MCP Hub
Back to servers

@git-fabric/aiana

A composable semantic memory layer that provides cross-project recall and session context using Qdrant and OpenAI embeddings. It enables users to securely store, search, and manage persistent memories with built-in secret scrubbing for privacy.

Updated
Feb 24, 2026

@git-fabric/aiana

Aiana memory fabric app — semantic memory, session context, and cross-project recall as a composable MCP layer.

Part of the git-fabric ecosystem.

Tools

ToolDescription
aiana_memory_searchSemantic search over stored memories
aiana_memory_addStore a new memory (auto-scrubbed for secrets)
aiana_memory_recallRecall top-N relevant memories for a project
aiana_memory_deletePermanently delete a memory by ID
aiana_memory_exportExport all memories as a JSONL-compatible array
aiana_memory_importImport memories from an exported array
aiana_session_listList sessions grouped by project
aiana_preference_addStore a user preference (type=preference memory)
aiana_memory_feedbackRecord helpfulness feedback on a recalled memory
aiana_statusCollection stats: count, by-project breakdown, model
aiana_healthPing Qdrant Cloud, return latency

Architecture

Follows the git-fabric layered pattern:

Detection / Query  →  layers/memories.ts (searchMemories, recallProjectContext)
Action             →  layers/memories.ts (addMemory, deleteMemory, import/export)
Sessions           →  layers/sessions.ts (read-only, derived from memory sessionIds)
Scrubbing          →  layers/scrub.ts (PII/secret redaction before embed+store)
Adapter            →  adapters/env.ts (Qdrant REST + OpenAI embeddings)
Surface            →  app.ts (FabricApp factory with 11 inline tools)

Zero footprint: no local state, no SQLite, no Redis. Qdrant Cloud is the only store.

Qdrant collection

PropertyValue
Collectionaiana_fabric__memories__v1
Dimensions1536
DistanceCosine
Embedding modeltext-embedding-3-small

Usage

Via gateway (recommended)

# gateway.yaml
apps:
  - name: "@git-fabric/aiana"
    enabled: true

Standalone MCP server

QDRANT_URL=https://xxx.qdrant.io:6333 \
QDRANT_API_KEY=your-key \
OPENAI_API_KEY=sk-... \
npx @git-fabric/aiana

Programmatic

import { createApp } from "@git-fabric/aiana";

const app = createApp();
// app.tools, app.health(), etc.

Environment Variables

VariableRequiredDescription
QDRANT_URLYesQdrant Cloud base URL (e.g. https://xxx.us-west-1-0.aws.cloud.qdrant.io:6333)
QDRANT_API_KEYYesQdrant Cloud API key
OPENAI_API_KEYYesOpenAI API key for text-embedding-3-small embeddings

Secret scrubbing

All content is scrubbed before embedding and storage. Redacted patterns:

  • GitHub tokens (ghp_, ghs_, github_pat_)
  • OpenAI keys (sk-...)
  • Bearer tokens in headers
  • JWT tokens (3-part base64)
  • Password patterns

License

MIT

Reviews

No reviews yet

Sign in to write a review