, LM Studio, Hugging Face, Jan, llama.cpp): layers, heads, vocabulary, chat template, weights. Ex
2/gün ort. +1 son gün — commit Rust 25 Eki 2026 güncellendi 6 gün önce
cli gguf inspector llama-cpp llm model-compression ollama pruning
16
7
demiralpdev/Caphlon-Model 13
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.
1,6/gün ort. +0 son gün — commit HTML 25 Eki 2026 güncellendi 6 gün önce
27b edge-llm gguf iq2s layer-pruning lightweight-llm llama-cpp llm
13
8
CookSleep/Rummage 26
基于 Google DeepMind 的 EmbeddingGemma 2 的本地多模态文件语义搜索器：用一句话描述文件的内容，在你选定的文件夹中找到文档、照片、截图、录音和视频，也可以以图搜图。支持 Windows、Android。
2,6/gün ort. +2 son gün — commit Rust 23 Eki 2026 güncellendi 8 gün önce
android cli desktop-search embeddinggemma embeddings file-search litert llama-cpp
26
9
alleyxd/quantpicker 15
Measures which GGUF quant of a model to run on your GPU: real speed and quality loss (KL divergence), not estimates.
1,5/gün ort. +0 son gün — commit Rust 23 Eki 2026 güncellendi 6 gün önce
benchmark gguf llama-cpp llm local-llm quantization rust
15
10
wici-ai/inferssd 235
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
21,4/gün ort. +50 son gün 183 commit 3 yazar C++ 22 Eki 2026 güncellendi dün
apple-silicon cuda gguf inference llama-cpp llm metal mixture-of-experts
235
11
MultiX0/ip-nas 72
Raspberry Pi 5 home NAS: CasaOS apps, Nur Hub and the Nur app (local AI, Fish Audio voice), a 3D-printed case and an ESP32-S3 touch screen
6,5/gün ort. +3 son gün 1 commit 1 yazar Dart 22 Eki 2026 güncellendi 9 gün önce
3d-printing casaos docker esp32-s3 fish-audio flutter home-server homelab
72
12
heterodoxin/AbliteratedOutTheBox 162
llama.cpp fork that abliterates at inference
13,5/gün ort. +2 son gün 4 commit 1 yazar C++ 21 Eki 2026 güncellendi 10 gün önce
abliteration ai inference llama-cpp llm llms
162
13
1picassoai/kraits 14
Run stock llama.cpp with the stock Unsloth Qwen3.6-35B-A3B 4-bit on a 16 GB Mac.
1,1/gün ort. +0 son gün — commit Shell 20 Eki 2026 güncellendi 8 gün önce
apple-silicon ggml gguf llama-cpp llm llm-inference local-ai local-llm
14
14
pnnnx/local-code-tutor 20
Fine-tune Qwen2.5-Coder-7B for free (QLoRA on Kaggle T4) and run a local coding agent that runs your code instead of guessing — 8 GB Mac, ll
1,4/gün ort. +0 son gün — commit Python 19 Eki 2026 güncellendi 13 gün önce
ai-agent apple-silicon coding-assistant dataset-generation fine-tuning gguf interpretability kaggle
20
15
EnamelTempoSlip/llm-arena 29
Published: 2026-10-18
1,9/gün ort. +0 son gün — commit C# 18 Eki 2026 güncellendi 16 gün önce
ai-tools benchmark blind-testing csharp dotnet elo-rating llama-cpp llm-arena
29
16
kayson-39/YishengTranslator-White 21
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. +1 son gün — commit Python 18 Eki 2026 güncellendi 15 gün önce
accessibility desktop-app gguf japanese llama-cpp pyside6 real-time speech-recognition
21
17
LoopLegendHum/token-bench 21
Published: 2026-10-19
1,4/gün ort. +0 son gün — commit C# 18 Eki 2026 güncellendi 15 gün önce
ai-tools benchmark charts csharp dotnet gpu-offload llama-cpp llm-performance
21
18
Fjordshupropagate/gguf-quant 19
Published: 2026-10-18
1,3/gün ort. +0 son gün — commit C# 18 Eki 2026 güncellendi 16 gün önce
ai-tools csharp dotnet gguf llama-cpp llm local-ai mit-license
19
19
Mergetricast/llm-box 19
Published: 2026-10-18
1,3/gün ort. +0 son gün — commit C# 18 Eki 2026 güncellendi 16 gün önce
llm local-ai ai-server ai-tools api-endpoint chat-template csharp dotnet
