Açık kaynak radarı

Havuz

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

354

repo · sayfa 1 / 8

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 benchmark

1
Interactive-Active-AI/NextTransformer 186
:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers, with compute-matched benchmarking and a plat
62/gün ort. +39 son gün 14 commit 4 yazar Python 31 Eki 2026 güncellendi bugün
auto-research benchmark deep-learning language-models linear-attention llm looped-transformer pytorch
186
2
tuotuoLyu/ForesightSafety-VLA 87
Official code for ForesightSafety-VLA (IROS 2026): a unified diagnostic safety benchmark for vision-language-action models on RoboTwin
17,4/gün ort. +0 son gün 1 commit 1 yazar Python 29 Eki 2026 güncellendi 5 gün önce
benchmark embodied-ai iros2026 robot-safety robotics robotwin safety-evaluation vision-language-action
87
3
Wiselnn570/Co-Design-Bench 70
Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models
11,7/gün ort. +16 son gün 5 commit 1 yazar Python 28 Eki 2026 güncellendi 6 gün önce
agentic agentic-coding benchmark reference-free verifier webdev webdevelopment
70
4
eval-sys/ibench 22
Interaction Bench: Benchmarked on what users feel
3,1/gün ort. +0 son gün — commit Python 27 Eki 2026 güncellendi 4 gün önce
agent benchmark
22
5
NEETnina/dsh-model-master 14
dsh-model-master（模型选择大师）— model selector for DeepSeek Harness: search across providers, probe any model with a real streaming request to mea
1,8/gün ort. +1 son gün — commit JavaScript 26 Eki 2026 güncellendi 3 gün önce
deepseek-harness dsh dsh-plugin model-selector artificial-analysis benchmark deepseek developer-tools
14
6
VictoriaMetrics/logs-benchmark 13
Reproducible benchmark that compares VictoriaLogs, Loki, Elasticsearch, OpenSearch, SigNoz and ClickStack
1,6/gün ort. +0 son gün — commit Go 26 Eki 2026 güncellendi 6 gün önce
benchmark clickhouse clickstack elasticsearch kubernetes logs loki opensearch
13
7
HexaFuture/EmbodiedLab 17
Manipulation benchmarks test acting to change; EmbodiedLab tests acting to know. Given only an objective and the apparatus, a robot runs its
1,5/gün ort. +0 son gün — commit Python 23 Eki 2026 güncellendi 7 gün önce
ai-for-science benchmark embodied-ai isaac-sim llm-agents physics-simulation robot-manipulation robotics
17
8
alleyxd/quantpicker 15
Measures which GGUF quant of a model to run on your GPU: real speed and quality loss (KL divergence), not estimates.
1,4/gün ort. +0 son gün — commit Rust 23 Eki 2026 güncellendi 6 gün önce
benchmark gguf llama-cpp llm local-llm quantization rust
15
9
allenai/novelty-eval 16
Benchmark and controlled study of LLM-based novelty judges for research ideas. Code and data for "Old Ideas, Novel Problems" (arXiv 2610.020
1,3/gün ort. +0 son gün — commit Python 22 Eki 2026 güncellendi 8 gün önce
ai-for-science ai-scientist benchmark dataset ideation llm-as-judge llm-evaluation novelty-detection
16
10
modulate-ai/speech-to-text-benchmark 51
Reproducible speech-to-text benchmark: WER, latency and cost for Velma, Deepgram, AssemblyAI, Chirp 3, MAI-Transcribe 2, Moonshine and whisp
3,9/gün ort. +12 son gün 5 commit 3 yazar Python 21 Eki 2026 güncellendi 6 gün önce
asr benchmark speech-recognition speech-to-text transcription velma wer
51
11
dolev31/lasagna 32
Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augment
2,5/gün ort. +2 son gün — commit Python 21 Eki 2026 güncellendi bugün
ablation-study agentic-rag beir benchmark evaluation hybrid-search information-retrieval llm
32
12
xuyicheng-zju/TARSphere 28
A robot-oriented full-stack framework for long-horizon embodied agents in evolving physical and social environments.
