ForkMind

Name: ForkMind
Author: Medhovarsh

@Medhovarsh

ForkMind について

🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.

基本情報

カテゴリ

AI とエージェント

ライセンス

MIT

ランタイム

node

公開者

Medhovarsh

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "forkmind": {
      "command": "npx",
      "args": [
        "-y",
        "forkmind",
        "mcp"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is ForkMind?

ForkMind is a local-first LLM state branching and debugging tool that treats AI context windows like a Git repository. It captures every LLM call into a local .forkmind/ directory, visualizes the conversation as a Directed Acyclic Graph (DAG), and lets you branch alternative prompts or model parameters from any point in history—all on your machine with no cloud or account. It works with any OpenAI-compatible API, defaulting to free open-source models via Ollama, and also supports Anthropic and hosted free tiers (Groq, OpenRouter, Together, vLLM, LM Studio).

How to use ForkMind?

Install ForkMind via npm (npx forkmind init, npx forkmind start) or globally (npm install -g forkmind). Quick start: install Ollama, pull a model, run the CLI to start a proxy on http://localhost:4500, then point your code at that proxy. ForkMind provides a drop-in SDK for Node.js (ForkMindOpenAI), adapters for LangChain.js and Vercel AI SDK, and a Claude Code plugin. Any language can capture calls by setting the client’s base URL to http://localhost:4500/v1 and passing the x-forkmind-upstream and x-forkmind-parent headers.