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 5.829 llm 4.974 mcp 4.437 claude 2.860 anthropic 1.310 openai 1.009 rag 872 agents 813 prompt-engineering 807 image-generation 712 generative-ai 402 knowledge-graph 387 text-to-speech 301 semantic-search 216 speech-recognition 176 embeddings 155 vector-search 139 llmops 111

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 research

1
synthetic-sciences/openscience önem 63gpt6-luna uyum 34gpt6-luna 4.358
OpenScience, bilimsel araştırma görevlerini planlayıp literatür taraması, kod çalıştırma ve sonuç raporlamayı tek bir AI workbench içinde birleştirir.
Neden yükseliyor · 86 günlük bir repoda 3.645 yıldız ve son 28 günde 434 commit dikkat çekici; bilimsel araştırma agent'ı fikri de güncel AI ilgisiyle örtüşüyor. README'de Y Combinator desteği belirtiliyor. Ancak aktivite yalnızca 5 farklı yazardan geldiği için büyümenin geniş katkıcı topluluğuna dayandığı söylenemez.
33,8/gün ort. +2 son gün — commit TypeScript 03 Tem 2026 güncellendi dün
agent ai bun cli llm ml open-source research
4.358
2
WantongC/journal-adapt-writing-skill 776
Learn any journal's writing conventions from its published papers, then revise your manuscript to match — section by section.
4,3/gün ort. +1 son gün — commit 13 May 2026 güncellendi 15 May 2026
academic-writing claude economics journal latex llm manuscript-revision prompt-engineering
776
3
beita6969/ScienceClaw 1.027
Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.
4,2/gün ort. +0 son gün — commit TypeScript 11 Mar 2026 güncellendi 4 gün önce
ai ai-agent bioinformatics literature-review llm mcp meta-analysis openclaw
1.027
4
docsagent/docsagent 578
⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero, Obsidian, Apple Notes supported now, loca
2,6/gün ort. +0 son gün — commit TypeScript 03 Nis 2026 güncellendi 28 Eyl 2026
local-ai pdf search ai-agents bm25 claude cursor full-text-search
578
5
Omni-Scientist/OmniScientist 173
An Omni-Modal, Omni-Discipline AI Scientist
2/gün ort. +0 son gün — commit TypeScript 16 Ağu 2026 güncellendi 26 Eyl 2026
agent ai-scientist llm research skill
173
6
Extraltodeus/J-Wash 242
Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.
2/gün ort. +0 son gün — commit Python 13 Tem 2026 güncellendi 06 Eyl 2026
ai anthropic huggingface interpretability jacobian-lens llm mechanistic-interpretability model-editing
242
7
microsoft/ArgusAgent 144
A persistent, reviewed multi-agent runtime for long-horizon research and engineering.
1,5/gün ort. +0 son gün — commit Python 05 Ağu 2026 güncellendi 9 gün önce
agentic-ai ai-agents autonomous-agents claude codex copilot llm mcp
144
8
p-e-w/lophius 111
A workbench for language model research
1,2/gün ort. +0 son gün — commit Python 09 Ağu 2026 güncellendi 09 Ağu 2026
llm research
111
9
moonlight-lupin/agent-skills 120
A collection of AI agent skills and plugins for Hermes Agent — research, creative, productivity, devops, and more. Each skill is self-contai
1/gün ort. +0 son gün — commit Python 08 Tem 2026 güncellendi 2 gün önce
agent-ops ai-agent ai-agent-skills automation claude-code hermes llm research
120
10
cLin-c/paper-skill 142
🎓 Claude Code skill — AI prompt library for academic paper writing, polishing, reviewing, translating and submitting to SCI/IEEE/Nature/TRO
0,9/gün ort. +1 son gün — commit HTML 12 Haz 2026 güncellendi bugün
academic-writing ai claude-code latex llm paper prompt-engineering research
142
11
assafkip/research-mode 154
Anti-hallucination research mode for Claude Code. Toggle on/off to enforce citation requirements and source grounding.
