Havuz
Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.
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
Etiketler yükleniyor…
- 51
Рейтинг VPS-хостингов по тестам сообщества: что взять под ноду, мост или бота
1,4/gün ort. +1 son gün — commit 06 Haz 2026 güncellendi 17 gün önce - 52
A counterfactual battery for instruction following in vision-language-action policies: change one word of the instruction, hold the scene, a
1,3/gün ort. +0 son gün 0 commit 0 yazar Python 17 Tem 2026 güncellendi 26 Eyl 2026 - 53
aws-bench measures how well AI agents and model combinations perform on real AWS work — diagnosing misconfigurations, provisioning infrastru
1,3/gün ort. +0 son gün 24 commit 9 yazar Python 14 Tem 2026 güncellendi dün - 54
🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery
1,2/gün ort. +1 son gün 10 commit 2 yazar Jupyter Notebook 18 Mar 2026 güncellendi 7 gün önce - 55
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
1,1/gün ort. +0 son gün — commit Python 15 Nis 2026 güncellendi 5 gün önce - 56
[EMNLP 2026] WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
1,1/gün ort. -1 son gün — commit Python 05 Haz 2026 güncellendi 22 Ağu 2026 - 57
Practical local LLM recipes and benchmarks for RTX 5060 Ti setups
1,1/gün ort. +1 son gün — commit Python 15 May 2026 güncellendi 26 gün önce - 58
Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open model
1/gün ort. +0 son gün — commit Python 19 Haz 2026 güncellendi 27 Ağu 2026 - 59
glTF 2.0 versions of common graphics research scenes
1/gün ort. +0 son gün — commit Python 13 Haz 2026 güncellendi bugün - 60
GateMem: a benchmark and evaluation toolkit for memory governance in multi-principal shared-memory LLM agents.
1/gün ort. -4 son gün — commit Python 16 Haz 2026 güncellendi 23 gün önce - 61
A benchmark for AI-driven CAD generation and editing
0,9/gün ort. +0 son gün — commit Python 27 May 2026 güncellendi 13 gün önce - 62
Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface
0,9/gün ort. +0 son gün — commit Python 15 Haz 2026 güncellendi 01 Eki 2026 - 63
Ultra-Fast Python Solutions: 110x Speed Optimization Guide 2026
0,9/gün ort. +0 son gün — commit HTML 28 Haz 2026 güncellendi bugün - 64
Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity re
0,9/gün ort. +0 son gün — commit TypeScript 02 Tem 2026 güncellendi 18 Ağu 2026 - 65
The marketplace for verifiable AI outcomes: state a task, get a fixed price upfront, and Primitive Bench routes across tools to complete it,
0,9/gün ort. +0 son gün — commit Python 17 Haz 2026 güncellendi 03 Eyl 2026 - 66
Self-healing DNS optimizer for servers in Iran. Benchmarks 60+ DNS servers, installs a local caching resolver, auto-detects Docker, and runs
0,9/gün ort. +0 son gün — commit Shell 08 Nis 2026 güncellendi 11 Eyl 2026 - 67
[NeurIPS 2026] SpatialBench: Is Your Spatial Foundation Model an All-Round Player?
0,8/gün ort. +1 son gün — commit Python 12 May 2026 güncellendi 25 Tem 2026 - 68
Anti-slop skills for AI agents: slopbeth cleans the shipped writing, slopgent cleans the conversation.
0,8/gün ort. +1 son gün — commit Python 18 Haz 2026 güncellendi 22 Tem 2026 - 69
A Benchmark for Evaluating Agent Self-Evolution on Real Business Tasks
0,8/gün ort. +1 son gün — commit Python 05 Haz 2026 güncellendi 6 gün önce - 70
📖 Data Engineering from Raw Corpora
0,8/gün ort. +0 son gün — commit TypeScript 26 Nis 2026 güncellendi 12 Haz 2026 - 71
A benchmark for evaluating LLM × harness performance.
0,7/gün ort. +0 son gün — commit Python 15 May 2026 güncellendi 03 Ağu 2026 - 72
Agent Memory Benchmark
0,7/gün ort. +2 son gün — commit Python 11 Mar 2026 güncellendi 2 gün önce - 73
AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?
0,6/gün ort. +0 son gün — commit Python 11 May 2026 güncellendi 26 gün önce - 74
🔍 The hardest search benchmark in the wild — vague, multi-turn, proactive. 200 long-horizon tasks with persona-driven progressive disclosure
0,6/gün ort. +0 son gün — commit Python 20 May 2026 güncellendi 28 May 2026 - 75
NeurIPS2026 , Scalable annotation pipeline for action-aglined fine-grained instruciton for Visual-language-Action model
0,6/gün ort. +0 son gün — commit Python 25 May 2026 güncellendi 04 Eki 2026 - 76
Benchmark AI Agents on Enterprise Workflows
0,6/gün ort. +1 son gün — commit Python 11 May 2026 güncellendi 05 Ağu 2026 - 77
State-Aware Collaboration Protocol: auditable work receipts for AI agents.
0,6/gün ort. +0 son gün — commit Python 08 May 2026 güncellendi 20 gün önce - 78
Self-evolving agentic reward framework for image-editing evaluation — 47.4% on EditReward-Bench from only 100 preference demos, no reward-mo
0,6/gün ort. +0 son gün — commit Python 14 May 2026 güncellendi 8 gün önce - 79
SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.
0,5/gün ort. +0 son gün — commit Python 16 Nis 2026 güncellendi 02 Tem 2026