sreenathmenon

Universal SDK for working with multiple LLM providers (OpenAI, Anthropic, Gemini, etc.). Built-in caching can reduce API costs by 90%+. 15K+ PyPI downloads.

pip install llmswap

Universal SDK for switching between any LLM provider with one line.

10 providers: OpenAI, Anthropic (Claude Sonnet 4.5), Google Gemini, xAI Grok, Cohere, Perplexity, IBM Watsonx, Groq, Ollama, Sarvam AI.

Key features: - Workspace memory: AI remembers your project context across sessions - Auto-learning journals per project - Multiple "second brains" for different aspects of life

Python SDK + CLI

pip install llmswap

Cool

:)

At some point, I have used AI ad my friend, mentor, teacher, etc.

good work :)

Love it :)

Fair point! Redis would be better for production. I went with in-memory for zero-config simplicity, but should add Redis as an option. Thanks!

Hey, functools.cache is definitely simpler and would be sufficient for most basic cases. But I was thinking of multi-tenant and context aware scenario's - that's why went with different strategy.

Hey, Thanks for the great feedback! You're raising valid point.

Actually, this package started based on a hackathon project where I was burning the Anthropic API credits for our hackathon project which was RAG (internal documentation) + MCP.

There were question which were getting repeated several times. The 50% + comes from this experience. So, based on this, I was thinking of some of the use cases like this:

Multi-User Support/FAQ Systems: - How do I reset my password? - Reset password steps? - Forgot my password help - Password reset procedure

RAG based: - How to configure VM? - How to deploy? - How to create a network?

Educational/Training Apps Developer Testing scenarios, etc

You're absolutely right that apps with unique queries won't see these benefits - this won't help in - Personalized Content - Real-Time Data - User-Specific Queries - Creative Generation and other scenarios

I think I should clarify this in the docs. Thanks for the great feedback. This is my first opensource package and first conversation in hackernews. Great to interact and learn from all of you

Just released v1.5.0 with IBM watsonx integration.

  ```python
  # Works with any provider now
  client = LLMClient(provider="watsonx")
  client = LLMClient(provider="anthropic")
  client = LLMClient(provider="openai")

  response = client.query("Analyze this data")

  New in v1.5.0:
  - IBM watsonx provider with Granite models
  - Same API across all 5 providers
  - Auto-fallback still works
  - Enterprise authentication

  Also supports 100+ local Ollama models including OpenAI's new GPT-OSS.