Skip to main content

Documentation Index

Fetch the complete documentation index at: https://astron-bb4261fd.mintlify.app/llms.txt

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

Quickstart

This page is a stub while the MVP is being built. The final quickstart will ship in Week 6 of Phase 1. For now, here is the shape of the developer experience we are targeting.

1. Install the SDK

pip install z3rno

2. Start a local Z3rno instance (optional)

If you want to run Z3rno locally instead of using the managed cloud:
git clone https://github.com/the-ai-project-co/z3rno-server
cd z3rno-server
docker compose -f docker-compose.dev.yml up
# Server at http://localhost:8000

3. Store and recall your first memory

from z3rno import Z3rnoClient

client = Z3rnoClient(
    base_url="http://localhost:8000",      # or https://api.z3rno.dev
    api_key="z3rno_sk_test_localdev",
)

# Store a memory
memory = client.store(
    agent_id="agent-1",
    content="User prefers dark mode and uses Python.",
    memory_type="semantic",
)

# Recall memories
results = client.recall(
    agent_id="agent-1",
    query="What does the user prefer?",
    top_k=5,
)

for r in results:
    print(r.content, "(relevance:", round(r.relevance_score, 2), ")")

Next steps

Core Concepts

Understand the four memory types, the lifecycle, and how temporal versioning works.

Framework Integrations

Drop Z3rno into LangChain, CrewAI, OpenAI Agents, or Claude via MCP.