0,7/gün ort. +0 son gün — commit 23 Mar 2026 güncellendi 16 Nis 2026
ai-safety anti-hallucination citations claude-code claude-code-plugin llm research
154
12
jameslemon2002/research-idea-explorer 137
Literature-grounded research idea exploration for CLI agents. 文献驱动的研究选题与方向探索工具。
0,6/gün ort. +0 son gün — commit Python 23 Mar 2026 güncellendi 02 Nis 2026
agent ai llm research
137
13
Citrus-bit/Anaxa 125
Anaxa 是一个面向科研工作流的开源智能体系统。它不是单纯的聊天机器人，也不是无人监管的自动发论文机器，而是把文献检索、证据审计、实验执行、论文写作、同行评审式检查和最终产物打包放进同一个可追踪的研究生命周期中。
0,6/gün ort. +0 son gün — commit Python 30 Mar 2026 güncellendi 07 Eyl 2026
agent css fastapi langchain langgraph llm nextjs nginx
125
14
OvOhao/auto-paper-collecter 64
📚🔭 Your personal research radar — an LLM-powered tool that auto-aggregates the latest papers for your keywords across arXiv / Crossref / Sem
0,5/gün ort. +0 son gün — commit Python 25 Haz 2026 güncellendi 28 Haz 2026
academic arxiv crossref fastapi literature-review llm paper-tracker python
64
15
zoharbabin/web-researcher-mcp 77
Search the web and primary sources, read full pages, and check every citation. MCP server for Claude, Cursor, Codex and more. Runs on your m
0,4/gün ort. +0 son gün — commit Go 18 May 2026 güncellendi bugün
ai claude content-extraction go llm mcp model-context-protocol research
77
16
wbopan/retro-harness 68
RHO: Evolving Agents in the Dark — Retrospective Harness Optimization via Self-Preference. Improving LLM agents from unlabeled past trajecto
0,4/gün ort. +0 son gün — commit Python 07 Haz 2026 güncellendi 10 gün önce
agent-optimization llm llm-agents prompt-optimization research self-supervised swe-bench
68
17
Mexregkan/claude-for-researchers 54
Practical guide and toolkit for physicists and mathematicians using Claude Code — built from months on a real research project
0,3/gün ort. +0 son gün — commit Shell 05 Haz 2026 güncellendi 03 Eyl 2026
academic ai-tools claude-code latex llm mathematica mathematics physics
54
18
xf686/Meet-Reviewer-2 47
Meet Reviewer 2 before they meet you ！ A Claude Code skill that red-teams your paper draft — a simulated peer-review panel + an evidence
0,3/gün ort. +0 son gün — commit 22 Haz 2026 güncellendi 23 Haz 2026
academic academic-skills arxiv claude-code claude-skill llm machine-learning paper
47
19
wanshuiyin/ARIS-Anything 58
Generalizing ARIS from 科研 to 研究 — same five-step loop (plan · draft · adversarial review · iterate · persist) applied beyond academic resear
0,3/gün ort. +1 son gün — commit Markdown 20 May 2026 güncellendi 3 gün önce
adversarial-review agent aris bilingual claude-code cross-model-review investment-research knowledge-management
58
20
SantanderAI/sota-stressed-datasets 42
Open benchmark datasets republished in stressed form to evaluate ML/LLM robustness. Curated by Santander AI Lab.
0,3/gün ort. +0 son gün — commit HTML 17 Haz 2026 güncellendi 12 gün önce
ai benchmark credit-risk dataset datasets evaluation fairness llm
42
21
exmergo/research-chatgpt-guesses-between-1-and-100 47
When asked to pick a random number between 1 and 100, ChatGPT does not follow a random uniform distribution
0,3/gün ort. +0 son gün — commit Python 22 May 2026 güncellendi 25 May 2026
open-research cognitive-bias gpt llm llm-evaluation python research uv
47
22
ly028716/harness-engineering-study 36
Research-backed Harness Engineering study repo with a runnable Python MVP built around Plan -> Work -> Review.
0,2/gün ort. +0 son gün — commit Python 11 Nis 2026 güncellendi 03 Ağu 2026
agent-workflows ai-agents code-review developer-tools engineering-productivity harness-engineering llm python
36
23
starkdcc/claude-code-source 32
Claude Code CLI — original source code snapshot for research. Property of Anthropic.
0,1/gün ort. +0 son gün — commit TypeScript 31 Mar 2026 güncellendi 31 Mar 2026
agent ai anthropic claude claude-code cli llm nodejs
32