> ## 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.

# Hosted vs Open Source

> Compare Cognis Hosted (lyzr-adk) and Open Source (lyzr-cognis) to choose the right fit

## Which Cognis is right for you?

Cognis is available in two flavors. Choose based on your priorities:

<CardGroup cols={2}>
  <Card title="Hosted (lyzr-adk)" icon="cloud" href="/cognis/quickstart">
    **Managed, production-ready**

    Get started in 5 minutes with the Lyzr cloud API. Full async, 6 retrieval strategies, summaries.
  </Card>

  <Card title="Open Source (lyzr-cognis)" icon="code-branch" href="/cognis/quickstart">
    **Local-first, zero infrastructure**

    Runs entirely in-process. SQLite + Qdrant local. 3 dependencies, \~156 MB.
  </Card>
</CardGroup>

***

## Feature Comparison

| Feature                       | Hosted                                 | Open Source                         |
| ----------------------------- | -------------------------------------- | ----------------------------------- |
|                               |                                        |                                     |
| **Setup**                     |                                        |                                     |
| Install                       | `pip install lyzr-adk`                 | `pip install lyzr-cognis`           |
| Time to first memory          | \~2 minutes                            | \~3 minutes                         |
| Infrastructure needed         | None (cloud API)                       | None (in-process)                   |
| API keys                      | `LYZR_API_KEY`                         | `GEMINI_API_KEY` + `OPENAI_API_KEY` |
| Data storage                  | Lyzr cloud                             | Local (`~/.cognis/`)                |
|                               |                                        |                                     |
| **Core Memory**               |                                        |                                     |
| Add messages                  | ✅                                      | ✅                                   |
| Semantic search               | ✅                                      | ✅                                   |
| Get/list memories             | ✅                                      | ✅                                   |
| Delete memories               | ✅                                      | ✅                                   |
| Update memories               | ✅                                      | ❌ (auto-dedup on add)               |
| Get context                   | ✅ `cog.context()`                      | ✅ `m.get_context()`                 |
| Smart deduplication           | ✅                                      | ✅                                   |
| Memory scoping                | ✅ `owner_id`, `agent_id`, `session_id` | ✅ Same model                        |
|                               |                                        |                                     |
| **Search & Retrieval**        |                                        |                                     |
| Hybrid search (vector + BM25) | ✅                                      | ✅ RRF fusion (70/30)                |
| Matryoshka embeddings         | ✅                                      | ✅ (256D → 768D)                     |
| Recency boost                 | ✅                                      | ✅ Exponential decay                 |
| Temporal query detection      | ✅                                      | ✅                                   |
| Cross-session search          | ✅ `cross_session=True`                 | ❌ (global scope by default)         |
| Immediate recall              | ✅                                      | ✅ (256D session-scoped)             |
| Retrieval strategies          | 6 (COGNIS, FOUR\_WAY\_TEMPR, etc.)     | 1 (hybrid RRF)                      |
|                               |                                        |                                     |
| **Advanced**                  |                                        |                                     |
| Async support                 | ✅ Full (`aadd`, `asearch`, etc.)       | ❌ Sync only                         |
| Summaries                     | ✅ `store_summary`, `search_summaries`  | ❌                                   |
| Get raw messages              | ✅ `get_messages()`                     | ❌                                   |
| Delete session                | ✅ `delete_session()`                   | ✅ `clear(session_id=...)`           |
| Memory categories             | 15                                     | 13 (customizable)                   |
| Memory versioning             | ✅                                      | ✅                                   |
| Context manager               | ✅ Sync + async                         | ✅ Sync only                         |
|                               |                                        |                                     |
| **Infrastructure**            |                                        |                                     |
| Storage backend               | MongoDB + Qdrant + Neo4j + OpenSearch  | SQLite + Qdrant local               |
| Embedding provider            | Pluggable (OpenAI, Nomic, Gemini)      | Gemini 2                            |
| Data residency                | Lyzr cloud                             | Your machine                        |
| Multi-tenant                  | ✅ Production-scale                     | ✅ Single-machine                    |
| Dependencies                  | `lyzr-adk`                             | 3 packages (\~156 MB)               |
|                               |                                        |                                     |
| **Pricing**                   |                                        |                                     |
| License                       | Usage-based                            | MIT (free)                          |
| Infrastructure costs          | Included                               | Embedding + extraction API costs    |
| Support                       | Included                               | Community + GitHub                  |

***

## Decision Guide

### Choose **Hosted** if you want:

<CardGroup cols={2}>
  <Card icon="bolt" title="Production Scale">
    Managed infrastructure, auto-scaling, and enterprise storage (MongoDB + Neo4j).
  </Card>

  <Card icon="rotate" title="Async Support">
    Full async/await API for high-throughput applications.
  </Card>

  <Card icon="book" title="Summaries">
    Store and search conversation summaries across sessions.
  </Card>

  <Card icon="puzzle-piece" title="Lyzr Ecosystem">
    Seamless integration with Lyzr Agent Studio and the ADK.
  </Card>
</CardGroup>

### Choose **Open Source** if you need:

<CardGroup cols={2}>
  <Card icon="lock" title="Data Privacy">
    All data stays on your machine. No cloud dependency for storage.
  </Card>

  <Card icon="feather" title="Lightweight">
    3 dependencies, \~156 MB install. Runs in-process, no servers.
  </Card>

  <Card icon="wrench" title="Custom Configuration">
    Tune search weights, swap embedding models, customize categories.
  </Card>

  <Card icon="dollar-sign" title="Free">
    MIT license. Only pay for embedding and extraction API calls.
  </Card>
</CardGroup>

***

## API Shape Comparison

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

    cog = Cognis(api_key="sk-your-api-key")

    # Add — returns dict
    cog.add(
        messages=[CognisMessage(role="user", content="Hello")],
        owner_id="user_1",
    )

    # Search — returns List[CognisSearchResult] (objects with .content, .score)
    results = cog.search(query="greeting", owner_id="user_1", limit=5)
    for r in results:
        print(r.content, r.score)

    # Get — returns CognisMemoryList (object with .memories)
    memories = cog.get(owner_id="user_1")
    for m in memories.memories:
        print(m.id, m.content)
    ```
  </Tab>

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

    m = Cognis(owner_id="user_1")

    # Add — returns dict with "success", "memories", "session_message_count"
    m.add([{"role": "user", "content": "Hello"}])

    # Search — returns dict with "results" list of dicts
    resp = m.search("greeting", limit=5)
    for r in resp["results"]:
        print(r["content"], r["score"])

    # Get all — returns dict with "memories" list of dicts
    resp = m.get_all()
    for mem in resp["memories"]:
        print(mem["memory_id"], mem["content"])

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

## Still Not Sure?

<CardGroup cols={2}>
  <Card title="Try Hosted" icon="rocket" href="/cognis/quickstart">
    Get started with the hosted API in 5 minutes
  </Card>

  <Card title="Try Open Source" icon="github" href="/cognis/quickstart">
    Install locally and run your first memory operations
  </Card>
</CardGroup>