Welcome to Hebbrix
Hebbrix gives your AI persistent memory. Build applications with memory that lasts, search across it, and automatic learning.
01. Why Hebbrix?
Traditional LLMs forget everything after each conversation. Hebbrix fixes this by providing a memory layer that stores, retrieves, and learns from every interaction. Your AI can now remember user preferences, past conversations, and build knowledge graphs that grow smarter over time.
Human-Like Memory
3-tier system (STM, MTM, LPM) mimicking how humans remember.
Smart Retrieval
Hybrid search finds exactly what you need, even from old conversations.
Drop-in Ready
Works with OpenAI, Anthropic, and any LLM. Just change the base URL.
02. Explore the API
Memory Management
Store, retrieve, and manage AI memories with a human-like 3-tier system.
Hybrid Search
5-layer search combining vector, BM25, and knowledge graph traversal.
Chat Completions
OpenAI-compatible chat API with automatic memory injection.
Collections
Organize memories into collections for multi-tenant applications.
Knowledge Graph
Automatic entity extraction and relationship mapping.
Automatic Learning
Self-improving AI with 6-step quality validation and RL feedback loops.
Coding Agent
MCP integration for Claude, Cline, and any MCP-compatible agent.
Privacy Controls
GDPR-compliant data export, deletion, and access management.
03. Quick Example
import asyncio
from hebbrix import MemoryClient
async def main():
async with MemoryClient(api_key="mem_sk_...") as client:
coll = await client.collections.create(name="my-agent")
# Store a memory
await client.memories.create(
collection_id=coll["id"],
content="User prefers dark mode",
)
# Search memories
results = await client.search(
query="user preferences",
collection_id=coll["id"],
)
asyncio.run(main())04. Ready to Build?
Get started in minutes with our quickstart guide or explore the full API reference.