> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lyzr.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Install Cognis and run your first memory operations in 3 minutes

## 1. Install

<Tabs>
  <Tab title="Hosted (lyzr-adk)">
    ```bash theme={null}
    pip install lyzr-adk
    ```
  </Tab>

  <Tab title="Open Source (lyzr-cognis)">
    ```bash theme={null}
    pip install lyzr-cognis
    ```
  </Tab>
</Tabs>

## 2. Set API Keys

<Tabs>
  <Tab title="Hosted (lyzr-adk)">
    ```bash theme={null}
    export LYZR_API_KEY="your-lyzr-api-key"
    ```
  </Tab>

  <Tab title="Open Source (lyzr-cognis)">
    ```bash theme={null}
    export GEMINI_API_KEY="your-gemini-key"    # For embeddings
    export OPENAI_API_KEY="your-openai-key"    # For fact extraction
    ```
  </Tab>
</Tabs>

## 3. Add Memories

<Tabs>
  <Tab title="Hosted (lyzr-adk)">
    ```python theme={null}
    from lyzr import Cognis, CognisMessage

    cog = Cognis()

    cog.add(
        messages=[
            CognisMessage(role="user", content="My name is Alice. I love hiking and I'm vegetarian."),
            CognisMessage(role="assistant", content="Nice to meet you, Alice!"),
        ],
        owner_id="user_alice",
    )
    ```
  </Tab>

  <Tab title="Open Source (lyzr-cognis)">
    ```python theme={null}
    from cognis import Cognis

    m = Cognis(owner_id="user_alice")

    result = m.add([
        {"role": "user", "content": "My name is Alice. I love hiking and I'm vegetarian."},
        {"role": "assistant", "content": "Nice to meet you, Alice!"},
    ])
    print(result["message"])
    # "Extracted 3 memories from 2 messages"
    ```
  </Tab>
</Tabs>

Cognis automatically extracts discrete facts from the conversation and stores them as searchable memory records.

## 4. Search Memories

<Tabs>
  <Tab title="Hosted (lyzr-adk)">
    ```python theme={null}
    results = cog.search(query="What does Alice eat?", owner_id="user_alice", limit=5)
    for r in results:
        print(f"  {r.content}  (score: {r.score})")
    # → Alice is vegetarian  (score: 0.89)
    ```
  </Tab>

  <Tab title="Open Source (lyzr-cognis)">
    ```python theme={null}
    resp = m.search("What does Alice eat?", limit=5)
    for r in resp["results"]:
        print(f"  {r['content']}  (score: {r['score']})")
    # → Alice is vegetarian  (score: 0.8712)
    ```
  </Tab>
</Tabs>

## 5. Get Context for Your LLM

<Tabs>
  <Tab title="Hosted (lyzr-adk)">
    ```python theme={null}
    context = cog.context(
        current_messages=[CognisMessage(role="user", content="Recommend a restaurant")],
        owner_id="user_alice",
    )
    # Use context in your LLM system prompt
    ```
  </Tab>

  <Tab title="Open Source (lyzr-cognis)">
    ```python theme={null}
    ctx = m.get_context(
        messages=[{"role": "user", "content": "Recommend a restaurant"}]
    )
    print(ctx["context_string"])
    # "Relevant memories:\n- Alice is vegetarian\n- ..."

    m.close()  # Required for OSS
    ```
  </Tab>
</Tabs>

## What Just Happened

1. Cognis stored your raw messages
2. The LLM extracted discrete facts and auto-categorized them (identity, preferences, interests, etc.)
3. Facts were embedded and indexed for hybrid search (vector + keyword)
4. Search used Reciprocal Rank Fusion: 70% vector similarity + 30% BM25 keyword matching
5. `context` / `get_context` assembled both short-term messages and long-term memories for LLM use

## Next Steps

<CardGroup cols={2}>
  <Card title="Configuration" icon="gear" href="/cognis/configuration">
    API keys, init params, search weight tuning
  </Card>

  <Card title="Add Memories" icon="plus" href="/cognis/add-memories">
    Full method reference for storing conversations
  </Card>

  <Card title="Features" icon="sparkles" href="/cognis/features/hybrid-search">
    Hybrid search, categories, session management, and more
  </Card>

  <Card title="Cookbooks" icon="utensils" href="/cognis/cookbooks/overview">
    CrewAI, LangChain, LangGraph, and Agno integrations
  </Card>
</CardGroup>