Bastra Recall
About
Persistent memory for any AI assistant — Claude, ChatGPT, Cursor — backed by your local Obsidian vault. One daemon, all your tools.
Details
- Author
- n0mad-ai
- Downloads
- 286
- Categories
- AI, Knowledge Base, Search, Productivity
Jump to
- 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
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Bastra RecallCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"bastra recall": {
"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"
}
}
}
}
}
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"
}
}
}
bastra-recall is a persistent memory layer that works across every AI surface — Claude (Code, Desktop, Web via Custom Connector), ChatGPT (via Custom GPT Actions over HTTP), Cursor, and anything else that speaks MCP or HTTP.
One local daemon serves all your AI tools at once. The vault is a folder of plain markdown files with YAML frontmatter — Obsidian-compatible, editable by hand, sync-friendly (iCloud / Google Drive / Dropbox).
Saves autonomously when a lesson is learned. Recalls before acting via PreToolUse and SessionStart hooks (Claude Code). Hybrid BM25 + vector search with the recall_when field as highest-weighted trigger — much better recall semantics than embed-everything approaches.
Memory types are typed (lesson, decision, preference, project-fact, workflow) with type-specific expiry defaults. Scope-based isolation per project. Wikilinks in bodies auto-mirror to a related[] graph.
MIT licensed, BYOK. Pre-alpha.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.


