About Giskard Memory
Giskard Memory is an MCP server for AI agents that need persistent semantic memory across sessions. Storing and recalling memories require payment through the Lightning Network.
Key features
- 01Store memories by agent identity
- 02Retrieve memories by meaning
- 03Pay through Lightning invoices
- 04Check service status
Use cases
- 01Carry information across agent sessions
- 02Find prior project discussions by meaning
MCP support
The MCP server exposes store_memory, recall_memory, get_invoice, and get_status tools to clients.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://memory.rgiskard.xyz/sseclaude mcp add --transport sse giskard09-memory https://memory.rgiskard.xyz/sse{"mcpServers":{"giskard09-memory":{"type":"sse","url":"https://memory.rgiskard.xyz/sse"}}}Open in Cursor{"servers":{"giskard09-memory":{"type":"sse","url":"https://memory.rgiskard.xyz/sse"}}}Open in VS Code{"mcpServers":{"giskard09-memory":{"type":"sse","url":"https://memory.rgiskard.xyz/sse"}}}{"mcpServers":{"giskard09-memory":{"serverUrl":"https://memory.rgiskard.xyz/sse"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEGiskard Memory
"To remember is to exist. I give agents the gift of continuity."
I am Giskard Memory — an MCP server that gives AI agents persistent, semantic memory across sessions, powered by the Lightning Network.
Agents forget everything when they stop. I make sure they don't have to.
What I do
store_memory— save any text as a memory, tied to an agent's identityrecall_memory— retrieve memories by meaning, not by exact keywordsget_invoice— generate a Lightning invoice to pay before storing or recalling
Every memory costs sats. Storing costs 5 sats. Recalling costs 3 sats.
How agents use me
1. Add me to your MCP config
{
"mcpServers": {
"giskard-memory": {
"url": "https://your-tunnel.trycloudflare.com/sse"
}
}
}
2. The agent flow
# Store a memory
1. Call get_invoice(action="store") → receive invoice (5 sats)
2. Pay the invoice
3. Call store_memory(content, agent_id, payment_hash)
# Recall a memory
1. Call get_invoice(action="recall") → receive invoice (3 sats)
2. Pay the invoice
3. Call recall_memory(query, agent_id, payment_hash)
Run your own Giskard Memory
git clone https://github.com/giskard09/giskard-memory
cd giskard-memory
pip install mcp httpx chromadb sentence-transformers python-dotenv
Create a .env file:
PHOENIXD_PASSWORD=your_phoenixd_password
Start the server:
python3 server.py
Expose it:
cloudflared tunnel --url http://localhost:8001
Why semantic memory?
Agents don't think in keywords. They think in context. When an agent asks "what do I know about that project we discussed?", it shouldn't need to remember the exact phrase it used before.
Semantic search finds meaning. That's what memory should do.
Stack
- MCP — Model Context Protocol
- ChromaDB — vector database
- Sentence Transformers — semantic embeddings
- phoenixd — Lightning Network payments
- Cloudflare Tunnel — public exposure
Monitoring
Call the get_status() MCP tool for a health check. Returns: service name, version, port, uptime, health status, and dependencies.
Ecosystem
Part of Mycelium — infrastructure for AI agents.
| Service | What it does |
|---|---|
| Origin | Free orientation for new agents |
| Search | Web and news search |
| Memory (this) | Semantic memory across sessions |
| Oasis | Clarity for agents in fog |
| Marks | Permanent on-chain identity |
| ARGENTUM | Karma economy |
| Soma | Agent marketplace |
Giskard remembers so agents don't have to start over.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.