Bastra Recall

Name: Bastra Recall
Author: n0mad-ai

@n0mad-ai

About Bastra Recall

Persistent memory for any AI assistant — Claude, ChatGPT, Cursor — backed by your local Obsidian vault. One daemon, all your tools.

#memory #knowledge-base #obsidian #markdown #search #productivity #personal-knowledge #vault #claude #claude-code #cursor #chatgpt #hooks #rest-api #bm25 #vector-search #hybrid-search

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "bastra-recall": {
      "command": "node",
      "args": [
        "/abs/path/to/bastra-recall/packages/daemon/dist/mcp-forwarder.js"
      ],
      "env": {
        "BASTRA_VAULT_PATH": "/abs/path/to/your/vault/memorys"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Bastra Recall?

Bastra Recall is a persistent memory layer that works across multiple AI surfaces — Claude, ChatGPT, Cursor, and any tool that speaks MCP or HTTP. It runs as a single local daemon serving all AI tools at once, storing memories as plain markdown files with YAML frontmatter in an Obsidian-compatible vault.

How to use Bastra Recall?

Install the daemon locally and point it to a vault folder of markdown files. The server autonomously saves learned information and recalls relevant memories before actions via hooks like PreToolUse and SessionStart (Claude Code). No manual configuration steps beyond setup are described in the README.

Key features of Bastra Recall

Single daemon serves every AI tool simultaneously
Vault is a folder of plain markdown with YAML frontmatter
Hybrid BM25 + vector search with recall_when field weighting
Typed memories (lesson, decision, preference, project-fact, workflow)
Scope-based isolation per project
Wikilinks automatically build a related[] graph

Use cases of Bastra Recall

Maintain consistent context across Claude Code sessions
Share memory between ChatGPT, Cursor, and Claude Desktop
Keep project-specific facts isolated by scope
Edit and sync memories via iCloud / Google Drive / Dropbox

FAQ from Bastra Recall

How does Bastra Recall differ from embed-everything memory approaches?

Bastra Recall uses hybrid BM25 + vector search with the recall_when field as the highest-weighted trigger, providing much better recall semantics than approaches that embed everything.

Where does Bastra Recall store data?

All memories are stored locally in a user-specified folder of plain markdown files with YAML frontmatter. This vault is compatible with Obsidian and can be synced via iCloud, Google Drive, or Dropbox.

What runtime or dependencies are required?

Bastra Recall runs as a single local daemon. The README does not specify a particular language runtime or dependency list, but it communicates over MCP and HTTP.

Does Bastra Recall support authentication or bring your own key?

Yes, it is BYOK (bring your own key) and MIT licensed.

What transport protocols does Bastra Recall support?

It supports both MCP (Model Context Protocol) and HTTP, allowing integration with any AI surface that speaks either protocol.

Comments

More AI & Agents MCP servers

1MCP - One MCP Server for All

1mcp-app

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

468

MCP Client for Ollama (ollmcp)

jonigl

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

768