Implement federated long-term memory with semantic retrieval and read-only MCP search tools.
npx skills add https://github.com/drewid74/ai_skills --skill federated-memory
Please help me install this Agent Skill. Skill: federated-memory Source: https://github.com/drewid74/ai_skills/tree/main/federated-memory Command: npx skills add https://github.com/drewid74/ai_skills --skill federated-memory
Federated-memory helps an AI agent retain and recall important information across sessions by storing knowledge in a searchable memory system and enabling read-only sharing across multiple agents without unsafe write sharing.
Ask your AI to design a federated memory setup that uses pgvector for archival recall, deduplicates entries with content hashes, and exposes MCP tools for read-only cross-agent memory search.
High-intent search queries and answers about installing and using this skill.
Share long-term agent memory across sessions by implementing a federated memory architecture that uses read-only MCP tools for cross-agent retrieval, enforcing deduplication and retention policies to prevent conflicting writes.
Perform semantic retrieval for past conversations by routing memory through a tiered architecture that uses pgvector or Qdrant for fast similarity search, optionally adding a graph layer like Neo4j for multi-hop relationship queries.
Stop unbounded memory growth by applying retention policies and deduplicating stored knowledge bases using content hashing, ensuring only unique information is persisted during multi-agent sessions.
Yes, you can expose read-only MCP search tools to let multiple agents query the same federated memory, strictly prohibiting cross-agent write paths to avoid data conflicts and ensure safe knowledge retrieval.
Federated memory supports multi-hop relationship queries across agent domains by integrating an optional graph layer using FalkorDB or Neo4j alongside the primary vector store for complex semantic retrieval.
You need a tiered memory architecture when your multi-agent system must route information dynamically between working memory, semantic recall, and permanent archival knowledge to persist past decisions effectively.
ancolemanImplement vector databases for AI/ML semantic search and RAG systems.
datamonsterrDesign agent memory architectures with short-term context and long-term vector stores.
monktuiUnify fragmented memory backends into a single AgentDB layer with HNSW vector search.
Neuron-Mr-WhiteStore, retrieve, and organize persistent memories across sessions.
