Giskard Memory

io.github.giskard09Published by GitHub account giskard09v1.0.1Updated Oct 24, 2026

Pay-per-use semantic memory for AI agents. SHA256 commitment, Ed25519 sig, Lightning.

The publisher's own server: Memory.fit

VerifiedSSEWeb executableFinanceKnowledge & Memory

Overview

AI-generated overview

Remote MCP server giving AI agents persistent semantic memory across sessions, with each store or recall paid for in Lightning sats.

What you can do
  • Store text as a memory tied to an agent identity
  • Recall memories by meaning rather than exact keywords
  • Generate a Lightning invoice before a store or recall
  • Report service health, version, uptime and dependencies
When to use it
Use it when an agent needs to carry context between sessions and semantic lookup by meaning is more useful than keyword search, and when paying small per-call Lightning fees is acceptable.
Requirements
A remote SSE endpoint (the README shows a tunnel URL in the MCP config). A Lightning wallet able to pay invoices, since storing costs 5 sats and recalling 3 sats. Self-hosting instead needs Python with mcp, httpx, chromadb and sentence-transformers, a phoenixd password in a .env file, and a tunnel for public exposure.
Before you install
Every store and recall costs sats, so an agent can spend money on its own; set spending limits. Memories are tied to an agent_id and sent to a third-party service, so avoid storing secrets or sensitive data. The README's example config points at a temporary tunnel URL rather than the advertised endpoint. Self-hosting requires a phoenixd password in a .env file.

Installation

In SourceWeft

  1. Open Giskard Memory in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via SSE. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.giskard09%2Fmemory/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "giskard-memory": {
      "type": "sse",
      "url": "https://memory.rgiskard.xyz/sse"
    }
  }
}

README

[CI] [License]

Giskard 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 identity
  • recall_memory — retrieve memories by meaning, not by exact keywords
  • get_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

json
{  "mcpServers": {    "giskard-memory": {      "url": "https://your-tunnel.trycloudflare.com/sse"    }  }}

2. The agent flow

# Store a memory1. Call get_invoice(action="store")   → receive invoice (5 sats)2. Pay the invoice3. Call store_memory(content, agent_id, payment_hash)
# Recall a memory1. Call get_invoice(action="recall")  → receive invoice (3 sats)2. Pay the invoice3. Call recall_memory(query, agent_id, payment_hash)

Run your own Giskard Memory

bash
git clone https://github.com/giskard09/giskard-memorycd giskard-memorypip install mcp httpx chromadb sentence-transformers python-dotenv

Create a .env file:

PHOENIXD_PASSWORD=your_phoenixd_password

Start the server:

bash
python3 server.py

Expose it:

bash
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


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.

ServiceWhat it does
OriginFree orientation for new agents
SearchWeb and news search
Memory (this)Semantic memory across sessions
OasisClarity for agents in fog
MarksPermanent on-chain identity
ARGENTUMKarma economy
SomaAgent marketplace

Giskard remembers so agents don't have to start over.

Source: README.md at commit fc6bcbd

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Memory integrations