2,2/gün ort. +2 son gün — commit Python 21 Eki 2026 güncellendi 8 gün önce
benchmark embodied-ai isaac-sim robotics
28
13
ScottDuncanAI/HistorianRCA 32
HistorianRCA: a root cause analysis benchmark. 90 days of simulated plant historian data from a steam-heated hold tank, with hidden faults t
2,3/gün ort. +1 son gün — commit 20 Eki 2026 güncellendi 14 gün önce
anomaly-detection benchmark chemical-engineering dataset fault-diagnosis process-control root-cause-analysis time-series
32
14
agentvfs/vfs-bench 17
The Virtual Filesystem Interface for AI Agents
1,2/gün ort. +1 son gün — commit Python 20 Eki 2026 güncellendi bugün
agentic-ai agents cli vfs benchmark llm virtual-filesystem
17
15
P90-RushB/robopaint-bench 52
A robot-painting benchmark for multimodal language models: reference images, text prompts, and custom goals. Built on AgentArk.
3,3/gün ort. +0 son gün — commit Jupyter Notebook 18 Eki 2026 güncellendi 6 gün önce
agentark benchmark embodied-ai multimodal robotics simulation
52
16
cmu-l3/reuF2F 25
Benchmarking coding agents on formalized undergraduate research problems
1,6/gün ort. +0 son gün — commit Lean 18 Eki 2026 güncellendi 9 gün önce
benchmark coding-agent formal-verification
25
17
skbskhud/p104-gen2-unlock 43
P104-100 (GP104) PCIe Gen2 x4 unlock tool for Windows. Gen1 x4 -> Gen2 x4: 0.78 -> 1.55 GB/s measured.
2,5/gün ort. +0 son gün — commit C# 17 Eki 2026 güncellendi 2 gün önce
benchmark cryptomining gpu hardware-hacking mining-gpu nvidia p104 pascal
43
18
Tencent-Hunyuan/DiagSafe 33
DiagSafe: diagnostic LLM safety benchmark with prompt-level rubrics (3,489 bilingual prompts, 84-label taxonomy)
1,7/gün ort. +0 son gün — commit Python 15 Eki 2026 güncellendi dün
benchmark bilingual dataset jailbreak llm-as-a-judge llm-evaluation llm-safety red-teaming
33
19
StartLuxLabs/DecisionPivot 152
DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with
7,6/gün ort. +0 son gün 2 commit 1 yazar Python 14 Eki 2026 güncellendi 13 gün önce
benchmark calibration decision-making evaluation llm llm-evaluation selective-prediction
152
20
AutoResearch-Factory/SciPIvot 13
SciPIvot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents
0,7/gün ort. +0 son gün — commit Python 14 Eki 2026 güncellendi 15 gün önce
ai-for-science ai-scientist benchmark dataset evaluation llm-agents reasoning scientific-research
13
21
composo-ai/DishwasherBench 73
A dishwasher-loading game on a physical simulation of one real machine, built to benchmark language models and playable in a browser. The ga
3,3/gün ort. +0 son gün 20 commit 3 yazar TypeScript 12 Eki 2026 güncellendi 17 gün önce
ai-agents benchmark evaluation game llm llm-benchmark mcp physics-simulation
73
22
cloudishai/ai-deploy-bench 16
Benchmark of AI coding agents building web apps and deploying them to Cloudish, DigitalOcean, Render and Vercel, measuring success, time, to
0,7/gün ort. +0 son gün — commit Python 12 Eki 2026 güncellendi 7 gün önce
ai-agents ai-benchmark anthropic benchmark claude claude-code cloud-deployment cloudish
16
23
ENE4S/Optiscaler-ILION 14
OptiScaler ILION — Community fork with bilingual ES/EN interface, FSR 4 version switching, live performance metrics and benchmarking tools.
0,6/gün ort. -1 son gün — commit C++ 12 Eki 2026 güncellendi 22 gün önce
amd benchmark frame-generation fsr4 gaming modding optiscaler upscaling
14
24
YuyaoGe/doc2harness 116
Official Code for the paper "Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents "
5/gün ort. +0 son gün 3 commit 1 yazar Python 11 Eki 2026 güncellendi 7 gün önce
agent benchmark harness llm llm-agents
116
25
DarkHater01/slopbench 15
Measures how much code LLM agents waste. 5 tasks, sandboxed, weekly snapshots, contestable references.
0,6/gün ort. +0 son gün — commit JavaScript 10 Eki 2026 güncellendi dün
ai-agents benchmark code-quality developer-tools evaluation llm minimalism
15
26
Aixio-AI/aixio-layer-v2 348
Aixio Layer v2 recovers editable layers from flat designs where possible. 150-design benchmark vs Canva Magic Layers, Qwen-Image-Layer and G
13,9/gün ort. +15 son gün 3 commit 1 yazar 09 Eki 2026 güncellendi 25 gün önce
ai-design benchmark image-to-layers layer-decomposition pptx
348
27
VectorSpaceLab/InfoVis 42
Official code for InfoVis: one 9B model for slide image generation and editing, with the VisSlideBench benchmark and 15M+ training records.
