Stars
⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA
Financial data platform for analysts, quants and AI agents.
TradingAgents: Multi-Agents LLM Financial Trading Framework
基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版
The agent that grows with you
The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are commi…
AKShare is an elegant and simple financial data interface library for Python, built for human beings! 开源财经数据接口库
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Bub it. Build it. A hook-first runtime for agents that live alongside people.
A plain-text life operating system powered by Claude Code. Inspired by Carmack's .plan files and Franklin's systematic self-improvement.
Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require e…
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more
Recursive Language Models (RLMs) implementation based on the paper by Zhang, Kraska, and Khattab
SGLang is a high-performance serving framework for large language models and multimodal models.
Toolchain built around the Megatron-LM for Distributed Training
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组
一个面向中文文本纠错任务的综合平台，集学术研究、模型训练、模型评测和推理部署于一体，文本纠错新Sota。（ 2026 ACL Main Oral ）
Lightweight daemon for monitoring CUDA runtime API calls with eBPF uprobes
chat log tool, easily use your own chat data. 聊天记录工具，轻松使用自己的聊天数据