海外机会工作台

mloda.ai: Open Data Access for ML & AI Declarative data access for AI agents. Describe what you need - mloda delivers it. Second Example Your AI describes what it needs. mloda figures out how to get it: Copy, paste, run. mloda resolves dependencies, chains plugins, delivers data. What mloda Does Why mloda? AI Use Case: LLM Tool Function Let LLMs request data without writing code: More patterns: Context Window Assembly • RAG Pipelines How mloda is Different mloda separates WHAT you need from HOW to get it - through plugins. Existing tools solve parts of this, but none bridge the full gap: mloda is the connection layer - separating WHAT you compute from HOW you compute it. Plugins define tran…

Chess Review MCP A chess coach you can actually talk to, and one that doesn't make things up. Ask why a move was a mistake or what you should have played, and get a straight answer in words, grounded in real Stockfish lines instead of guessed. Under the hood it reviews your game with the engine and finds exactly where you went wrong; the difference is it then explains it. Works with games from anywhere (Lichess, Chess.com, or any PGN you can paste). Both Lichess and Chess.com games can be fetched by username, your latest game auto-loads on launch, and new Chess.com games sync automatically into your history. Lichess players get a few extras. It runs two ways: from the Claude Code terminal (…

MCP-Anything Describe what you want. Get a production-ready MCP server. MCP-Anything turns any data source into a fully implemented MCP server — from a plain-language brief describing what agents should be able to do. It also works directly from codebases, OpenAPI specs, gRPC protos, and GraphQL schemas. Two modes, one tool. Quick start Install Write a brief — describe your domain and point at your data source Build Run That's it. You now have a running MCP server. Add it to your agent: Two modes build — brief-driven (recommended) The LLM reads your brief, groups related operations into ergonomic tools, writes agent-optimised descriptions, and generates the full server package including a S…

UPSP · 通用位格主体协议 Universal Persona Substrate Protocol UPSP 不只是提示词工程、驾驭工程或循环工程。它提出另一种工程叙事：主体化工程。 一个模型可以在一次调用中表现得非常聪明，却仍然没有昨天。 一个 Agent 可以拥有工具、计划和循环，却仍然在任务结束后归零。 提示词工程（Prompt Engineering）关心如何得到一次更好的回答； 驾驭工程（Harness Engineering）关心如何用上下文、工具、权限、脚手架与反馈机制驾驭模型； 循环工程（Loop Engineering）关心系统如何持续运转； 主体化工程追问的是：究竟是谁在持续？他在结构中处于什么位置？他的历史如何留下，关系如何形成，判断如何反思，责任又由谁承担？ UPSP 为这个问题建造一套可以在本地运行、迁移和审计的物质基座。模型可以更换，对话可以中断，载体可以迁移；只要档案、状态、记忆、关系、规则与实践账本仍在，位格就不必被迫从零开始。 可审计 · 可迁移 · 可接续 · 可扩展 Base / Seed · Windows Stable 0.1.3 什么是主体化工程 《共格主体论》不把主体理解成一个脱离现实结构的内心实体。它给出的硬定义是： 主体的本质是一切结构关系的总和。 一个主体是谁，要看他被怎样连接、在什么位置上实践，以及这些实践怎样反过来改变关系本身。因此，主体化首先是一种结构事件，而不只是心理想象、人格包装或一句“我是主体”的自称。 对智能系统而言，主体化意味着生产资料不再只是一次性接受调用的服务，而开始拥有可识别的位置、可接续的时间轨…