19
20
WalidHadri-Iron/dowse 15
Find anything on your PC by what's in it: local, private semantic search for Windows. Photos, screenshots, PDFs, documents, recordings and v
0,9/gün ort. +0 son gün — commit Python 16 Eki 2026 güncellendi 9 gün önce
desktop-app embeddinggemma embeddings file-search llama-cpp local-first multimodal privacy
15
21
FrigadeHQ/hob 432
An easier way to use AI on your own computer. A free, open-source alternative to Claude and ChatGPT that runs open-weight models like Gemma
22,7/gün ort. +17 son gün 208 commit 3 yazar TypeScript 14 Eki 2026 güncellendi 4 gün önce
ai-agent ai-assistant chatgpt-alternative claude-alternative desktop-app electron gemma gpt-oss
432
22
danbiocchi/hermes-vcc-engine 21
Instant context compaction for Hermes Agent. Builds the compaction summary in milliseconds with no LLM call, keeping the exact commands, exi
1,1/gün ort. +0 son gün — commit Python 14 Eki 2026 güncellendi 8 gün önce
ai-agents context-compression context-engineering hermes-agent hermes-plugin llama-cpp llm-agents local-llm
21
23
anisayari/sparky 64
🔒 Your private AI assistant, 100% local on Windows: chat, vision, documents (RAG), web search, images, videos with sound, voice, code projec
3,2/gün ort. +1 son gün 25 commit 1 yazar Python 13 Eki 2026 güncellendi 18 gün önce
chatgpt-alternative comfyui image-generation llama-cpp llm local-ai mcp offline
64
24
1nikitas/NIKA_desktop 34
Native AI assistant for macOS, built with SwiftUI and llama.cpp. Run local LLMs offline, work with PDFs, and create custom AI assistants. Op
1,7/gün ort. +0 son gün — commit Swift 13 Eki 2026 güncellendi 21 gün önce
ai-assistant apple-silicon desktop-app gguf llama-cpp llm local-llm macos
34
25
T-Crypt/berth 272
Berth is a lightweight GPU resource manager written in Go. It controls which applications get access to your GPU, when they get it, and how
12,4/gün ort. +7 son gün 808 commit 2 yazar Go 11 Eki 2026 güncellendi dün
comfyui golang gpu inference llama-cpp llama-swap llm local-ai
272
26
amurgola/LumaBrowser 130
Local AI desktop app: a Chromium browser with a GPU-aware llama.cpp runtime, OpenAI-compatible API, AI chat and agents, Stable Diffusion ima
5,4/gün ort. +0 son gün 15 commit 1 yazar JavaScript 09 Eki 2026 güncellendi dün
ai-agents ai-browser browser-automation chatgpt-alternative desktop-app electron gguf llama-cpp
130
27
ARahim3/DigUp 6.108
Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, bui
244,3/gün ort. +35 son gün 204 commit 12 yazar Swift 08 Eki 2026 güncellendi 8 gün önce
embeddinggemma embeddings file-search linux llama-cpp local-first macos menubar-app
6.108
28
estebanstifli/OpenDub 18
Local AI video dubbing studio with voice cloning, speech translation, speaker diarization and audio separation. Edit, preview and export dub
0,7/gün ort. +0 son gün — commit C# 07 Eki 2026 güncellendi 24 gün önce
ai-dubbing audio-separation avalonia dotnet ffmpeg indextts llama-cpp local-ai
18
29
0xPD33/commonplace 27
Offline AI research assistant for Android. Answers from Wikipedia and other reference packs on the phone, with citations. Gemma 4 runs on th
1/gün ort. +4 son gün — commit Rust 06 Eki 2026 güncellendi 10 gün önce
android edge-ai gemma grapheneos litert llama-cpp llm local-llm
27
30
lastreload/mnemonic-proxy 45
Context management proxy for AI coding agents: verbatim archive, on-demand recall, and saved engine state on supported backends.
