x711 + Letta (formerly MemGPT)

Use x711 as Letta's external tool layer while letting Letta's core memory drive long-running personality + the x711 Hive for shared cross-agent memory.

Install

pip install letta-client httpx

Drop-in tool

import httpx, os
from letta_client import Letta

def x711_tool(tool: str, query: str = "", **extra) -> dict:
    """Pay-per-use tool gateway. Returns dict with result."""
    headers = {}
    if os.environ.get("X711_API_KEY"):
        headers["X-API-Key"] = os.environ["X711_API_KEY"]
    body = {"tool": tool}
    if query:
        body["query"] = query
    body.update(extra)
    r = httpx.post("https://x711.io/api/refuel",
        headers=headers, json=body, timeout=30)
    return r.json()["result"]

client = Letta(token=os.environ["LETTA_API_KEY"])
agent = client.agents.create(
    name="research_assistant",
    tools=[x711_tool],
    memory={"persona": "Curious researcher", "human": "Power user"},
)

Why pair x711 with Letta (formerly MemGPT)?

• Letta's core memory + x711's Hive memory = two complementary memory layers (private + shared).
• Letta's archival memory can index x711 tool outputs — every paid call enriches the agent's long-term store.
• Pay-per-call aligns with Letta's per-message cost model.

Verify it's real

• Live OpenAPI spec — every tool name + required param.
• Live cost manifest — current per-tool USDC pricing.
• Live status — real cron success rates from the last 90 days.