Açık kaynak radarı

Havuz

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

repo · sayfa 1 / 2

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 nvidia

1
T-Crypt/berth 287
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
11,5/gün ort. +0 son gün +10,8 son 15g 808 commit 2 yazar Go 11 Eki 2026 güncellendi 2 gün önce
comfyui golang gpu inference llama-cpp llama-swap llm local-ai
287
2
NVIDIA/NemoClaw önem 66gpt6-luna uyum 27gpt6-luna 22.950
NVIDIA NemoClaw, OpenClaw, Hermes ve LangChain Deep Agents Code ajanlarını NVIDIA OpenShell sandbox’larında çalıştırmak için kurulum, inference yönetimi ve güvenlik politikaları sağlayan bir stack’tir.
Neden yükseliyor · 196 günde 22 bini aşan yıldız ve son 28 gündeki 751 commit ile 20 farklı yazar, güçlü ilgi ve yüksek geliştirme temposuna işaret ediyor. Agent güvenliği güncel ve gerçek bir ihtiyaç; NVIDIA markası ile birden fazla agent entegrasyonu da görünürlüğünü artırıyor. Ancak bu ölçüler tek başına üretim olgunluğunu veya güvenlik etkinliğini kanıtlamaz.
97,7/gün ort. +20 son gün +9,6 son 30g 315 commit 20 yazar TypeScript 15 Mar 2026 güncellendi bugün
ai-agents nvidia openclaw openshell sandboxing typescript hermes deep-agents
22.950
3
akivajp/rigtop 53
System monitor for workstations, laptops and NAS — terminal UI and native GUI, many hosts over SSH. A btop alternative.
4,1/gün ort. +2 son gün +3,9 son 8g 206 commit 1 yazar Rust 23 Eki 2026 güncellendi bugün
btop btop-alternative btrfs egui gpu linux nvidia raid
53
4
skbskhud/p104-gen2-unlock 45
P104-100 (GP104) PCIe Gen2 x4 unlock tool for Windows. Gen1 x4 -> Gen2 x4: 0.78 -> 1.55 GB/s measured.
2,4/gün ort. +1 son gün +3,6 son 8g — commit C# 17 Eki 2026 güncellendi 4 gün önce
benchmark cryptomining gpu hardware-hacking mining-gpu nvidia p104 pascal
45
5
Freim32/vllmops 101
Self-hosted vLLM made simple. Git-friendly YAML for models and profiles, full lifecycle from an intuitive CLI and TUI.
0,7/gün ort. +0 son gün +2,7 son 29g — commit Python 18 Haz 2026 güncellendi 02 Eki 2026
cli gpu inference llm local-llm mlops model-serving nvidia
101
6
meshapplied/goethe 44
Serve your models fast on your own infra in 3 steps.
1,6/gün ort. +0 son gün +2,4 son 8g — commit Rust 08 Eki 2026 güncellendi 3 gün önce
gpu inference llm nvfp4 nvidia openai-api self-hosted sglang
44
7
DevDock-AI/Speedy 32
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
8/gün ort. +5 son gün +2,3 son 3g 71 commit 9 yazar C++ 01 Kas 2026 güncellendi bugün
cuda inference llm long-context mixture-of-experts multi-gpu qwen rtx-3080
32
8
EvgenRublev/Minimax_Studio 44
Локальная студия генерации кинематографичных видео со звуком на MiniMax H3 — Windows, NVIDIA GPU, полностью offline.
