Starred repositories
The roadmap of long-horizon agents
DeepSeek Harness: Everything is a Plugin.
DLRover: An Automatic Distributed Deep Learning System
Official Python implementation for DocAgent, accepted to EMNLP 2025
同频（Resonance）是一个本地化的 ETF「国家队」资金监控系统。它通过价格位置、份额流向、交易方向、成交额热度、融资杠杆五个指标各自亮灯，当同色灯≥3盏时判定为「危险共振」或「机会共振」，量化识别中央汇金等资金的系统性进出。数据、计算、存储全部在本机，支持一键重建全量历史、定时增量拉取，并提供 CLI 供外部Agent 转 IM 预警。仅用于研究，非投资建议。
陈小群视角 Skill — 用情绪周期与龙头信仰研判短线机会 & Talk to 群总 · 龙头语音室，跟群总直接对话
Better Harness turns project and session evidence into loop-level insights, prioritized improvements, and verifiable next steps—inside the coding agent you already use.
In order to make it easier to use the ComfyUI, I have made some optimizations and integrations to some commonly used nodes.
Skills for Real Engineers. Straight from my .agents directory.
Turn vague or complex Codex tasks into strong `/goal` commands with outcome, verification, constraints, boundaries, iteration policy, completion evide
An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance
A simple, open source bilingual translation extension & Greasemonkey script (一个简约、开源的 双语对照翻译扩展 & 油猴脚本)
A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progress
利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
The open-source app everyone uses to manage agents at work
🚀 Beautiful highly customizable statusline for Claude Code CLI with powerline support, themes, and more.
Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
Fin-R1 is a large language model for complex financial reasoning developed and open-sourced with the joint efforts of the SUFE-AIFLM-Lab at the School of Statistics and Data Science, Shanghai Unive…
[ICML 2026] Official resources of "Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning".
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
MiroFish的免费本地运行版本 | Graphiti+Neo4j替代付费Zep | 简易便捷本地跑通
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Train your AI self, amplify you, bridge the world
"RAG-Anything: All-in-One RAG Framework"
An embedded document database with native candid support for Motoko developers
Reproduction and extension of Memory-R1 (arXiv:2508.19828) — RL for LLM agent memory