Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.plyra.dev/llms.txt

Use this file to discover all available pages before exploring further.

By default, plyra-memory runs entirely locally. Server mode connects the library to a running plyra-memory-server instance, enabling:
  • Multi-agent memory sharing — multiple agents share a memory space
  • Multi-tenant isolation — each API key has its own isolated workspace
  • Cross-process recall — memory survives process restarts and redeploys
  • Centralised management — one server, multiple teams or customers

​
Connect

Set two environment variables: 
export PLYRA_SERVER_URL=https://plyra-memory-server.politedesert-a99b9eaf.centralindia.azurecontainerapps.io
export PLYRA_API_KEY=plm_live_your_key_here
No code changes. The library detects PLYRA_SERVER_URL and routes all remember(), recall(), and context_for() calls to the server. 
# Exactly the same code — works in local and server mode
async with Memory(agent_id="support-agent") as mem:
    await mem.remember("User opened ticket #4821")
    ctx = await mem.context_for("recent user issues")

​
When to use server mode

SituationMode
Single agent, developmentLocal
Single agent, productionLocal or server
Multiple agents sharing memoryServer required
Multiple teams or customersServer required
Need cross-process recall without file sharingServer

​
Get an API key

Generate an API key

Create a live API key in seconds. Shown once — store it securely.

​
Test the connection

import asyncio
from plyra_memory import Memory

async def test():
    async with Memory(agent_id="test") as mem:
        await mem.remember("connection test")
        ctx = await mem.context_for("connection test")
        print("Connected:", ctx.content)

asyncio.run(test())

​
Switching between modes

# Local mode (default — no env vars needed)
unset PLYRA_SERVER_URL

# Server mode
export PLYRA_SERVER_URL=https://...
export PLYRA_API_KEY=plm_live_...
Your code is identical in both modes.