3,7/gün ort. +2 son gün +2,1 son 8g 102 commit 1 yazar TypeScript 24 Eki 2026 güncellendi bugün
comfyui electron local-ai minimax minimax-h3 nextjs nvidia text-to-video
44
9
arcships/light-ocr 655
Fast, offline OCR for Node.js & C++. PP-OCRv6 with Core ML / WebGPU hardware acceleration — recognize text in images with confidence scores
5,7/gün ort. +1 son gün +2 son 30g 1 commit 1 yazar C++ 14 Tem 2026 güncellendi 28 gün önce
apple-silicon computer-vision coreml cpp17 d3d12 image-processing machine-learning napi
655
10
aiptimizer/TurboOCR 1.155
TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC
5/gün ort. +3 son gün +1,7 son 30g 0 commit 0 yazar C++ 20 Mar 2026 güncellendi 27 Eyl 2026
document-parsing fastapi fp16 grpc ocr paddleocr pdf-extraction rag
1.155
11
Deen-Media/dgx-monarch 54
Distributed image and video generation in ComfyUI for two NVIDIA DGX Sparks.
2/gün ort. +0 son gün +1,7 son 24g — commit Python 09 Eki 2026 güncellendi bugün
comfyui dgx-spark diffusion-models distributed-inference gb10 image-generation nvidia video-generation
54
12
NVIDIA-NeMo/nemo-helix 137
NeMo Helix: Make the agents you ship faster, more accurate, and safer.
0,8/gün ort. +1 son gün +1,6 son 17g — commit Python 14 May 2026 güncellendi bugün
agent-evaluation ai-agents guardrails kubernetes llm llmops nemo nvidia
137
13
hasso5703/alzeo 246
dgx-spark-qwen38 is an open-source installer that turns an NVIDIA DGX Spark, or any GB10 machine (ASUS, Dell, HP, Lenovo, MSI, GIGABYTE, Ace
3/gün ort. +1 son gün +0,9 son 18g 625 commit 1 yazar Python 15 Ağu 2026 güncellendi bugün
ai-agents asus-ascent-gx10 dgx-spark gb10 image-generation llm-inference local-ai local-llm
246
14
Lowaltitudeflight/local-llm-tuning-guide 29
A decision library for running local LLMs on multi-GPU machines without NVLink: parallelism, communication, quantization, speculative decodi
1,5/gün ort. +0 son gün +0,9 son 18g — commit Python 16 Eki 2026 güncellendi dün
benchmarking decision-guide gpu-serving inference-optimization kv-cache llm llm-deployment llmops
29
15
AbdoKnbGit/tau 425
Your adaptive AI agent for your work.
2/gün ort. -1 son gün +0,8 son 30g 95 commit 1 yazar TypeScript 04 Nis 2026 güncellendi dün
agent anthropic antigravity api claudecode cli copilot free
425
16
yanfei0725/dsh-qwen-paint 32
面向 DeepSeek Harness 的本地图像生成插件（优化版）：经本机 ComfyUI 调用 Qwen-Image 2.1 生成图像，全部流量限于 127.0.0.1。本版增强推理性能、NVIDIA/Intel/AMD 显卡适配与 Windows/Linux 兼容。原作者
1,2/gün ort. +1 son gün +0,8 son 19g — commit JavaScript 10 Eki 2026 güncellendi 16 gün önce
amd-rocm comfyui cross-platform deepseek-harness dsh-plugin gpu-acceleration image-generation intel-arc
32
17
5p00kyy/club-5060ti 197
Practical local LLM recipes and benchmarks for RTX 5060 Ti setups
1,1/gün ort. +2 son gün +0,7 son 30g — commit Python 15 May 2026 güncellendi 27 gün önce
benchmark cuda ik-llama-cpp llama-cpp vllm blackwell nvidia qwen
197
18
ngthaihoc/CMP30HXmodtoGEN2 68
This project is inspired by CMP40HX-Unlock. If you find it useful, please consider giving a star to both the original author and this reposi
1,5/gün ort. +0 son gün +0,7 son 30g — commit Go 20 Eyl 2026 güncellendi 11 gün önce
cmp developer-tools leagueoflegends linux mining nvidia nvidia-gpu riot-games
68
19
Somnusochi/VLM-AutoYOLO 275
AI Auto Annotation & YOLO Training Pipeline, End-to-end object detection auto-labeling and YOLO training platform. VLM-powered annotation wi
1,8/gün ort. +0 son gün +0,6 son 30g 0 commit 0 yazar Python 02 Haz 2026 güncellendi 22 Eyl 2026
auto-labeling computer-vision data-annotation deep-learning fastapi locate-anything machine-learning nvidia
275
20
SikamikanikoBG/homelab-monitor 231
Self-hosted homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, energy costs. Read-only MCP server so AI agents can ex
1,4/gün ort. +0 son gün +0,6 son 30g 13 commit 2 yazar Python 25 May 2026 güncellendi dün
docker gpu homelab monitoring nvidia self-hosted vram ai-infrastructure
231
21
moezdil/siltide 36
Terminal fleet monitor for GPUs, NPUs, and 13 other accelerator kinds, from utilization down to which pod is using them.