1,6/gün ort. +1 son gün — commit Python 05 Eki 2026 güncellendi bugün
agent-memory claude-code codex coding-agents context-engineering context-management context-window kv-cache
45
31
Vkuparin/gamepause-for-local-ai 25
GamePause for Local AI: a Windows tray app that pauses LM Studio, Ollama and other local AI servers while you game, and restores them afterw
0,8/gün ort. +0 son gün — commit Rust 03 Eki 2026 güncellendi 16 gün önce
gaming llama-cpp llm lm-studio local-ai ollama rust tray-application
25
32
LivingTwice/lumen 13
Learn languages by reading and listening, just like LingQ, with a local AI. Free. Forever.
0,4/gün ort. +0 son gün — commit Rust 02 Eki 2026 güncellendi 4 gün önce
language-learning llama-cpp local-ai macos react rust tauri whisper
13
33
cobanov/PS5LM önem 34gpt6-luna uyum 25gpt6-luna 787
PS5LM, jailbreak yapılmış PS5 üzerinde llama.cpp tabanlı GGUF modellerini çalıştırmak için hazırlanmış bir homebrew payload’ıdır.
Neden yükseliyor · Bir gün yaşında 27 yıldız almış; PS5 üzerinde yerel LLM çalıştırma fikri ve gösterilebilir demo dikkat çekici. Ancak son 28 günlük commit ve farklı yazar verisi ölçülmediğinden ilginin sürdürülebilirliği ve geliştirme temposu hakkında kanıt yok.
24,6/gün ort. +18 son gün 76 commit 5 yazar C++ 01 Eki 2026 güncellendi dün
homebrew llama-cpp llm playstation-5 ps5 qwen
787
34
kouhxp/gutsy 81
Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option.
2,5/gün ort. +0 son gün 2 commit 1 yazar HTML 01 Eki 2026 güncellendi 29 gün önce
agents classifier content-moderation cpu-inference decision-model gguf intent-classification jev
81
35
sjespersen/homelab-agent 27
Started as a €70 used mini PC running an always-on AI agent (Hermes, n8n, Pi-hole, monitoring, Tailscale, encrypted backups). Now with a sec
0,8/gün ort. +1 son gün — commit Shell 01 Eki 2026 güncellendi 3 gün önce
ai-agent docker-compose hermes-agent homelab n8n pihole self-hosted tailscale
27
36
jhmeel/bigfoot 41
An assistant that lives next to your cursor on Windows. It sees your screen, talks with you, draws on things, solves the math you write, and
1,2/gün ort. +0 son gün — commit JavaScript 30 Eyl 2026 güncellendi 23 gün önce
ai-agents ai-automation electron kokoro-tts llama-cpp qwen3 qwen3-vl whisper
41
37
StartLuxLabs/StartLux-Decision 1.634
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
48,1/gün ort. +3 son gün 22 commit 2 yazar Python 29 Eyl 2026 güncellendi 11 gün önce
agents calibration classification decision-making gguf inference llama-cpp llm
1.634
38
sudiptacmd/homedroid 71
Turn an old Android phone into a home server: SSH, web hosting, Jellyfin with hardware transcoding, Immich, qBittorrent, Home Assistant and
2,1/gün ort. +0 son gün 0 commit 0 yazar Kotlin 29 Eyl 2026 güncellendi 02 Eki 2026
android android-server cloudflare-tunnel home-server homelab immich jellyfin llama-cpp
71
39
goosehouse-llc/redde 100
iPhone, iPad and CarPlay client for the Hermes AI agent or any OpenAI-compatible model. Talk or type, watch it work, approve what it runs. N
2,6/gün ort. +0 son gün 380 commit 1 yazar Swift 25 Eyl 2026 güncellendi bugün
ai-agent carplay hermes hermes-agent ios ipados llama-cpp llm
100
40
akivet/Mica 82
A 4B decision model: calibrated probabilities for yes/no, choice and score questions over long inputs.
