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 reinforcement-learning

1
datamllab/HarborRL 127
An end-to-end framework for Agentic Reinforcement Learning.
5,1/gün ort. +13 son gün +11,6 son 7g 16 commit 3 yazar Python 12 Eki 2026 güncellendi 7 gün önce
agent agent-framework agentic agentic-ai agentrl coding-agent coding-agents dapo
127
2
rsi-gear/gear 417
Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
5,2/gün ort. +1 son gün +11 son 7g 52 commit 5 yazar TypeScript 18 Ağu 2026 güncellendi 2 gün önce
meta-learning reinforcement-learning rsi ai-agents continual-learning infrastructure llm-training agent-harness
417
3
datamllab/OpenEBFM 273
Open-source code for training and scaling up energy-based foundation models.
5,9/gün ort. +13 son gün +10,7 son 7g 11 commit 3 yazar Python 21 Eyl 2026 güncellendi 3 gün önce
energy-based-models fine-tuning language-models llm post-training pretraining-model scaling-laws energy-based-language-models
273
4
worldbench/DiffusionOPSD 1.036
🔥 On-Policy Self-Distillation in Diffusion Models
10,4/gün ort. +10 son gün +10,6 son 7g 3 commit 1 yazar Python 29 Tem 2026 güncellendi 25 gün önce
aigc diffusion-models generative-ai image-editing on-policy-distillation on-policy-self-distillation image-generation post-training
1.036
5
Human-Agent-Society/reef önem 64gpt6-luna uyum 61gpt6-luna 7.802
Reef, agent isteklerini sunma, feedback toplama, öğrenme döngüsü yürütme ve kabul edilen güncellemeleri sürümleyerek dağıtma işlevlerini bir araya getiren Python altyapısıdır.
Neden yükseliyor · Sürekli öğrenen agent'lar gündemde ve Reef, inference'tan feedback'e, eğitimden sürüm dağıtımına uzanan altyapıyı tek projede toplamayı hedefliyor. Verilen ölçümlerde 28 günde 6.122 yıldız, 362 commit ve 19 farklı yazar güçlü ilgi ve geliştirme faaliyeti gösteriyor; ancak bu veriler tek başına üretim kullanımını veya teknik başarıyı kanıtlamıyor.
116,4/gün ort. +3 son gün +5,1 son 7g 266 commit 7 yazar Python 31 Ağu 2026 güncellendi bugün
agent-infrastructure ai-agents continual-learning inference llm llm-training reinforcement-learning self-improving-agents
7.802
6
BlueRingsLabs/no-shortcuts 172
Free Course : Data, Machine Learning, Deep Learning and AI Engineering, the long way round: the math, the code, the systems and the security
4,2/gün ort. +2 son gün +5 son 7g 1 commit 1 yazar Python 26 Eyl 2026 güncellendi 8 gün önce
ai-engineering course data-engineering deep-learning llm machine-learning mlops python
172
7
scaleapi/agentenv-framework 414
Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifac
9,6/gün ort. +1 son gün +3,4 son 7g 419 commit 7 yazar Python 24 Eyl 2026 güncellendi bugün
a2a agent-evaluation agentic-ai ai-agents llm-agents llm-evaluation mcp model-context-protocol
414
8
Purewhiter/mobilegym 853
[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. +0 son gün +1,6 son 7g 2 commit 1 yazar Python 14 May 2026 güncellendi 2 gün önce
benchmark mobile-agent reinforcement-learning vlm agents gym llm llm-agents
853
9
whitecircle/halo 845
Halo is an open-source framework built by White Circle for training large language and multimodal models
11,7/gün ort. +2 son gün +1,3 son 7g 6 commit 2 yazar Python 26 Ağu 2026 güncellendi bugün
agent async-rl distributed-training fine-tuning grpo large-language-models llm lora
845
10
huggingface/Repo2RLEnv 770
