Skip to main content

Which Cognis is right for you?

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

Hosted (lyzr-adk)

Managed, production-readyGet started in 5 minutes with the Lyzr cloud API. Full async, 6 retrieval strategies, summaries.

Open Source (lyzr-cognis)

Local-first, zero infrastructureRuns entirely in-process. SQLite + Qdrant local. 3 dependencies, ~156 MB.

Feature Comparison

FeatureHostedOpen Source
Setup
Installpip install lyzr-adkpip install lyzr-cognis
Time to first memory~2 minutes~3 minutes
Infrastructure neededNone (cloud API)None (in-process)
API keysLYZR_API_KEYGEMINI_API_KEY + OPENAI_API_KEY
Data storageLyzr cloudLocal (~/.cognis/)
Core Memory
Add messages
Semantic search
Get/list memories
Delete memories
Update memories❌ (auto-dedup on add)
Get contextcog.context()m.get_context()
Smart deduplication
Memory scopingowner_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 searchcross_session=True❌ (global scope by default)
Immediate recall✅ (256D session-scoped)
Retrieval strategies6 (COGNIS, FOUR_WAY_TEMPR, etc.)1 (hybrid RRF)
Advanced
Async support✅ Full (aadd, asearch, etc.)❌ Sync only
Summariesstore_summary, search_summaries
Get raw messagesget_messages()
Delete sessiondelete_session()clear(session_id=...)
Memory categories1513 (customizable)
Memory versioning
Context manager✅ Sync + async✅ Sync only
Infrastructure
Storage backendMongoDB + Qdrant + Neo4j + OpenSearchSQLite + Qdrant local
Embedding providerPluggable (OpenAI, Nomic, Gemini)Gemini 2
Data residencyLyzr cloudYour machine
Multi-tenant✅ Production-scale✅ Single-machine
Dependencieslyzr-adk3 packages (~156 MB)
Pricing
LicenseUsage-basedMIT (free)
Infrastructure costsIncludedEmbedding + extraction API costs
SupportIncludedCommunity + GitHub

Decision Guide

Choose Hosted if you want:

Production Scale

Managed infrastructure, auto-scaling, and enterprise storage (MongoDB + Neo4j).

Async Support

Full async/await API for high-throughput applications.

Summaries

Store and search conversation summaries across sessions.

Lyzr Ecosystem

Seamless integration with Lyzr Agent Studio and the ADK.

Choose Open Source if you need:

Data Privacy

All data stays on your machine. No cloud dependency for storage.

Lightweight

3 dependencies, ~156 MB install. Runs in-process, no servers.

Custom Configuration

Tune search weights, swap embedding models, customize categories.

Free

MIT license. Only pay for embedding and extraction API calls.

API Shape Comparison

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)

Still Not Sure?

Try Hosted

Get started with the hosted API in 5 minutes

Try Open Source

Install locally and run your first memory operations