1,7/gün ort. +0 son gün — commit Python 09 Eki 2026 güncellendi 20 gün önce
benchmark diffusion-models flux image-editing image-generation multimodal presentation slide-generation
42
28
como-votam/teor 30
Benchmark aberto de LLMs para o processo legislativo brasileiro
1,2/gün ort. +0 son gün — commit Python 09 Eki 2026 güncellendi 4 gün önce
benchmark civic-tech inspect-ai legislative llm open-data portuguese
30
29
ZJU-REAL/WorldMemBench 21
WorldMemBench: A Comprehensive Benchmark for Memory of Video World Models
0,8/gün ort. +0 son gün — commit Python 09 Eki 2026 güncellendi 19 gün önce
benchmark memory world-model
21
30
google-research/ple 18
Physical-Engineering’s Last Exam
0,7/gün ort. +1 son gün — commit Python 09 Eki 2026 güncellendi dün
benchmark physical-ai
18
31
worldbench/Orbia 62
🔥 Orbia: Do Generated Videos Form a Consistent 3D World?
2,4/gün ort. +0 son gün 7 commit 3 yazar Python 08 Eki 2026 güncellendi 4 gün önce
3d 4d video-generation world-model world-modeling 3d-world-model aigc generation
62
32
pipelinelabai/paperbench-expanded 49
PaperBench High-Difficulty and Expanded Tasks: paper reproduction beyond machine learning. 93 tasks in 12 research areas, run in domain-nati
1,9/gün ort. +0 son gün — commit Python 08 Eki 2026 güncellendi 25 gün önce
ai-agents benchmark harbor llm-evaluation reproducibility scientific-computing
49
33
VectorSpaceLab/AgentSWE 45
Can coding agents build the agent you actually want? A benchmark of 25 agent software engineering tasks across creation, editing and optimiz
1,7/gün ort. +0 son gün — commit Python 08 Eki 2026 güncellendi 21 gün önce
agent-evaluation benchmark coding-agents llm-agents software-engineering
45
34
MegaTroll222/edit-drift 15
How much does an image model change what you told it to leave alone? Chained-edit benchmark for image models + installable scorer and Claude
0,6/gün ort. +0 son gün — commit Python 07 Eki 2026 güncellendi 26 gün önce
benchmark claude-code evaluation flux generative-ai image-editing image-generation nano-banana
15
35
deeplethe/fde-gym 113
The online judge for the LLM era. Every case is a real customer delivery: you work it with a coding agent, and your system is judged once it
4/gün ort. +2 son gün 25 commit 1 yazar TypeScript 06 Eki 2026 güncellendi 5 gün önce
agent-evaluation ai-agents benchmark coding-agent docker forward-deployed-engineer llm online-judge
113
36
alaintural/synctile-h3 13
MiniMax H3: 4.9x faster local generation and seam-free 4K via synchronized tiles (SyncTile). Benchmarks included.
0,5/gün ort. +0 son gün — commit Python 06 Eki 2026 güncellendi 28 gün önce
4k benchmark comfyui local-ai minimax-h3 multidiffusion upscaling video-generation
13
37
AetherLabsAI/Video2World 234
Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos - Rethinking Embodied Real2Sim from a Software Engineering Pe
8,1/gün ort. +7 son gün 6 commit 2 yazar Python 05 Eki 2026 güncellendi 15 gün önce
benchmark coding-agent embodied-ai foundation-models real-to-sim robot-learning robotics simulation
234
38
bottomless/agent-duel 31
Blinded battles between coding agents: two agents, one prompt, you pick the winner. Desktop app, runs locally.
1,1/gün ort. +1 son gün — commit TypeScript 05 Eki 2026 güncellendi bugün
ai-agents benchmark coding-agents desktop-app developer-tools electron llm
31
39
cocel-postech/NarrowWide 26
NarrowWide: A LiDAR-inertial dataset with repeated transitions between confined and open spaces (IEEE T-FR 2026)
0,9/gün ort. +0 son gün — commit 05 Eki 2026 güncellendi 27 gün önce
benchmark dataset disaster imu indoor indoor-outdoor lidar lidar-inertial-odometry
26
40
keegan0521/AnyFlow 14
AnyFlow - flow-matching video generation: training, inference and VBench evaluation for t2v and i2v models.