0,7/gün ort. +0 son gün +0,6 son 29g — commit Go 16 Eyl 2026 güncellendi 3 gün önce
accelerators amd apple-silicon cli go gpu kubernetes monitoring
36
22
Han-DongHeun/nvmon 34
A fancy NVIDIA GPU monitor for the terminal. One Python file, no dependencies.
0,9/gün ort. +0 son gün +0,6 son 22g — commit Python 28 Eyl 2026 güncellendi 4 gün önce
btop cli deep-learning gpu monitoring nvidia nvml python
34
23
pantheongpu/pantheonsim 18
PantheonSim: GPU simulator for CUDA and ROCm. Run CUDA and HIP programs unmodified on a CPU, no GPU needed: simulated NVIDIA and AMD GPUs fo
0,3/gün ort. +0 son gün +0,5 son 11g — commit C++ 01 Eyl 2026 güncellendi bugün
amd ci cuda cuda-simulator emulator github-actions gpu gpu-programming
18
24
niklasfrick/spark-dashboard 140
Real-time hardware and LLM inference monitoring — GPU, CPU, memory, and vLLM metrics streamed to a dashboard.
0,7/gün ort. -1 son gün +0,4 son 30g — commit TypeScript 20 Nis 2026 güncellendi 19 gün önce
dashboard dgx metrics nvidia observability spark vllm ai
140
25
ttlequals0/Audicle 104
Your reading list, as a podcast you own
0,6/gün ort. +0 son gün +0,4 son 30g 51 commit 1 yazar Python 25 May 2026 güncellendi 10 gün önce
ai audiobook llm podcast tts media nvidia ollama
104
26
BUNNY-19C/DLSSG-30s-manager 52
RTX 30 系 DLSS 帧生成管理器：按游戏部署 dlssg_for_sm86，一键恢复，自动检测内核级反作弊 | DLSS frame generation manager for RTX 30 series: per-game deployment of dlssg_fo
0,9/gün ort. +0 son gün +0,4 son 30g — commit C# 10 Eyl 2026 güncellendi 9 gün önce
anti-cheat csharp dlss dlss-frame-generation dlssg dotnet frame-generation game-mod
52
27
joeynyc/spark-doctor 166
Local diagnostic CLI for NVIDIA DGX Spark (GB10). Detects power caps, UMA pressure, thermal risk, CUDA 13/SM_121 wheel mismatches, Docker is
0,9/gün ort. +0 son gün +0,3 son 30g — commit Python 24 Nis 2026 güncellendi 14 gün önce
cli dgx dgx-spark diagnostics gb10 grace-blackwell llama-cpp local-llm
166
28
ianalloway/solvent-agent 114
Offline-first Python AI agent that runs a tiny research business: quotes each job against its own costs, collects via Stripe, fulfils with N
0,8/gün ort. +1 son gün +0,3 son 30g — commit Python 17 Haz 2026 güncellendi dün
agentic-ai ai-agent ai-agents autonomous-agents cli fastapi fintech guardrails
114
29
OneYoungMean/KimodoUnityBridge 114
Free Local Unity AI Motion Generate Tool.Based By Nvlab Kimodo.
