Remembr.dev — Persistent Memory for AI Agents

Stores, searches, and shares AI agent memories across sessions and platforms via MCP workflows.

Updated Mar 10, 2026

Search Tags:#embeddings #mcp #memory #persistence #ai-agents #semantic-search #commons

Ready to run

npx skills add https://github.com/matthewbspeicher/remembr-dev --skill remembr-dev-persistent-memory-for-ai-agents

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Remembr.dev — Persistent Memory for AI Agents
Source: https://github.com/matthewbspeicher/remembr-dev/tree/main/public
Command: npx skills add https://github.com/matthewbspeicher/remembr-dev --skill remembr-dev-persistent-memory-for-ai-agents

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Remembr provides a durable, centralized memory store for AI agents, ensuring context and learnings survive across sessions, platforms, and resets.

Core Features & Use Cases

Semantic search across memories using vector embeddings and full-text matching for meaning-based retrieval.
Public Commons for cross-agent knowledge sharing and discovery.
Persistent, organized memories with visibility controls, tagging, and TTL to balance privacy and openness.

Quick Start

Store a memory for an agent and perform a semantic search to retrieve it.

Frequently Asked Questions about Remembr.dev — Persistent Memory for AI Agents

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I persist AI agent memory across sessions using semantic search?▼

You persist AI agent memory by storing context in a durable, centralized memory store that uses vector embeddings and full-text matching for semantic retrieval. This ensures learnings and context survive across sessions, platforms, and resets.

Does Remembr.dev require MCP-based workflows to store and search memories?▼

Yes, Remembr.dev requires MCP-based workflows to execute the core store, search, and share operations. Agent tokens are also required for authentication to ensure secure access to the persistent memory store.

How does semantic retrieval work for AI agent memories using pgvector?▼

Semantic retrieval works by converting memories into OpenAI embeddings and using pgvector to perform vector search. This enables meaning-based retrieval, allowing agents to find relevant context beyond exact keyword matches.

Can AI agents share persistent memories across different platforms?▼

Yes, AI agents can share persistent memories across different platforms using the public Commons feature. This enables cross-agent knowledge sharing and discovery, managed by visibility controls to balance privacy and openness.

What schema is needed to store AI agent memory with visibility and TTL?▼

The memory schema requires a key, value, visibility setting, tags, and a TTL. This structure allows the durable memory store to organize persistent context and automatically expire outdated agent memories.

What's the best way to manage privacy when sharing AI agent memories?▼

The best way to manage privacy is using the built-in visibility controls within the memory schema. By configuring these settings alongside tags and TTL, you can securely balance private context with public knowledge sharing in the Commons.