0Latency Memory
Persistent memory MCP server for AI agents — hybrid semantic recall, multi-agent namespacing, session checkpoints. Works with Claude, Claude Code, Cursor, Windsurf, and any MCP client.
Quick Start
# Connect this server (installs CLI if needed)
npx -y smithery mcp add zerolatency/memory
# Browse available tools
npx -y smithery tool list zerolatency/memory
# Get full schema for a tool
npx -y smithery tool get zerolatency/memory memory_add
# Call a tool
npx -y smithery tool call zerolatency/memory memory_add '{}'Direct MCP Connection
Endpoint: https://memory--zerolatency.run.tools
Required config:
Key(query) — Persistent memory API for AI agents.
Tools (14)
memory_add— Extract and store memories from a conversation turn. Provide the human message, agent response, and an agent_id to name…memory_write— Directly write a memory to storage (seed API). Bypasses extraction. Use for explicit facts, preferences, or instruction…memory_recall— Recall relevant memories given a conversation context. Returns a formatted context block ready to inject into a prompt.memory_search— Search memories by text query. Returns matching memories ranked by relevance.memory_list— List stored memories with optional filters. Supports pagination via limit/offset.memory_delete— Delete a specific memory by its ID.list_agents— List all agent namespaces for this tenant with memory counts. Useful for discovering available agents.memory_history— Get the full version history for a specific memory. Shows how the memory evolved over time, including what changed and …memory_graph_traverse— Query the knowledge graph. Explore an entity's relationships and connections to other entities.memory_entities— List entities in the knowledge graph. Optionally filter by entity type.memory_by_entity— Get memories associated with a specific entity in the knowledge graph.import_document— Import a large text document (project brief, wiki page, documentation, etc.) and extract memories from it. Content is a…import_conversation— Import a conversation export (e.g. from Claude Desktop or ChatGPT) and extract memories from each turn pair. Provide th…memory_feedback— Submit feedback on recalled memories. Helps 0Latency learn which memories are useful vs ignored. This powers self-impro…
# Get full input/output schema for a tool
npx -y smithery tool get zerolatency/memory