0,7/gün ort. +1 son gün +0,3 son 30g — commit C# 19 May 2026 güncellendi 3 gün önce
ai animation motion nvidia unity kimodo
114
30
surya-koritala/condor 34
Qwen3.8-Flash-Next (180B MoE) on one 12-16 GB NVIDIA GPU, Linux or Windows. Own engine, own compression.
1,5/gün ort. +0 son gün +0,3 son 15g — commit Python 14 Eki 2026 güncellendi 15 gün önce
cuda inference linux llm local-llm mixture-of-experts nvidia qwen
34
31
vuplea/simple-nvidia-undervolt 33
Overclock or undervolt your NVIDIA RTX GPU from the command line — a no-background-process MSI Afterburner alternative for Windows.
0,2/gün ort. +1 son gün +0,3 son 30g — commit C# 21 Haz 2026 güncellendi 04 Eyl 2026
cli geforce gpu gpu-tuning msi-afterburner nvapi nvidia overclocking
33
32
anakronox/spark-dash 16
A dashboard for a home cluster of NVIDIA GB10 (DGX Spark / ASUS GX10) inference servers: GPU and system health, plus live per-model metrics
0,2/gün ort. +0 son gün +0,3 son 11g — commit Python 22 Ağu 2026 güncellendi 4 gün önce
dashboard dgx-spark gb10 grafana homelab llama-cpp monitoring nvidia
16
33
gammahazard/locate-anything 170
Sleek, mobile-friendly web UI for NVIDIA LocateAnything-3B — open-vocabulary object detection & grounding on your own GPU, via one docker co
1/gün ort. +0 son gün +0,2 son 30g 0 commit 0 yazar TypeScript 27 May 2026 güncellendi 11 Eyl 2026
bounding-boxes computer-vision cuda docker fastapi gpu grounding machine-learning
170
34
devarshishimpi/codra 124
Self-hosted AI code review for GitHub pull requests.
0,6/gün ort. +0 son gün +0,2 son 30g — commit TypeScript 11 Nis 2026 güncellendi 2 gün önce
ai-agents ai-code-review code-review codra pr-intelligence pr-review ai-pr-review cloudflare
124
35
Devansh-365/freellm 70
OpenAI-compatible gateway aggregating 8 free LLM providers with automatic failover, circuit breakers, and smart routing. 32+ models, zero c
0,3/gün ort. +2 son gün +0,2 son 30g — commit TypeScript 03 Nis 2026 güncellendi 29 May 2026
api-gateway cerebras circuit-breaker free-api gemini groq llm llm-gateway
70
36
stevibe/SparklingKit 69
Local-first AI workbench for OCR, transcription, translation, image generation, mind maps and composable workflows. Built for DGX Spark.
1/gün ort. +0 son gün +0,2 son 30g — commit TypeScript 31 Ağu 2026 güncellendi 02 Eyl 2026
ai-workflows dgx-spark llm local-ai nvidia ocr react self-hosted
69
37
timothystewart6/vllm-gb10 60
Production-ready, bleeding-edge, upstream-first vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a), verified against real models on
0,4/gün ort. +0 son gün +0,2 son 30g — commit Python 20 May 2026 güncellendi dün
arm64 cuda dgx-spark docker gb10 inference llm nvidia
60
38
MauroDruwel/NIMStats 58
📊 Automated hourly benchmarks for 20+ NVIDIA NIM models — interactive dashboard, zero infra, self-hostable. Open-source & community-driven.
0,3/gün ort. +0 son gün +0,2 son 30g — commit JavaScript 27 Nis 2026 güncellendi bugün
ai benchmark dashboard github-actions llm machine-learning nim nvidia
58
39
SemiAnalysisAI/InferenceX-app 51
Dashboard for InferenceX™, Open Source Continuous Inference | InferenceX 仪表板
0,2/gün ort. +1 son gün +0,2 son 30g — commit TypeScript 11 Mar 2026 güncellendi bugün
agi amd benchmarking cuda deepseek llm nvidia reactjs
51
40
alphastorm/omp-ninfer 48
Durable local inference for Oh My Pi: NInfer + Qwen3.8 27B on one RTX 3090/4090/5090, with restart-resumable OpenAI Responses state.
