峰哥亡命天涯视角Skill

🤖 从零开始学 Agent - Agentic RL | Agent Memory | Agent 前沿进展

PolyDepth is a real-time analytics bot for Polymarket crypto Up/Down markets, combining order book data, Binance trades, and price anchors to detect short-term market inefficiencies.

加密货币智能定投小程序

iTerm2 + Oh My Zsh 打造舒适终端体验

Actionbook provides up-to-date action manuals, so your AI agent operates any website 10x faster without guessing.

Agent skills for Obsidian. Teach your agent to use Markdown, Bases, JSON Canvas, and use the CLI.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

LLM驱动的 A/H/美股智能分析器：多数据源行情 + 实时新闻 + LLM决策仪表盘 + 多渠道推送，零成本定时运行，纯白嫖. LLM-powered stock analysis system for A/H/US markets.

Trading Strategies for Freqtrade

SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.

FacTool: Factuality Detection in Generative AI

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Production-grade Rust-native trading engine with deterministic event-driven architecture

Crypto Trading Operating System) with a clean, Linux‑inspired layout that treats each exchange (OKX / Backpack / Binance) as its own “arch”

Awesome Long-Form Factuality: A Curated List of Papers and Resources on Enhancing Factuality in Long-Form LLM Generations

verl: Volcano Engine Reinforcement Learning for LLMs

RM-R1: Unleashing the Reasoning Potential of Reward Models

AllenAI's post-training codebase

Reproducing R1 for Code with Reliable Rewards

✨ A synthetic dataset generation framework that produces diverse coding questions and verifiable solutions - all in one framwork

structured outputs for llms

[ACL 2025 Main] Official Repo for Paper "Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric"

Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples

An Open-source RL System from ByteDance Seed and Tsinghua AIR

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

一个面向多模态大模型训练的智能数据集构建与评估平台

verl: Volcano Engine Reinforcement Learning for LLMs

Code for "SemDeDup", a simple method for identifying and removing semantic duplicates from a dataset (data pairs which are semantically similar, but not exactly identical).