agenticmemory-sdk 1.0.0

Official Python SDK for Agentic Memory — 3-tier persistent memory for AI agents. Short-term recall, semantic search, and auto-summarised knowledge in one API.

agenticmemoryai

Official Python SDK for Agentic Memory. Give your AI agents persistent memory in one line.

Install

pip install agenticmemoryai

Quick Start

from agenticmemoryai import AgenticMemory

memory = AgenticMemory(api_key="amk_your_key")

# Store a message
memory.store("your-space-id", role="user", content="Hello!")

# Recall recent messages
messages = memory.recall("your-space-id", limit=20)

# Search by meaning (Pro plan)
results = memory.search("your-space-id", "pricing discussion")

Features

• Short-term memory — instant recall, sub-millisecond reads
• Medium-term memory — search past conversations by meaning
• Long-term memory — auto-summarised knowledge across months

API

• store(space_id, role, content) — append a message
• recall(space_id, limit) — get recent messages
• search(space_id, query, scope, tags) — semantic search
• set_context(space_id, key, value) — set key-value context
• get_context(space_id, key) — get context value
• add_entry(space_id, type, title, content, tags) — append entry
• bootstrap(space_id, ...) — load full context in one call
• set_shared(space_id, key, value) — shared world memory
• create_space(name, slug) — create a memory space

Get an API key

Sign up free at agenticmemory.ai. 1,000 messages/month on the free tier.

Links

• Quick Start Guide
• API Docs
• Pricing

Acknowledgements

The structured memory architecture was influenced by work from the h-network community by Halil Baysal.

License

Proprietary — Tyga.Cloud Ltd. See LICENSE file.