0,7/gün ort. +1 son gün +0,2 son 30g — commit Python 27 Ağu 2026 güncellendi bugün
ai-agent coding-agent coding-assistant cuda directstorage local-ai local-llm nvidia
48
41
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. +0 son gün +0,2 son 30g — commit Python 27 May 2026 güncellendi dün
benchmarking cuda fastapi gguf llama-cpp llm lm-evaluation-harness machine-learning
47
42
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 +0,2 son 30g — commit Python 07 Ağu 2026 güncellendi dün
diagnostics exl3 gguf gptq llama-cpp llm low-resource mac
33
43
ClaireMoonlit/codex-nvidia-proxy 30
让 Codex 白嫖 NVIDIA 免费顶级模型，一键接入 | Transparent proxy between Codex and NVIDIA NIM — use NVIDIA's free hosted top-tier models with Codex
0,2/gün ort. +0 son gün +0,2 son 30g — commit JavaScript 18 May 2026 güncellendi 12 gün önce
ai-coding codex deepseek glm llm minimax nim nvidia
30
44
NVDLI/NemoClawDLI 27
Free NVIDIA DLI course: build, coordinate, and secure AI agents with NemoClaw and OpenShell. Browser-based, no GPU required. Available in En
0,2/gün ort. +0 son gün +0,2 son 30g — commit Python 03 Tem 2026 güncellendi dün
agent-security ai-agents free-course llm-security nemoclaw nvidia nvidia-dli openclaw
27
45
TheAiSingularity/hermesclaw 74
Hermes Agent (NousResearch) sandboxed by NVIDIA OpenShell — hardware-enforced network/filesystem/syscall policy, full memory + gateway stack
0,3/gün ort. +0 son gün +0,1 son 30g — commit Shell 30 Mar 2026 güncellendi 24 Nis 2026
ai-agent docker hermes llama-cpp llm nemoclaw nvidia openclaw
74
46
calico88x/DGX-Model-Manager 57
Browser-based model and inference management for NVIDIA DGX Spark - inventory local and Hugging Face models, manage Ollama and LiteLLM, gene
0,3/gün ort. +0 son gün +0,1 son 30g — commit Python 01 Nis 2026 güncellendi 18 gün önce
ai dgxspark gb10 llm model-deployment nvidia python
57
47
botAGI/AGmind 50
Legacy: self-hosted LLM/RAG stack installer for DGX Spark (arm64). The work continued as AGmind Systems Lab — measured local-LLM performance
0,2/gün ort. +1 son gün +0,1 son 30g — commit Shell 13 Mar 2026 güncellendi 27 Tem 2026
ai-stack dify docker gpu open-webui self-hosted vllm ai
50
48
parallelArchitect/sparkview 36
Operator-grade GPU monitor for NVIDIA GPUs with native GB10 / DGX Spark coherent UMA support — PSI pressure, clock detection, ConnectX-7 net
0,2/gün ort. +1 son gün +0,1 son 30g — commit Python 17 Nis 2026 güncellendi 31 May 2026
cuda dgx-spark gb10 gpu monitoring nvidia psi python
36
49
joeynyc/spark-image-lab 33
Local image generation and editing for NVIDIA DGX Spark, powered by Qwen-Image-2.1 and Gradio.
0,7/gün ort. +0 son gün +0,1 son 30g — commit Python 20 Eyl 2026 güncellendi 21 Eyl 2026
dgx-spark gb10 gradio image-editing image-generation local-ai nvidia python
33
50
aivrar/multi-turboquant 30
Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity simula
0,1/gün ort. +0 son gün +0,1 son 30g — commit Python 10 Nis 2026 güncellendi 26 gün önce
attention compression cuda deep-learning gpu inference kv-cache llama-cpp
30