# LLMSlim integrations

> Use LLMSlim output with model providers and frameworks. LLMSlim prepares context; your application makes the model call.

## LLM Provider

- [Sarvam](https://www.llmslim.app/integrations/sarvam.md): Adaptive context planning meets Sarvam’s Indic language models and language tools.
- [OpenAI](https://www.llmslim.app/integrations/openai.md): Compress Python application context before an OpenAI SDK request.
- [Anthropic](https://www.llmslim.app/integrations/anthropic.md): Prepare long Python-managed context before an Anthropic SDK request.
- [Google Gemini](https://www.llmslim.app/integrations/gemini.md): Compress retrieved Python context before a Gemini SDK request.

## Framework

- [LangChain](https://www.llmslim.app/integrations/langchain.md): A BaseDocumentCompressor for ContextualCompressionRetriever. Use it where you would use LLMLinguaCompressor.
- [LlamaIndex](https://www.llmslim.app/integrations/llamaindex.md): A BaseNodePostprocessor for query engines. Use it where you would use LongLLMLinguaPostprocessor.
- [Haystack](https://www.llmslim.app/integrations/haystack.md): A Haystack 2.x and 3 component that compresses retrieved documents between the retriever and the prompt builder.

## Backend Services

- [Zoho](https://www.llmslim.app/integrations/zoho.md): Bounded, read-only CRM and WorkDrive context for planning.
- [MongoDB](https://www.llmslim.app/integrations/mongodb.md): Explicit persistent context, Atlas retrieval, and hosted quota accounting.
- [Exa](https://www.llmslim.app/integrations/exa.md): Live web search results as bounded, untrusted context for planning.
- [Neo4j](https://www.llmslim.app/integrations/neo4j.md): Temporal agent memory where newer facts supersede old ones, with an audit trail.

Canonical page: https://www.llmslim.app/integrations