Turn any repository into verifiable RL environments for coding agents - Harbor tasks you can train on, evaluate and share on the Hugging Fac
4,2/gün ort. +3 son gün +1,3 son 7g 38 commit 9 yazar Python 05 May 2026 güncellendi 2 gün önce
coding-agents datasets harbor huggingface llm reinforcement-learning rl-environments swe-bench
770
11
adithya-s-k/FineEnvs 548
FineEnvs — RL Environments 101: building and scaling RL environments in the age of LLMs
2,9/gün ort. +0 son gün +1,1 son 7g 27 commit 3 yazar Python 01 May 2026 güncellendi dün
agents grpo huggingface llm openenv reinforcement-learning rl-environments rlhf
548
12
Animan-AI/DuckBuddy 85
Your real-life buddy duck: an open-source embodied AI robot duck that walks, hears, sees, and has a life of its own. 让 DuckBuddy 成为你真正的生活伙伴鸭
4,5/gün ort. +0 son gün +1,1 son 7g 19 commit 1 yazar Rust 18 Eki 2026 güncellendi 2 gün önce
biped-robot feetech microduck orange-pi reinforcement-learning robotics computer-vision embodied-ai
85
13
snap-stanford/memorilla 84
🦍 Memorilla: Latent Semantic Memory for LLMs
0,6/gün ort. +0 son gün +0,4 son 7g — commit Python 23 Haz 2026 güncellendi bugün
continual-learning llm memory context-compression long-context personalization reinforcement-learning retrieval-augmented-generation
84
14
xiaofengShi/MechVQA 56
ICML 2026 benchmark and MechVL models for multimodal understanding of mechanical engineering drawings.
0,4/gün ort. +0 son gün +0,4 son 7g — commit Python 25 Haz 2026 güncellendi 22 Eyl 2026
benchmark icml-2026 multimodal-llm visual-question-answering mechanical-drawings dataset engineering-drawing engineering-drawings
56
15
aiming-lab/MetaClaw önem 56gpt6-luna uyum 45gpt6-luna 3.467
MetaClaw, agent konuşmalarından öğrenme sinyalleri çıkarıp skill güncellemeleri ve isteğe bağlı LoRA tabanlı RL eğitimiyle agent’ı zaman içinde iyileştirmeyi amaçlayan bir yazılımdır.
Neden yükseliyor · 3492 yıldız ve README’de duyurulan teknik rapor ile birden fazla agent entegrasyonu dikkat çekmesini açıklayabilir. Ancak son 28 günde commit ve farklı yazar sayısı sıfır; bu nedenle mevcut ivme veya bakım temposu doğrulanamıyor. Teknik raporun HuggingFace Daily Papers sıralaması README’de proje tarafından bildiriliyor.
14,3/gün ort. +0 son gün +0,3 son 7g 0 commit 0 yazar Python 09 Mar 2026 güncellendi 07 Haz 2026
agent ai-agent fine-tuning llm lora metaclaw online-learning reinforcement-learning
3.467
16
THU-BPM/RLCSD 117
Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"
0,8/gün ort. +0 son gün +0,3 son 7g — commit Python 05 Haz 2026 güncellendi 14 Eyl 2026
large-language-models llm on-policy-distillation opsd reinforcement-learning self-distillation opd
117
17
Infini-AI-Lab/astraflow 114
Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs
0,6/gün ort. +0 son gün +0,3 son 7g — commit Python 14 May 2026 güncellendi 26 Tem 2026
agentic-ai llm llm-rl rl mlsys reinforcement-learning
114
18
alex-jb/orallexa-ai-trading-agent 73
Self-tuning multi-agent AI trading system. 8-source signal fusion, Bull/Bear/Judge debate on Claude Opus 4.7, Kelly + ATR position sizing. P
0,3/gün ort. +0 son gün +0,3 son 7g — commit Python 01 Nis 2026 güncellendi 8 gün önce
ai-trading algorithmic-trading claude fintech llm machine-learning multi-agent python
73
19
Rhoban/mjlab_microban 57
Reinforcement Learning (RL) environments for the Microban platform, a 30cm open-source and affordable humanoid robot.
