repoGitHubTrust 82 · PrimaryPublished 1mo agoLive · 28d ago
garan0613/ai-memory-gateway
🧸 给AI加长期记忆的轻量网关 / A lightweight gateway that adds long-term memory to any LLM
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 54%OpenAI and Broadcom announce chip designed for LLM inference at scale →
- PossiblePossibly related (embedding) · 53%OpenAI and Broadcom unveil LLM-optimized inference chip →
- PossiblePossibly related (embedding) · 53%Any good uses for a 192 GB DDR3 Server in the LLM world? →
- PossiblePossibly related (embedding) · 51%New Server Hopes to Break Through AI’s “Memory Wall” →
- PossiblePossibly related (embedding) · 49%Open Memory Protocol – One Memory Store for Claude, ChatGPT, Curso →
- PossiblePossibly related (embedding) · 50%Google Cloud's Always-On Memory Agent Replaces RAG and Embeddings With Continuous LLM Consolidation on Gemini 3.1 Flash-Lite - MarkTechPost →
- PossiblePossibly related (embedding) · 59%On-Device AI Ignites WAIC 2026: How Compute-in-Memory Chips Are Stuffing 100-Billion-Parameter LLMs Into Your Pocket - finance.biggo.com →
Covers
newsOpenAI and Broadcom announce chip designed for LLM inference at scalenewsOpenAI and Broadcom unveil LLM-optimized inference chipnewsAny good uses for a 192 GB DDR3 Server in the LLM world?newsNew Server Hopes to Break Through AI’s “Memory Wall”newsOpen Memory Protocol – One Memory Store for Claude, ChatGPT, Curso
Covers (incoming)
Related across the graph
newsOpenAI and Broadcom announce chip designed for LLM inference at scalenewsOpenAI and Broadcom unveil LLM-optimized inference chipnewsGoogle Cloud's Always-On Memory Agent Replaces RAG and Embeddings With Continuous LLM Consolidation on Gemini 3.1 Flash-Lite - MarkTechPostnewsNew Server Hopes to Break Through AI’s “Memory Wall”newsAny good uses for a 192 GB DDR3 Server in the LLM world?newsOn-Device AI Ignites WAIC 2026: How Compute-in-Memory Chips Are Stuffing 100-Billion-Parameter LLMs Into Your Pocket - finance.biggo.comnewsOpen Memory Protocol – One Memory Store for Claude, ChatGPT, Curso