I Built a Cross-Client Memory Hub for AI Agents — Here's What I Learned

Описание и применение

MemTether объединяет 23+ ИИ-клиента в одну локальную базу SQLite, устраняя облачные расходы и улучшая контекст. Бенчмарки показывают 62.6% точного совпадения и 54.6% LLM-оценки.

Задача

AI tools each maintain separate memory; switching tools causes loss of context.

Результат

MemTether enables 23+ AI clients to share a single memory store, eliminating cloud costs and improving context continuity. Benchmarking shows 62.6% strict match and 54.6% LLM judge on LongMemEval, with multi-session improvements via E-Hybrid method.

Рабочий процесс

• Identify that all AI tools run on the same machine
• Create a local SQLite database to store memories
• Configure each AI client to point to the shared database
• Implement supersession logic to avoid deletion
• Add bi-temporal timestamps (valid and recorded times)
• Introduce Q-Value to rank frequently used memories
• Blend four re-ranking factors (semantic similarity, recency, usage frequency, type importance)
• Use SQLite triggers for FTS5 sync instead of Python code
• Package the engine as a pip installable wheel with console entry points
• Publish on GitHub and PyPI

Доказательства

I built MemTether — a local-first memory hub that lets 23+ AI clients share one physical SQLite database.

Источник

Existing memory solutions (mem0, cognee, zep) all treat memory as a service. You send memories to their cloud API, they store and retrieve them.

Источник

No cloud. No API fees. No abstraction layer. One memory.db, 23 clients reading and writing to it.

Источник

I ran LongMemEval (500 questions, full run): Strict match 62.6%, LLM judge 54.6%.

Источник