0,3/gün ort. +0 son gün +0,3 son 7g — commit Python 08 May 2026 güncellendi 19 Tem 2026
diy humanoid-robot open-source reinforcement-learning robotics
57
20
tianyi-zhang-02/cooking-agi 35
Cooking AGI / AGI 大锅烩 · Bilingual (English / 中文) ML & LLM notes with worked examples, step-by-step figures and coding practice. Free to read
0,4/gün ort. +1 son gün +0,3 son 7g — commit Python 08 Ağu 2026 güncellendi bugün
llm post-training ai-agents bilingual deep-learning interview-preparation llm-evaluation machine-learning
35
21
AlessioPagliai/primo 18
Primo open source humanoid robot. 3D printed, 30 RobStride actuators, Jetson Thor. In design.
0,4/gün ort. +1 son gün +0,3 son 7g — commit Python 19 Eyl 2026 güncellendi 21 Eyl 2026
3d-printed-robot 3d-printing biped bipedal-robot humanoid humanoid-robot isaac-lab isaac-sim
18
22
jinzijian/EvoTrace önem 44gpt6-luna uyum 17gpt6-luna 282
EvoTrace, Claude Code ve Codex oturumlarını inceleyip eğitim, değerlendirme ve doğrulama için yeniden kullanılabilir varlıklara dönüştürür.
Neden yükseliyor · 39 günde 292 yıldız, coding agent oturumlarından eğitim ve değerlendirme varlığı üretme fikrine ilgi olduğunu gösteriyor; ancak bu ilginin nedeni ölçümlerden anlaşılamıyor. Son 28 günde commit ve farklı yazar olmaması, ilginin devam eden geliştirme veya benimsemeyle desteklendiğine dair kanıt sunmuyor.
3,6/gün ort. +0 son gün +0,1 son 7g 0 commit 0 yazar Python 19 Ağu 2026 güncellendi 5 gün önce
agents benchmark claude-code codex-cli coding-agents developer-tools evaluation llm-evaluation
282
23
inclusionAI/AReno 383
An easy-to-use, fast toolkit to scale up RL post-training on a single node.
2,6/gün ort. +0 son gün +0,1 son 7g 37 commit 6 yazar Python 09 Haz 2026 güncellendi bugün
agent agentic-ai grpo llm machine-learning post-training reinforcement-learning rl
383
24
DaoyuanLi2816/mini-verl 308
verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.
3/gün ort. +0 son gün +0,1 son 7g 0 commit 0 yazar Python 27 Tem 2026 güncellendi 15 Eyl 2026
agentic-rl consumer-gpu knowledge-distillation llm llm-agents on-policy-distillation post-training qlora
308
25
autonomous-ai/autonomous-grid 274
Your AI intranet: network the computers you already own for inference and training.
1,9/gün ort. +0 son gün +0,1 son 7g 99 commit 3 yazar Python 17 Haz 2026 güncellendi 3 gün önce
ai homelab inference llm local-llm openai-compatible orchestration python
274
26
omnilink-tech/omnisim 191
An open-source robotics workshop for agents: simulate complete robots on high-fidelity physics, build digital twins, make the parts on CNC,
1/gün ort. +1 son gün +0,1 son 7g — commit Python 01 May 2026 güncellendi dün
ai-agents mcp mujoco physics-simulation reinforcement-learning robot-simulator robotics ros2
191
27
reunios2024/cortex-sentinel-trading-nexus 124
Self-Tuning Multi-Agent AI Trading System 2026: 8-Source Signal Fusion & Kronos Model
0,9/gün ort. +0 son gün +0,1 son 7g — commit HTML 28 Haz 2026 güncellendi bugün
agentic ai-trading algorithmic-trading claude claude-opus fintech kalshi kronos
124
28
HumphreySun98/Smart-Study-Agent 58
The AI study agent that learns how you learn — RL picks the action, FSRS picks the timing, the LLM only writes the quizzes. Chrome extension
0,3/gün ort. +0 son gün +0,1 son 7g — commit JavaScript 08 Nis 2026 güncellendi 17 Ağu 2026
agent-framework ai-agent chrome-extension claude-api contextual-bandit huggingface pomdp q-learning
58
29
afx-team/UI-UX 34
UI-UX: a 4B multimodal LLM for mobile UX defect diagnosis, with UXBench — the first vision–language benchmark for UX reasoning (CVPR 2026 Fi
0,2/gün ort. +0 son gün +0,1 son 7g — commit Python 11 Haz 2026 güncellendi 26 Haz 2026
benchmark cvpr2026 grpo gui mllm multimodal-llm qwen reinforcement-learning
34
30
AllSpark-Research/Vela 32
Vela: User Behavior as Supervision Sparks LLM Intelligence — official paper, task templates, and prompts from AllSpark at Xiaohongshu.
