Açık kaynak radarı

Havuz

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

repo · sayfa 1 / 1

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

AI / LLM

Tümü ai-agents 5.831 llm 4.970 mcp 4.440 claude 2.858 anthropic 1.309 openai 1.007 rag 874 agents 813 prompt-engineering 807 image-generation 712 generative-ai 400 knowledge-graph 388 text-to-speech 301 semantic-search 217 speech-recognition 176 embeddings 155 vector-search 139 llmops 112

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 vlm

1
lightseekorg/tokenspeed önem 66gpt6-luna uyum 22gpt6-luna 2.894
TokenSpeed, agentic workloads için LLM inference sunumunu hızlandırmayı ve istek yönetimini daha güvenli hale getirmeyi amaçlayan bir inference engine’dir.
Neden yükseliyor · 144 günde 2.178 yıldız ve son 28 günde 385 commit ile 20 farklı yazar, hem ilgi hem de yakın dönem geliştirme faaliyeti gösteriyor. README ayrıca PyTorch Ecosystem’e katılımı ve yeni model desteğini vurguluyor; performans iddiaları ise proje tarafından sunulan kıyaslamalara dayanıyor.
15,5/gün ort. +8 son gün 731 commit 15 yazar Python 06 May 2026 güncellendi bugün
deepseek gpt-oss kimi lightseek llm minimax qwen speed-of-light
2.894
2
OmniJev/OneJev 249
🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forw
5,8/gün ort. +5 son gün 49 commit 2 yazar Python 27 Eyl 2026 güncellendi dün
calibration computer-use decision-model gui-agent huggingface jev llm multimodal
249
3
Purewhiter/mobilegym 856
[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted A
4,8/gün ort. +2 son gün 0 commit 0 yazar Python 14 May 2026 güncellendi 5 gün önce
benchmark mobile-agent reinforcement-learning vlm agents gym llm llm-agents
856
4
baidu-baige/LoongForge 831
A high-performance framework for training LLMs, VLMs, diffusion, and embodied models on NVIDIA GPUs and Kunlun XPUs. Supports Pi0.5, GR00T
4,2/gün ort. +1 son gün 40 commit 18 yazar Python 23 Nis 2026 güncellendi 3 gün önce
llm vla vlm wan pretraining sft megatron lora
831
5
zenstory-ai/video-recap-skills 614
AI 视频解说全流程 skill 包：自动切镜头、看画面写解说词、配音合成成片，支持一键导出可编辑的剪映/CapCut 草稿，无需 GPU ｜ Agent skills that turn videos into narrated recaps & editable CapCut
3,2/gün ort. +4 son gün 9 commit 1 yazar Python 02 May 2026 güncellendi 2 gün önce
claude-code video-narration video-recap tts ai-agent asr claude-code-plugin claude-skills
614
6
taco-group/SparkVSR 748
[ECCV 2026] SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation
3,1/gün ort. +1 son gün 0 commit 0 yazar Python 16 Mar 2026 güncellendi 03 Ağu 2026
artificial-intelligence generative-ai generative-models image-processing llm machine-learning restoration super-resolution
748
7
hardrave/NIGHTRUN 304
Boot your PC straight into an LLM. Rust, UEFI-resident, no operating system underneath.
2,9/gün ort. +0 son gün 0 commit 0 yazar Rust 27 Tem 2026 güncellendi 27 Tem 2026
ai genai llama-cpp llm ollama runtime vlm
304
8
WayneChou-bot/WareTwin 158
Real-time 3D digital twin of an autonomous warehouse — 20 AMRs, deterministic simulation, explainable fleet scheduling, failure injection, V
2/gün ort. +0 son gün 0 commit 0 yazar TypeScript 22 Ağu 2026 güncellendi 11 Eyl 2026
amr digital-twin fastapi llm python react-three-fiber robotics simulation
158
9
libnyx/LT2MD 99
AI-agent skill producing reusable Markdown from PDFs. It turns flowcharts, diagrams, and charts into text beside each caption instead of emp
1,1/gün ort. +0 son gün 0 commit 0 yazar Python 14 Ağu 2026 güncellendi 23 Ağu 2026
agent-skills ai-agents codex codex-skill document-conversion llm markdown ocr
99
10
john-rocky/coreai-kit 123
Swift SDK for running chat, vision and speech models on iPhone and Mac with Apple's Core AI. Model download and caching, FoundationModels in
0,8/gün ort. +0 son gün — commit Swift 12 Haz 2026 güncellendi 4 gün önce
apple asr coreai foundation-models ios llm local-llm macos
123
11
jaeseok614/ai-hardware-fit 44
Can my GPU run this? Pick a GPU to get 3 fitting AI models, quantization, VRAM, speed ranges, and run commands. 한국어·English.
0,4/gün ort. +0 son gün — commit JavaScript 20 Tem 2026 güncellendi 7 gün önce
gpu gpu-calculator korean llama-cpp llm llm-inference local-llm ollama
44
12
walkinglabs/hands-on-world-models 34
Build world models from scratch — from perception and latent dynamics to planning, JEPA, VLA, and 3D/4D intelligence.
0,4/gün ort. +1 son gün — commit Python 12 Ağu 2026 güncellendi 03 Eyl 2026
dreamer jepa pytorch robotics vla ai deeplearning diffusion
34
13
NanoNets/nanoindex 71
Agentic RAG Harness for long documents, Tree and Graph based reasoning. Cited answers down to the pixel
0,3/gün ort. +0 son gün — commit Python 03 Nis 2026 güncellendi 15 Nis 2026
graph indexing llm ocr rag-pipeline vectorless-rag vlm vlm-ocr
71
14
InternLM/Visual-ERM 68
[NeurIPS 2026] Official Implementation of "Visual-ERM: Reward Modeling for Visual Equivalence"
0,3/gün ort. +0 son gün — commit Python 09 Mar 2026 güncellendi 23 Mar 2026
chart-understanding document-parsing large-language-models large-vision-language-models llm reward-model svg-generation vision-langauge-model
68
15
zlab-princeton/VisionFoundry 58
VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images
0,3/gün ort. +1 son gün — commit Python 02 Nis 2026 güncellendi 08 Eyl 2026
llm lmm mllm synthetic-data synthetic-dataset-generation visual-perception vlm large-language-models
58
16
MIT-RLX/rlx-models 40
ML model ports (ASR · TTS · LLM · VLM · vision · audio codecs) on the rlx multi-backend compiler + runtime — CPU/Metal/MLX/CUDA/wgpu
0,2/gün ort. +0 son gün — commit Rust 22 May 2026 güncellendi 6 gün önce
asr compiler computer-vision cuda deep-learning inference llm machine-learning
40
17
LZF1111/nullflux 38
NullFlux — 本地部署的中文 CFD / 科学计算智能体（OpenFOAM · MFIX · LBM · ParaView · 视觉核验 · 论文复现），by LZF
0,2/gün ort. +0 son gün — commit JavaScript 11 May 2026 güncellendi 3 gün önce
agent ai-agent cfd chatbot chinese-nlp computational-fluid-dynamics copilot deepseek
38
18
NativoML/JibarOS 28
Android 16 fork. AI as a platform primitive. Twelve capabilities, one shared runtime, every app. OEM-pluggable. Apache 2.0.
0,1/gün ort. +0 son gün — commit Shell 23 Nis 2026 güncellendi 06 May 2026
ai-runtime android android-16 aosp inference-runtime llm multimodal oir
28