Start building with one prompt

I want to add persistent memory to my app using Cerebe. First, read the full API documentation:

Fetch https://cerebe.ai/llms-full.txt

Then:
1. Install the Cerebe Python SDK: pip install cerebe
2. Add memory storage that persists user preferences across sessions
3. Add semantic search to retrieve relevant memories
4. Use the async client (AsyncCerebe) for best performance

My API key is in the CEREBE_API_KEY environment variable.

I want to integrate Cerebe (cerebe.ai) for persistent AI memory in my project.

Cerebe docs: https://cerebe.ai/llms-full.txt

Install: npm install @cerebe/sdk (TypeScript) or pip install cerebe (Python)

Please:
1. Read the docs URL above to understand the full API
2. Add Cerebe memory to my app — store user context and retrieve it semantically
3. Use the correct field names from the docs (the SDK matches the API exactly)
4. Set up the client with api key from CEREBE_API_KEY env var

Key endpoints: memory.add(), memory.search(), memory.harvest() for extracting memories from conversations.

Build me a personal knowledge assistant app that uses Cerebe (cerebe.ai) as its memory backend.

The app should:
- Let users chat with an AI that remembers everything across sessions
- Store conversation memories using Cerebe's memory API
- Search past memories semantically when answering questions
- Show a "memory timeline" sidebar of what the AI remembers

Tech: Use the @cerebe/sdk npm package. API docs at https://cerebe.ai/llms-full.txt

The Cerebe API key should come from an environment variable CEREBE_API_KEY.
Key SDK methods: client.memory.add(), client.memory.search(), client.memory.harvest()

Add Cerebe cognitive memory to my project. Cerebe gives AI apps persistent memory, knowledge graphs, and meta-learning.

Full API docs: https://cerebe.ai/llms-full.txt

Setup:
- TypeScript: npm install @cerebe/sdk
- Python: pip install cerebe

Implement:
1. Initialize client: new Cerebe({ apiKey: process.env.CEREBE_API_KEY })
2. Store memories: client.memory.add({ content, sessionId, type: 'semantic' })
3. Search memories: client.memory.search({ query, sessionId })
4. Harvest from conversations: client.memory.harvest({ sessionId, transcript: [{role, content}] })

The SDK uses camelCase params that map to the API's snake_case automatically.

You are a coding assistant that helps developers integrate Cerebe, a cognitive memory platform for AI applications.

Cerebe API base URL: https://api.cerebe.ai
Authentication: X-API-Key header

Core endpoints:
- POST /api/v1/memory/store — Store a memory (content, session_id, memory_type, importance)
- POST /api/v1/memory/search — Search memories (query, session_id, limit)
- POST /api/v1/memory/harvest — Extract memories from conversation transcript
- POST /api/v1/knowledge/ingest — Add to knowledge graph
- POST /api/v1/knowledge/query — Query knowledge graph

SDKs: pip install cerebe (Python), npm install @cerebe/sdk (TypeScript)
Full docs: https://cerebe.ai/llms-full.txt

When helping users, always use the SDK rather than raw HTTP calls. Prefer async patterns.