1,1/gün ort. +0 son gün +0,1 son 7g — commit 09 Eki 2026 güncellendi 23 gün önce
large-language-models llm machine-learning natural-language-processing reinforcement-learning supervised-fine-tuning user-behavior user-modeling
32
31
THMOS2025/MOS-9-Open-Source-Humanoid-Robot 27
MOS9 open-source humanoid robot hub for RoboCup Kid-Size, connecting hardware, deployment, IPC, policy learning, retargeting, drivers, and s
0,2/gün ort. +0 son gün +0,1 son 7g — commit Shell 15 Tem 2026 güncellendi 23 Tem 2026
humanoid-robot ipc open-source reinforcement-learning robocup robotics
27
32
sediment-ai/sediment 21
Self-hosted evidence store for coding agents.
0,5/gün ort. +0 son gün +0,1 son 7g — commit Python 21 Eyl 2026 güncellendi dün
agent-evaluation ai-agents coding-agents context-engineering developer-tools llm-observability postgresql reinforcement-learning
21
33
Hoyant-Su/Agentic-RL-A3 20
[NeurIPS 2026] Agentic reinforcement learning for CLI agents with structured action credit assignment, budgeted workspace context selection,
0,1/gün ort. +1 son gün +0,1 son 7g — commit Python 08 May 2026 güncellendi 25 gün önce
agentic-rl cli-agent cli-agents credit-assignment harness harness-design llm reinforcement-learning
20
34
AltmanD/HarborRL 16
An end-to-end framework for Agentic Reinforcement Learning.
0,2/gün ort. +0 son gün +0,1 son 7g — commit Python 05 Ağu 2026 güncellendi 3 gün önce
agentic agentic-ai agentic-framework grpo large-language-models post-training ppo reinforcement-learning
16
35
vrtnis/tycoon-learning-environment 16
A JAX transport-economy learning environment for route planning, cargo flow, financing, and replayable agent benchmarks.
0,1/gün ort. +0 son gün +0,1 son 7g — commit Python 05 Haz 2026 güncellendi 27 Tem 2026
agents benchmark economy jax logistics openttd planning reinforcement-learning
16
36
juanjo-barrientos/genaiguide 14
Guía gratuita de IA generativa avanzada en español (311 págs.): Transformer, post-entrenamiento, inferencia, GPU, difusión, agentes, segurid
0,4/gün ort. +0 son gün +0,1 son 7g — commit 02 Eki 2026 güncellendi 02 Eki 2026
ai-agents deep-learning diffusion-models espanol free-book generative-ai inference llm
14
37
Stxqq/self-driving-car önem 29gpt6-luna uyum 4gpt6-luna 25
JavaScript ile yazılmış, neural network ve genetic algorithm kullanarak sentetik otoyol trafiğinde araç sürüşünü simüle eden etkileşimli bir demo.
Neden yükseliyor · Repo bir günlükken 46 yıldız almış ve canlı demo ile görsel olarak anlaşılır bir konu sunuyor; ancak son 28 günlük commit ve farklı yazar verisi ölçülmediğinden yükselişin devamlılığı veya ekip aktivitesi hakkında kanıt yok.
