OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Arcrift

Arcrift is a local-first memory tool for AI coding workflows. Its browser extension captures conversations from supported AI chat services, and its native MCP server makes stored context available to coding assistants. A local SQLite knowledge graph organizes conversations and decisions for search and context retrieval.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Arcrift — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Arcrift when development work is spread across browser chats and coding assistants, and you want to retain project context between those sessions.

Who it is for

  • Developers who want project decisions from browser AI chats available to coding assistants.
  • People using supported browser chat services alongside Claude Code, Cursor, Windsurf or Claude Desktop.
  • Developers seeking an open-source, locally oriented memory layer.

Documented uses

  • Save a browser AI conversation under a project name.
  • Keep earlier project decisions searchable in a local knowledge graph.
  • Pass stored conversation context to a coding assistant through MCP.
  • Reduce repeated explanations when continuing AI-assisted development across tools.
Before you choose

Requirements & limits

The repository identifies Arcrift as MIT-licensed open-source software. The desktop setup documentation names Node.js and Ollama as prerequisites. No subscription is claimed in the project README.

  • Browser capture requires the Arcrift backend to be running.
  • The browser extension and MCP server are distinct components with separate setup paths.
  • The MCP server communicates over stdio and can initialize its own storage connection without an HTTP backend.
  • The repository documents Node.js, Ollama, a local SQLite knowledge graph and a TypeScript implementation.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Connect Arcrift’s MCP server to a coding assistant

Build the backend MCP server and add its path to an AI tool’s configuration.

Before you start

  • Node.js and npm
  • The Arcrift repository
  • Claude Desktop, Claude Code or Cursor

Steps

  1. From the backend directory, run the command below and the command below.

    Documented command
    npm install
    Documented command
    npm run build

  2. Run the command below from the backend directory to print a configuration block with resolved paths.

    Documented command
    npm run mcp:config

  3. Add the server configuration to Claude Desktop or Cursor, or use the documented claude mcp add command for Claude Code.

Expected outcome

The coding assistant is configured to connect to Arcrift’s MCP server, which communicates over stdio.

Guide limitations

  • The documented setup describes configuration, not a tested connection or successful retrieval.
  • The MCP server initializes its own storage connection; an HTTP backend is not required for this mode.
Documentation 1 ↗
Source-based practical guide

Install the browser extension and save a chat

Install the extension and save a conversation from a supported browser chat service.

Before you start

  • The Arcrift backend running, such as through the desktop app
  • A supported browser chat service
  • For Chrome, Edge or Brave, the extension ZIP from GitHub Releases; for Firefox, the signed XPI

Steps

  1. For Chrome, Edge or Brave, extract the downloaded ZIP to a permanent folder, open chrome://extensions, enable Developer mode and select Load unpacked.

  2. For Firefox, drag the downloaded XPI into the open browser and confirm Add.

  3. Open Claude, ChatGPT, Gemini, DeepSeek, Grok, Copilot or Mistral; use the Arcrift popup to enter a project name and select Save Chat.

Expected outcome

The chat is saved under the named project, and the README says auto-connect activates immediately.

Guide limitations

  • The extension requires the Arcrift backend to be running.
  • The guide describes saving chats, not verification of later retrieval.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
ArcriftSave a browser AI conversation under a project name.Browser Extension, Desktop, Self-hostedThe repository identifies Arcrift as MIT-licensed open-source software. The desktop setup documentation names Node.js and Ollama as prerequisites. No subscription is claimed in the project README.
Continuum — pouyahasanamrejiStore project lessons so coding agents can retrieve them across conversations.CLI, Self-hosted, ServerThe repository documents local Docker Compose and bare-metal development setups. Bare-metal startup requires Node 22.12.0 or later and pnpm 10.33 or later; the Compose path skips these host prerequisites.
HaftRecord the problem a project is solving and the options considered.CLI, Self-hosted
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
Eshaan-Nair/ArcRift · Official homepage title · retained in its source language
How we review sourcesSuggest a correction