Tier 3 · Agent memory Agent memory · fetched 2026-07-02

Memosynth Lite

A lightweight memory ingestion pipeline that processes JSON memory logs through summarization and deduplication, then fans out to three backends: a vector DB (Qdrant), a relational timeline (DuckDB), and a memory graph (Neo4j).

View source on GitHub

Key takeaways

01
Ingestion pipeline: summarize and dedupe BEFORE storing
02
Tri-store fan-out shows one memory feeding vector, timeline, and graph views

Flows built on this research

Memory & Context

Memory Recall: Ranking and Relevance

Make recall surface the right memories: hybrid lexical+semantic search, rank fusion, and explainable retrieval.

4 steps · 90-120 minutes

From the archive

Verbatim excerpts mined from our local archive of this repository — the prompts, schemas, and patterns worth stealing.

Memory

A memory record schema with confidence and sensitivity

{
  "id": 1,
  "content": "Today I learned about vector databases and Qdrant.",
  "project": "demo_project",
  "agent": "doc_bot",
  "summary": "Client asked about margin drop in Q2.",
  "type": "insight",
  "tags": ["finance", "Q2", "risk"],
  "source": "Earnings_Report_Q2.pdf",
  "author": "doc_bot",
  "created_at": "2025-06-19",
  "version": 1,
  "confidence": 0.9,
  "visibility": "project",
  "sensitivity": "medium"
}

A memory entry schema worth copying: versioning, confidence scores, visibility scoping, and sensitivity labels on every stored fact - backed by a Qdrant + DuckDB + Neo4j triple store.

config/sample_memory.json