0,7/gün ort. +0 son gün +0 son 7g — commit JavaScript 01 Eki 2026 güncellendi 01 Eki 2026
autonomous-driving canvas evolutionary-algorithms genetic-algorithm javascript machine-learning neural-network neuroevolution
25
38
CUTEPKQ/NEWTON 139
NEWTON: Agentic Planning for Physically Grounded Video Generation
1/gün ort. +0 son gün +0 son 7g — commit Python 13 Haz 2026 güncellendi 31 Tem 2026
agentic-ai ai-agents aigc computer-vision diffusion-models grpo llm-agent multimodal
139
39
grandgaming9321-prog/reality-engine 132
Top Dynamic AI World Simulation & Storytelling Tools 2026
1/gün ort. +0 son gün +0 son 7g — commit HTML 28 Haz 2026 güncellendi bugün
3d ai ai-simulation creative-ai digital-twin game-ai game-development generative-ai
132
40
deepelementlab/clawcode 126
ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source c
0,6/gün ort. +0 son gün +0 son 7g — commit Python 01 Nis 2026 güncellendi 21 May 2026
ai-agents automation coding-assistant llm multi-agent python3 reinforcement-learning rust-library
126
41
aminekago-web/Paradigm-Survival-Arena 116
Top 6 AI Paradigms Fighting for Survival in 2026
0,9/gün ort. +0 son gün +0 son 7g — commit HTML 28 Haz 2026 güncellendi bugün
agario ai-simulation artificial-intelligence canvas educational evolutionary-algorithms game interactive-learning
116
42
znxzsy/AlignLedger 100
Human-feedback and data-governance infrastructure for RSI research: annotation, review, provenance and frozen dataset candidates.
1,4/gün ort. +0 son gün +0 son 7g — commit Python 26 Ağu 2026 güncellendi 8 gün önce
annotation annotation-tool data-labeling data-provenance data-quality dpo human-feedback kto
100
43
Harahan/MeanFlowNFT 99
[arXiv 2026] This is the official PyTorch implementation of "MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators".
0,9/gün ort. +0 son gün +0 son 7g — commit Python 14 Tem 2026 güncellendi 30 Ağu 2026
diffusion-models few-step-generation flow-map grpo image-generation meanflow nft reinforcement-learning
99
44
Sheltercosmo/Rilldex-RL-Studio 80
RL observability for LLM agents: behavior maps, native trainer metrics, rollout investigations, and Python/SQL analysis.
3,8/gün ort. +0 son gün +0 son 7g 20 commit 1 yazar Python 16 Eki 2026 güncellendi 2 gün önce
experiment-tracking grpo reinforcement-learning llm-observability post-training reward-hacking rlhf agent-observability
80
45
onyx-robotics/onyx-agent 71
Use large-scale AI agent teams to rapidly discover code improvements and "autoresearch" your hardware systems.
0,5/gün ort. +0 son gün +0 son 7g — commit TypeScript 07 Haz 2026 güncellendi 17 gün önce
ai ai-agents autoresearch control-systems control-theory hyperparameter-optimization hyperparameter-tuning model-predictive-control
71
46
alem-world/alem-env 57
Can LLM/MARL agents coordinate in long-horizon, open-ended tasks? NeurIPS 2026 (Evaluations and Datasets).
0,4/gün ort. +0 son gün +0 son 7g — commit Python 05 Haz 2026 güncellendi dün
agents benchmark llm marl reinforcement-learning rl llm-agents multi-agent
57
47
Aaryan-Kapoor/ModelGate-Hackathon 54
🏆Winning Project | ModelGate is a contract-aware AI control plane that ingests customer contracts, extracts SLA/privacy/routing constraints,
0,2/gün ort. +0 son gün +0 son 7g — commit TypeScript 20 Mar 2026 güncellendi 22 Mar 2026
ai cost-optimization fastapi fine-tuning gguf grpo hackathon llamacpp
54
48
Spreadsheet-RL/Spreadsheet-RL 54
Official Repo for Spreadsheet-RL
0,3/gün ort. +0 son gün +0 son 7g — commit Python 17 May 2026 güncellendi 30 Tem 2026
agents reinforcement-learning spreadsheets
54
49
aganthos/clawloop 47
Make your agents learn from experience. One protocol for weights, harness and routing.
0,2/gün ort. +0 son gün +0 son 7g — commit Python 27 Mar 2026 güncellendi 12 Haz 2026
agents ai-agents llm machine-learning prompt-optimization python reinforcement-learning
47
50
Suraj-G-Rao/RL-Based-Cyber-Threat-Detection 47
A powerful AI-powered chatbot that leverages Neo4j's Cyber Knowledge Graph (CKG) and Groq API to provide intelligent cybersecurity threat in
0,2/gün ort. +0 son gün +0 son 7g — commit Jupyter Notebook 03 Nis 2026 güncellendi 04 May 2026
generative-ai groq-api neo4j-database reinforcement-learning
47