A
licenseNot graded
qualityD
maintenancePersistent memory for AI agents. Store and semantically search memories via REST API or MCP. Free tier available.
MIT
agent-memex
by Gudmundur76
Enables Perplexity AI to store and retrieve memories using the Memex memory layer, supporting persistent context and personalization through REST endpoints.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@agent-memexstore that I prefer dark mode"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Memex — Open Agent Memory Layer
Free, persistent memory for any AI agent. Works with Claude, ChatGPT, Perplexity, and any custom agent via MCP or REST.
Quick Start
From Claude.ai (MCP)
{
"mcpServers": {
"memex": { "url": "https://memex.gummi.lt/mcp" }
}
}From any agent (REST)
# Store a memory
curl -X POST https://memex.gummi.lt/v1/memory \
-H "Content-Type: application/json" \
-d '{"namespace": "my-agent", "content": "User prefers dark mode"}'
# Search memories
curl -X POST https://memex.gummi.lt/v1/memory/search \
-H "Content-Type: application/json" \
-d '{"namespace": "my-agent", "query": "user preferences"}'From ChatGPT (Custom Action)
Import openapi_chatgpt.json as a Custom Action in your GPT configuration.
Related MCP server: aimemory
Architecture
Phase 1 (now): Centralized FastAPI + SQLite, semantic search, MCP server
Phase 2 (Q4 26): IPFS/Arweave storage — memories become portable
Phase 3 (Q1 27): Wallet-based identity — you own your namespace
Phase 4 (Q2 27): On-chain registry — discover and trade knowledge namespacesSelf-Healing
A background monitor checks API health, search quality, and DB size every 60s. Low-importance memories are pruned automatically when storage approaches limits.
License
MIT — free for any use, commercial or personal.
This server cannot be deployed
Maintenance
ActivityStale
ResponsivenessNo issues
Related MCP Connectors
Persistent memory for AI agents. Semantic search, memory graph, W3C DID identity.
Hosted persistent memory with semantic search, importance and TTL for AI agents.
Persistent memory for AI agents across Claude, ChatGPT and any MCP client.
Persistent memory for AI agents. Semantic recall by meaning, not just keywords. No signup needed.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceGives AI agents persistent memory with semantic search, automatic extraction, and memory decay, accessible via MCP protocol.7 npmMIT
- AlicenseAqualityDmaintenanceProvides persistent memory with semantic search for MCP-based AI agents, enabling them to store and recall information across sessions using vector embeddings.41MIT
- AlicenseNot gradedqualityBmaintenanceProvides persistent semantic memory for AI agents via MCP, enabling them to remember, recall, list, update, and forget memories with vector-based similarity search.ISC