🖥️ 주간 IT 통합 리포트 (2026년 05월 15일)

🥇 anthropics / financial-services

설명 없음

Python ⭐ 23026 전체  |  📈 12,529 stars this week

🥈 CloakHQ / CloakBrowser

Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patc…

Python ⭐ 11517 전체  |  📈 8,404 stars this week

🥉 yikart / AiToEarn

Let’s use AI to Earn!

TypeScript ⭐ 13952 전체  |  📈 4,412 stars this week

4위 rohitg00 / agentmemory

#1 Persistent memory for AI coding agents based on real-world benchmarks

TypeScript ⭐ 9367 전체  |  📈 6,467 stars this week

5위 bytedance / UI-TARS-desktop

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

TypeScript ⭐ 34018 전체  |  📈 4,184 stars this week

6위 decolua / 9router

Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via …

JavaScript ⭐ 10490 전체  |  📈 6,024 stars this week

7위 Hmbown / DeepSeek-TUI

Coding agent for DeepSeek models that runs in your terminal

Rust ⭐ 29581 전체  |  📈 11,303 stars this week

8위 HKUDS / AI-Trader

“AI-Trader: 100% Fully-Automated Agent-Native Trading”

Python ⭐ 17308 전체  |  📈 3,013 stars this week

9위 mattpocock / skills

Skills for Real Engineers. Straight from my .claude directory.

Shell ⭐ 83831 전체  |  📈 17,059 stars this week

10위 playcanvas / supersplat

3D Gaussian Splat Editor

TypeScript ⭐ 8011 전체  |  📈 2,866 stars this week

1. Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents

arXiv:2605.12620v1 Announce Type: new Abstract: Building generalist embodied agents capable of solving complex real-world tasks remains a fundamental challenge in AI. Multimodal Large Language Models…

arXiv (cs.AI)

2. Macro-Action Based Multi-Agent Instruction Following through Value Cancellation

arXiv:2605.12655v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) in real-world use cases may need to adapt to external natural language instructions that interrupt ongoing be…

arXiv (cs.AI)

3. Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with B…

arXiv:2605.12673v1 Announce Type: new Abstract: Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hacki…

arXiv (cs.AI)

4. Vision-Based Runtime Monitoring under Varying Specifications using Semantic Latent Represe…

arXiv:2605.13923v1 Announce Type: new Abstract: We study certified runtime monitoring of past-time signal temporal logic (ptSTL) from visual observations under partial observability. The monitor must…

arXiv (cs.LG)

5. Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders

arXiv:2605.13930v1 Announce Type: new Abstract: EEG foundation models achieve state-of-the-art clinical performance, yet the internal computations driving their predictions remain opaque: a barrier t…

arXiv (cs.LG)

6. Rethinking Molecular OOD Generalization via Target-Aware Source Selection

arXiv:2605.13932v1 Announce Type: new Abstract: Robust prediction of molecular properties under extreme out-of-distribution (OOD) scenarios is a pivotal bottleneck in AI-driven drug discovery. Curren…

arXiv (cs.LG)

7. Merging Methods for Multilingual Knowledge Editing for Large Language Models: An Empirical…

arXiv:2605.13919v1 Announce Type: new Abstract: Multilingual knowledge editing (MKE) remains challenging because language-specific edits interfere with one another, even when locate-then-edit methods…

arXiv (cs.CL)

8. VectraYX-Nano: A 42M-Parameter Spanish Cybersecurity Language Model with Curriculum Learni…

arXiv:2605.13989v1 Announce Type: new Abstract: We present VectraYX-Nano, a 41.95M-parameter decoder-only language model trained from scratch in Spanish for cybersecurity, with a Latin-American focus…

arXiv (cs.CL)

9. Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding

arXiv:2605.14005v1 Announce Type: new Abstract: Speculative decoding has become a widely adopted technique for accelerating large language model (LLM) inference by drafting multiple candidate tokens…

arXiv (cs.CL)

1. tslib v2.8.1

Runtime library for TypeScript helper functions

2. hasown v2.0.3

A robust, ES3 compatible, “has own property” predicate.

3. typescript v6.0.3

TypeScript is a language for application scale JavaScript development

4. @babel/parser v7.29.3

A JavaScript parser

5. @typescript-eslint/typescript-estree v8.59.3

A parser that converts TypeScript source code into an ESTree compatible form

1. pydantic v2.13.4 주간 ⬇ 262,045,912

Data validation using Python type hints

2. httpx v0.28.1 주간 ⬇ 175,135,217

The next generation HTTP client.

3. litellm v1.84.0 주간 ⬇ 110,416,472

Library to easily interface with LLM API providers

4. typer v0.25.1 주간 ⬇ 91,847,597

Typer, build great CLIs. Easy to code. Based on Python type hints.

5. ruff v0.15.13 주간 ⬇ 52,926,243

An extremely fast Python linter and code formatter, written in Rust.

⚠️ 본 리포트는 자동 수집 정보이며, 정확성을 보장하지 않습니다.
📅 생성일: 2026년 05월 15일