aiqinxuancai/AutoLinker

AutoLinker支持库，易语言AI Agent、MCP服务。另外支持不同源文件使用不同的Linker，调试编译时动态与静态ec自动切换等功能。

What it solves

AutoLinker provides AI Agent capabilities for the E-language (易语言) IDE, enabling AI to automatically search, read, and edit source code based on user requirements. It bridges the gap between traditional E-language development and modern AI-assisted coding by allowing external AI tools to interact directly with the IDE's internal state.

How it works

AutoLinker acts as a support library (.fne) for the E-language IDE. It implements a local Model Context Protocol (MCP) server that allows AI agents (like Claude Code, Gemini CLI, or Codex) to communicate with the IDE via JSON-RPC 2.0. To avoid polluting original source files, it creates a temporary workspace mirror of the project. It provides a suite of 26 tools for the AI to perform actions such as reading files, searching code, editing text with SHA-256 hash verification (CAS), and managing modules.

Who it’s for

Developers using E-language who want to integrate AI agents into their workflow to automate coding, optimization, and documentation tasks.

Highlights

  • AI Agent Integration: Built-in session tab for AI interaction and right-click menu shortcuts for function optimization, commenting, and translation.
  • MCP Server: Enables integration with external AI tools (Claude Code, Gemini CLI, etc.) via a streamable HTTP transport.
  • Project-Specific Rules: Supports .AGENTS.md files to inject custom system prompts and project specifications into the AI.
  • Headless Compilation: Allows triggering E-language compilation via command line, supporting both native and BlackMoon compilers.
  • Core Library Overwriting: Enables replacing standard core library functions with custom C++ implementations to improve performance and evade detection.
  • Automatic Module Switching: Automatically swaps between dynamic and static .ec modules during debug and compile phases.

Related

  • Project
    SAIL-Research-Lab/cheetahclaws

    A Python-native agent harness for AI coding assistants that supports any LLM provider or local model, offering a hackable alternative to closed-source agent frameworks.

  • Project
    datalayer/jupyter-mcp-server

    Jupyter MCP Server is an open‑source bridge that lets AI agents talk to Jupyter notebooks in real time via the Model Context Protocol. It exposes notebook files, cells, and kernel execution as structured tools, supports many cloud sandbox back‑ends, and uses OAuth 2.1 for secure token‑based access.

  • Project
    daobataotie/CAD-MCP

    CAD-MCP is a Model Context Protocol server that connects AI assistants like Claude or Cursor to CAD software (AutoCAD, GstarCAD, ZWCAD). It exposes 35 tools for drawing, editing, querying, and managing layers and blocks, so users can create and modify drawings by typing plain-language commands instead of using the CAD interface manually.

  • Project
    redis/mcp-redis

    Redis MCP Server is a Python‑based, Docker‑ready server that lets AI agents interact with Redis via natural‑language commands. It implements the Model Content Protocol, exposing tools for every Redis data type (strings, hashes, lists, sets, streams, JSON, vector indexes, pub/sub, etc.) and supports Azure Entra ID authentication. Install from PyPI or Docker, configure via CLI flags or env‑vars, and plug it into Claude Desktop, OpenAI Agents SDK, or any MCP client.

  • Project
    msitarzewski/agency-agents

    A library of markdown‑based AI agent personas (e.g., Frontend Developer, AI Engineer, UI Designer) that can be installed into code‑assistant tools like Claude Code, Cursor, Gemini CLI, etc., via a native desktop app or command‑line scripts. Each agent defines a role, workflow, deliverables and success metrics, enabling consistent, specialist‑level behavior from LLMs.