Back to directory

Arra Oracle V3

A local memory and search layer that stores notes in SQLite and exposes full-text and vector-capable search over them through HTTP, MCP, a CLI and a web UI.

Arra Oracle V3

Arra Oracle runs as a single Docker container needing no separate Bun install, API key, schema choice or vector service. A mine command indexes Markdown, MDX and plain text files from a chosen folder using deterministic IDs, so re-running it safely skips files that have not changed, and a built-in Simple Mode web interface shows health information alongside save and search actions.

An HTTP API supports both plain full-text search and a grounded 'ask' endpoint that can return citations, or stay purely extractive and local when asked to. A separate stdio Docker image exposes the same memory as Model Context Protocol tools to a desktop app or agent, sharing the same underlying Docker volume as the HTTP server, so a client such as Claude Code can be configured to add it directly as an MCP server. It is written in TypeScript.

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.