[Trend Scout] RMANOV/sqlite-memory-mcp

[github-actions]

🔭 Trend Scout: RMANOV/sqlite-memory-mcp

Auto-generated by trend-scout.py — review and edit as needed.

📌 What problem it solves

SQLite-backed MCP Memory Server with WAL concurrent safety, FTS5 search, session tracking, task management, and cross-machine bridge sync

📅 Timeline

Field	Value
Created	2026-03-01
Last pushed	2026-04-25
Stars	8
Forks	3
Open issues	0
License	MIT
Language	Python
Topics	ai-memory, claude, claude-code, concurrent, fts5, full-text-search, knowledge-graph, llm, llm-memory, mcp, mcp-server, memory-server, model-context-protocol, persistent-memory, python, session-tracking, sqlite, wal-mode

✅ Strengths

• Well-tagged: ai-memory, claude, claude-code, concurrent, fts5, full-text-search
• Primary language: Python
• Actively maintained (pushed within 30 days)

⚠️ Weaknesses / Risks

• Low star count (8) — limited community validation

💡 What this repo can learn

• Claude Code session patterns: this repo's Claude Code integration approach could improve claude-adapter.py's JSONL parsing — e.g., handling new session event types or extracting richer metadata from Claude Code tool-use blocks
• Hybrid FTS+semantic retrieval: combining keyword and embedding-based search could improve recall in query-session.py / briefing.py — e.g., a query for 'docker networking' would also surface entries tagged 'container' or 'network_mode' even without exact term overlap
• Graph-based knowledge linking: a relation graph over session entries could let briefing.py surface related decisions and mistakes by topic proximity — e.g., linking a mistake:auth record to pattern:jwt across separate session files without requiring identical keywords
• Automated knowledge consolidation: a background consolidation pass (like this repo's dream command) could extend extract-knowledge.py to merge near-duplicate learnings and flag contradicting patterns discovered across sessions
• Zero-config install UX: install.py / setup-project.py could adopt a single-command bootstrap pattern (similar to this repo's one-command install) to lower the setup barrier when onboarding new machines or environments

README excerpt

# SQLite Memory MCP Server

## Technical deep-dives

- **Medium:** [The Amnesiac That Learned to Remember](https://medium.com/@r.manov/the-amnesiac-that-learned-to-remember-4fe4342db89d)
- **Dev.to:** [The Amnesiac That Learned to Remember — Building a Brain for Claude Code](https://dev.to/ruslan_manov/the-amnesiac-that-learned-to-remember-building-a-brain-for-claude-code-1ok6)
- **Dev.to:** [How a SQLite WAL Fix Grew into a 54-Tool MCP Memory Stack](https://dev.to/ruslan_manov/how-a-sqlite-wal-fix-grew-into-a-54-tool-mcp-memory-stack-4nkl)

[![CI](https://github.com/RMANOV/sqlite-memory-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/RMANOV/sqlite-memory-mcp/actions/workflows/ci.yml)

A production-quality SQLite-backed MCP Memory stack with WAL concurrent safety (10+ sessions), FTS5 BM25 search, session tracking, task management, bridge sync, collaboration workflows, and a native system tray task manager.

Drop-in compatible with `@modelcontextprotocol/server-memory` for the core 9 knowledge-graph tools, with 47 additional tools split across companion FastMCP micro-servers for sessions, tasks, bridge sync, collaboration, entity linking, and intelligence workflows (56 OSS tools total). Includes a PyQt6 desktop app for visual task management and standalone automation scripts.

## Why SQLite?

Existing MCP memory servers use JSONL files, cloud APIs, or heavyweight databases. Each has trade-offs that hurt real-world Claude Code usage:

- **JSONL files** (official MCP

*(truncated)*

---

Scouted on 2026-04-27 · View on GitHub

[magicpro97]

Closing this old Trend Scout report because it was generated by the previous heuristic-only pipeline and is too repetitive / low-signal to be actionable.

This repo now has the improved Trend Scout flow with GitHub Models-backed analysis. If this target repo is still worth evaluating, we should re-scout it with the new pipeline instead of keeping the old report open.