Back to directory

ArcRift

A local-first memory layer that captures conversations from browser AI chats such as Claude or ChatGPT and from MCP-connected coding tools such as Cursor, builds a searchable local knowledge graph, and injects relevant context into new prompts either way.

ArcRift

ArcRift installs as a browser extension that captures conversations from Claude, ChatGPT, Gemini, DeepSeek, Grok, Copilot or Mistral, and as a native MCP server that connects to coding tools such as Claude Code, Cursor, Windsurf or Claude Desktop. It extracts structured facts from captured conversations into a local SQLite-backed knowledge graph, embeds them as searchable vectors, and automatically prepends the most relevant context to a new prompt in whichever tool the user is working in, so context from a browser chat is available in an IDE agent and vice versa.

It runs entirely on the user's own machine, with no cloud service or subscription, and installs with a single setup command. The project has been rebranded from two earlier names, and installing it requires Node.js and, for local model features, Ollama already installed.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.