0,5/gün ort. +0 son gün — commit Python 05 Eki 2026 güncellendi 13 gün önce
benchmark diffusion-models flow-matching generative-ai image-to-video inference llm python
14
41
Folkbench/folkbench 4.273
AI API 中转站评测排行与切换工具：实测可用率、延迟与价格 · Open-source AI API relay benchmark, rankings & switcher for Claude Code / Codex
133,5/gün ort. +93 son gün 58 commit 5 yazar Rust 02 Eki 2026 güncellendi 2 gün önce
ai api-relay api-relay-pricing benchmark benchmarks llm model-evaluation reliability
4.273
42
facebookresearch/swe-sweep önem 50gpt6-luna uyum 27gpt6-luna 217
SWE-sweep, agent'ların büyük kod tabanlarındaki konumu ve türü önceden belirtilmeyen birden fazla bug'ı bulup düzeltebilmesini ölçen bir benchmark'tır.
Neden yükseliyor · 1 günlük, 33 yıldızlı yeni bir Facebook Research benchmark'ı olması ve LLM agent değerlendirmesine yönelik güncel bir soruyu ele alması dikkat çekebilir. Ancak yükselişin kesin nedeni bilinmiyor; son 28 günlük commit ve farklı yazar verisi ölçülmemiş.
6,6/gün ort. +1 son gün 0 commit 0 yazar Python 01 Eki 2026 güncellendi 2 gün önce
ai ai-agents benchmark benchmarking harbor harbor-framework llm llm-benchmark
217
43
SimuVerity/SimuVerity 21
SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation
0,6/gün ort. +0 son gün — commit MATLAB 01 Eki 2026 güncellendi 29 gün önce
ai-agents benchmark llm-agents matlab model-generation simulink
21
44
PKU-VaLuE-Lab/EmbodiedCLBench 18
Official code for EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents.
0,5/gün ort. +0 son gün — commit Python 01 Eki 2026 güncellendi 22 gün önce
benchmark continual-learning embodied-agent embodied-ai self-evolution self-evolving self-evolving-agents
18
45
Lingikaushikreddy/indicorderbench 10
Catches multilingual voice agents placing the wrong order. τ-bench style benchmark + CI gate for voice ordering agents in English and Hingli
0,3/gün ort. +0 son gün — commit Python 01 Eki 2026 güncellendi 15 gün önce
benchmark ci conversational-ai evaluation function-calling hindi hinglish indic-languages
10
46
Chengjun023/agent-smith önem 44gpt6-luna uyum 34gpt6-luna 9
Agent Smith, Codex görevleri için yerel model yönlendirmesi, macOS kullanım izleme arayüzü ve tekrarlanabilir benchmark araçları sunuyor.
Neden yükseliyor · Altı günde 194 yıldız alması dikkat çekici; yerel model routing, görünür kullanım takibi ve benchmark sonuçlarını tek projede birleştirmesi ilgi çekmiş olabilir. Ancak bu erken ilgi benimseme kanıtı değil: son 28 günde 5 commit ve 1 farklı yazar var.
0,3/gün ort. +0 son gün — commit Python 30 Eyl 2026 güncellendi 01 Eki 2026
ai-agents benchmark codex cost-optimization llm-routing local-first macos swiftui
9
47
stanford-iris-lab/ScholarCatalyst 39
A Benchmark for Retrieving Papers that Inspire New Research
1,1/gün ort. +1 son gün — commit Python 29 Eyl 2026 güncellendi 02 Eki 2026
benchmark retrieval scientific-discovery
39
48
zhangruotian/SalArt-VQA 21
Evaluation code for SalArt-VQA: Diagnosing Whether VLMs Understand Salient Artifacts in Generated Images (NeurIPS 2026).
0,6/gün ort. +0 son gün — commit Python 29 Eyl 2026 güncellendi 18 gün önce
benchmark neurips2026 vision-language-models visual-question-answering
21
49
JoaquinRuiz/medula 13
Several coding agents, one repo, at the same time: a reproducible lab to measure how they coordinate, and Médula, a kernel that decides who
0,4/gün ort. +0 son gün — commit Python 29 Eyl 2026 güncellendi 02 Eki 2026
agent-coordination ai-agents anthropic benchmark calibration claude-code coding-agents concurrency
13
50
keta1930/what-the-jev 13
What can Jev actually do? Reproducible experiments and research reports exploring its capabilities and limits.
0,4/gün ort. +0 son gün — commit Python 29 Eyl 2026 güncellendi 11 gün önce
benchmark decision-model decision-models evals jev jev-ai jev-model llm-evaluation
13