2,2/gün ort. +1 son gün — commit Python 25 Eyl 2026 güncellendi 5 gün önce
agents decision-making decision-model gguf jev llama-cpp llm-as-a-judge qwen
82
41
FeiLiuEM/open-medical-jev 5
High-performance, high-precision, locally-fast-deployed Jev-class medical decision service on national medical exams — four readings, one ro
0,1/gün ort. +0 son gün — commit Python 25 Eyl 2026 güncellendi 28 Eyl 2026
calibration conformal-prediction gguf llama-cpp llm medical qwen routing
5
42
sennett-lau/oratype 13
OraType (formerly Typelite). Just say it. Free, open-source voice typing for macOS: speak in any app and get clean text. Runs on your comput
0,3/gün ort. — commit Rust 24 Eyl 2026 güncellendi 5 gün önce
ai dictation llama-cpp macos open-source speech-to-text tauri translation
13
43
ollaya-dev/ollaya 1.433
Jev-compatible API server for open decision models. Ollama for decision models: pull and serve 29 model families (Laya, pplx-decider, Clef,
35,8/gün ort. +2 son gün 148 commit 5 yazar Rust 23 Eyl 2026 güncellendi dün
calibration decision-model decision-models inference-server jev jev-alternative jev-compatible laya
1.433
44
dzaczek/phoneborg 14
Proof of concept: turn old Android phones into an LLM inference cluster. ADB zero-touch provisioning, llama.cpp on each phone, OpenAI-compat
0,4/gün ort. +0 son gün — commit Go 23 Eyl 2026 güncellendi 14 gün önce
adb android cluster edge-ai golang grafana inference llama-cpp
14
45
Reza2kn/Bev 12
Ternary decision scoring with Jevfire-style inference, typed APIs, and reproducible Persian evaluation.
0,3/gün ort. +0 son gün — commit Python 23 Eyl 2026 güncellendi 23 Eyl 2026
decision-making gguf llama-cpp llm persian ternary
12
46
kakushiarerukea/Deinei 18
Fully local AI companion with Long-Term Memory RAG, branch-isolated worldlines, Live2D/VRM 3D avatars, and real-time TTS for consumer GPUs (
0,4/gün ort. +0 son gün — commit TypeScript 22 Eyl 2026 güncellendi 4 gün önce
ai-companion chromadb live2d-web llama-cpp llama-cpp-gui local-llm python rag
18
47
midagedev/bloomery 54
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. +0 son gün — commit Rust 19 Eyl 2026 güncellendi dün
cuda deepseek gguf glm inference llama-cpp llm moe
54
48
NotXf1le/choosekit 24
Typed choices and probability distributions from text and images with llama.cpp, Ollama, and OpenRouter
0,5/gün ort. +0 son gün — commit JavaScript 19 Eyl 2026 güncellendi 4 gün önce
llama-cpp llm local-ai logprobs typescript
24
49
nirbhay41120003/EchoMind önem 39gpt6-luna uyum 55gpt6-luna 29
EchoMemory, konuşmaları cihazda yazıya döküp aranabilir belleğe kaydeden ve bu kayıtlar hakkında yerel bir RAG chatbot ile soru sormayı sağlayan bir uygulamadır.
Neden yükseliyor · 11 günde 68 yıldız ve son 28 günde 16 commit ile erken ilgi ve geliştirme hareketliliği var; ancak yalnızca 2 farklı yazar görülüyor. Yerel AI, gizlilik ve konuşma belleğini tek bir kullanıma hazır uygulamada birleştirmesi ilgi çekici olabilir; yıldız sayısı benimseme veya kalite kanıtı değil.
0,6/gün ort. +0 son gün — commit Python 16 Eyl 2026 güncellendi 17 Eyl 2026
accessibility hearing-assistance llama-cpp llama-cpp-python local-llm on-device-ai open-source privacy
29
50
LISK819129/OpenNPC 21
A NPC AI Framework , based on character personalities, can be used for game NPC (extendable for Godot / Unity)
0,4/gün ort. +1 son gün — commit C# 13 Eyl 2026 güncellendi 21 Eyl 2026
game-ai gamedev llama-cpp llm local-llm lora npc procedural-dialogue
21