Welcome to Hebbrix
Hebbrix gives your AI a brain that remembers everything. Build applications with persistent memory, intelligent search, and automatic learning.
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.
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.
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())Ready to Build?
Get started in minutes with our quickstart guide or explore the full API reference.