pymentisdb 0.9.0

Python client for MentisDB - semantic hash-chained memory for agents

pymentisdb

Official Python client for MentisDB — a durable semantic memory engine for AI agents.

Installation

pip install pymentisdb

With LangChain integration:

pip install pymentisdb[langchain]

Quick Start

from pymentisdb import MentisDbClient, ThoughtType

client = MentisDbClient()

# Append a thought
thought = client.append_thought(
    thought_type=ThoughtType.INSIGHT,
    content="Rate limiting is the real bottleneck."
)
print(f"Appended: {thought.id}")

# Semantic search
results = client.ranked_search(text="performance optimization")
for hit in results.results:
    print(f"[{hit.score.total:.3f}] {hit.thought.content}")

# Context bundles
bundles = client.context_bundles(text="cache invalidation", limit=5)

LangChain Integration

from pymentisdb import MentisDbMemory
from langchain_openai import ChatOpenAI

memory = MentisDbMemory(
    chain_key="my-project",
    agent_id="assistant"
)

llm = ChatOpenAI(model="gpt-4")
chain = llm.with_memory(memory)

Configuration

# Remote server
client = MentisDbClient(base_url="http://my.mentisdb.com:9472")

Full Documentation

• MentisDB documentation
• REST API reference
• Python client guide