underthesea
Underthesea - AI Assistant
AI 智能体是一种用大模型决定下一步做什么的程序:它会调用浏览器、代码解释器或 API 等工具,反复执行,直到任务完成。这里的项目既有用来搭建自己智能体的框架,也有能写代码、浏览网页或运行业务流程的现成智能体。
比较时看三点:能用哪些模型——只支持一家服务商,还是任何兼容 OpenAI 接口的端点(包括本地模型);怎么限制智能体能做的事——沙箱、审批步骤、权限清单;以及它能否在步骤之间、会话之间保留记忆。会执行代码或命令行的智能体应该在沙箱里运行,给它访问你电脑的权限之前先确认这一点。
Underthesea - AI Assistant
DATAGEN: AI-driven multi-agent research assistant automating hypothesis generation, data analysis, and report writing.
WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.
LM Studio TypeScript SDK
MCP Server para 70 APIs públicas brasileiras
百聆 是一个类似GPT-4o的语音对话机器人,通过ASR+LLM+TTS实现,集成DeepSeek R1等优秀大模型,接入openClaw,真正的个人语音助手,时延低至800ms,Mac等低配置也可运行,支持打断
Scalable data pre processing and curation toolkit for LLMs
自然语言处理、知识图谱、对话系统,大模型等技术研究与应用。
Waku Waku! Waku Agent is a local-first AI agent harness you actually own, including loop, memory, eval, all in code built to stay legible as it grows.
Claude Code for Financial Market
AI+金融(量化):1.多因子股票量化框架开源教程 2.学界和业界的经典资料收录 3.AI + 金融的相关工作,包括LLM, Agent, benchmark(evaluation), etc.
Build Anything with AI Agents
Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.
Grounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools
Synthetic data curation for post-training and structured data extraction
Advanced LLM-powered brute-force tool combining AI intelligence with automated login attacks
Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others. Includes CodeRabbit open-source alternative.
Optimized Agentic and LLM Bulk Processing Over Your Data
Lightweight coding agent written in Rust, optimized for memory footprint and performance
Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
一款包含了 Prompt管理,Skill管理,Agent管理的一站式AI工具箱,助你高效管理提示词,一键分发skills ,一站式管理Agent资产,并实现云同步,备份,版本管理 | An all-in-one AI toolbox for prompt, agent, and skills management. Reuse prompts, distribute skills with one click, manage agent assets, and support cloud sync, backup, and version control
A collection of AI Agents papers (Updated biweekly)
Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.