Get started with Aura

pip install aura-memory

from aura import Aura

brain = Aura("./my_brain")

# Store knowledge
brain.store("Deploy to staging first. Never push straight to prod.")
brain.store("Our database is PostgreSQL. Auth uses JWT, 15-minute tokens.")
brain.store("User prefers concise answers without bullet points.")

# Recall relevant context — <1ms, no API call
results = brain.recall("deployment rules", limit=3)
for r in results:
    print(r.content)

# Output:
# Deploy to staging first. Never push straight to prod.

from aura import Aura
import anthropic

brain = Aura("./brain")
client = anthropic.Anthropic()  # ANTHROPIC_API_KEY

def chat(message: str) -> str:
    # Pull relevant memories before each message
    memories = brain.recall(message, limit=5)
    context = "\n".join(f"- {m.content}" for m in memories)

    response = client.messages.create(
        model="claude-haiku-4-5-20251001",
        max_tokens=1024,
        system=f"You are a helpful assistant.\n\nWhat you remember:\n{context}",
        messages=[{"role": "user", "content": message}]
    )

    brain.store(f"User asked: {message}")
    return response.content[0].text

# Teach the agent
brain.store("The user is building a FastAPI service with PostgreSQL.")
brain.store("The user prefers async endpoints.")

print(chat("What database should I use?"))
# → Answers with PostgreSQL from memory

from aura import Aura

brain = Aura("./my_agent_brain")
# Creates: my_agent_brain/brain.cog, beliefs.cog, etc.

# Store — write something to memory
brain.store("content", tags=["optional", "tags"])

# Recall — find relevant memories for a query
results = brain.recall("your query", limit=5)
for r in results:
    print(r.content)      # the stored text
    print(r.confidence)   # how reliable is this memory
    print(r.tags)         # associated tags

from aura import Aura
import anthropic

brain = Aura("./brain")
client = anthropic.Anthropic()

memories = brain.recall(user_message, limit=5)
context = "\n".join(f"- {m.content}" for m in memories)

response = client.messages.create(
    model="claude-haiku-4-5-20251001",
    max_tokens=1024,
    system=f"Assistant with memory:\n{context}",
    messages=[{"role": "user", "content": user_message}]
)

from aura import Aura
import google.generativeai as genai

brain = Aura("./brain")
genai.configure(api_key="YOUR_KEY")
model = genai.GenerativeModel("gemini-2.5-flash-lite")

memories = brain.recall(user_message, limit=5)
context = "\n".join(f"- {m.content}" for m in memories)
prompt = f"Memory:\n{context}\n\nUser: {user_message}"

response = model.generate_content(prompt)
brain.store(f"User asked: {user_message}")

from aura import Aura
import requests

brain = Aura("./brain")

memories = brain.recall(user_message, limit=5)
context = "\n".join(f"- {m.content}" for m in memories)

r = requests.post("http://localhost:11434/api/generate", json={
    "model": "gemma3n:e4b",
    "prompt": f"Memory:\n{context}\n\nUser: {user_message}",
    "stream": False
})
brain.store(f"User asked: {user_message}")

from aura import Aura
from crewai.tools import tool

brain = Aura("./brain")

@tool("remember")
def remember(content: str) -> str:
    """Store important information in long-term memory."""
    brain.store(content)
    return "Stored."

@tool("recall")
def recall_memory(query: str) -> str:
    """Search long-term memory for relevant information."""
    results = brain.recall(query, limit=5)
    return "\n".join(r.content for r in results) or "Nothing found."

record = brain.recall("something")[0]

record.id           # unique record ID
record.content      # stored text
record.level        # memory level (Working/Decisions/Domain/Identity)
record.tags         # list of tags
record.confidence   # reliability score 0.0–1.0
record.namespace    # isolation namespace
record.created_at   # unix timestamp

# Start MCP server
python -m aura.mcp --brain ./my_brain

# Or via CLI
aura-mcp --brain ./my_brain --port 8765