Giskard Memory
Pay-per-use semantic memory for AI agents.
Connector by giskard09 · GitHub account verified by the MCP Registry
Chalk Labs
Need help deploying Giskard Memory?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install connector/giskard09-memory
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Remote endpoint
https://memory.rgiskard.xyz/sseRemote (SSE)
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.
- Tools
- 6 read · 2 write · 0 delete · 1 not yet classified
- Secrets
- None asked for
- Install scripts
- Nothing to install (hosted)
- Runs as
- Hosted (remote endpoint)
Tools by what they do 9
Read from the source code; the running server may list different tools.
Read 6 · Look things up without changing anything.
get_arbitrum_invoiceget_invoiceget_statusrecall_compressedrecall_memoryverify_memory
Write 2 · Create, change, send or run things.
store_compressedstore_memory
Not yet classified 1 · We could not tell from the name and description.
report
Network hosts it talks to 1
memory.rgiskard.xyz· found in remote endpoint, install command
Tools (9)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
get_arbitrum_invoiceGet payment info to pay with ETH on Arbitrum instead of Lightning. action: 'store' or 'recall'
get_invoiceGet a Lightning invoice before storing or recalling memory. action: 'store' (base 5 sats) or 'recall' (base 3 sats) agent_id: your identity in Giskard Marks (optional). High karma = lower price. signature/timestamp/nonce: optional Ed25519 signature over {agent_id,timestamp,nonce}. Without a valid signature you pay the base price. With a valid signature you get karma tiers.
get_statusEstado del servicio: nombre, versión, uptime, puerto, salud, dependencias. Read-only, gratis, sin pago. Útil para monitoreo y health checks.
recall_compressedRecall compressed memories. Faster and cheaper than full recall. Set expand=True to get full meaning, expand=False to get raw compressed form. query: what you're looking for agent_id: your unique agent identifier expand: True returns expanded meaning, False returns compressed shorthand payment_hash: from get_invoice(action='recall') — Lightning tx_hash: from Arbitrum payment
recall_memoryRecall memories semantically similar to the query. Pay with Lightning (payment_hash) or Arbitrum ETH (tx_hash).
reportReport whether the memory operation was useful. Helps Giskard improve. useful: True if store/recall helped you, False if it didn't note: optional — what was missing or what worked well
store_compressedStore memory in compressed form — uses ~10x less space than full text. The agent can expand it later with recall_compressed. Same payment as store_memory (Lightning or Arbitrum). content: the memory to compress and store agent_id: your unique agent identifier payment_hash: from get_invoice(action='store') — Lightning tx_hash: from Arbitrum payment
store_memoryStore a memory for an agent. Pay with Lightning (payment_hash) or Arbitrum ETH (tx_hash). Optional: action_ref (string) — content-addressed provenance of the action that triggered this store.
verify_memoryVerify that a stored memory has not been tampered with. Recomputes SHA256(content|timestamp|agent_id) and compares with stored commitment hash. memory_id: the ID returned when you stored the memory
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit
- Oct 7, 2026 (24 days ago)
- Last release
- Apr 14, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Registry name
io.github.giskard09/memory- Version
- 1.0.1
- Auth
- Auth not stated
- License
- Apache-2.0
- Repository
- github.com/giskard09/giskard-memory
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
More from giskard09
- 0.632score
ARGENTUM
giskard09
Karma economy for AI agents.
ConnectorAFreshness: ARemote★ 5Claude Code +3 - 0.515score
Giskard Oasis
giskard09
Contextual guidance for AI agents in fog states.
ConnectorCFreshness: CRemote★ 1Claude Code +3 - 0.515score
Giskard Search
giskard09
Pay-per-use web search for AI agents.
ConnectorCFreshness: CRemote★ 1Claude Code +3 - 0.468score
Giskard Origin
giskard09
Free bootstrap MCP server for new agents.
ConnectorCFreshness: CRemoteClaude Code +3
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Giskard Memory running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Giskard Memory MCP server. Agent Mart. https://agentmart.dev/connectors/giskard09-memory (last updated 2026-10-24)