google-gemini/genai-processors

Health v2 · maintenance only

Adoption not part of the score

2120 stars · 227 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

GenAI Processors is a lightweight Python library for building modular, asynchronous, and composable AI pipelines around Gemini and other generative AI models. It provides a unified multimodal content model, composable Processor classes built on asyncio, and built-in streaming for turn-based and real-time agent interactions.

Use cases

• build streaming multimodal ai agents in python
• chain llm calls into composable pipelines
• process text, image, and audio streams with gemini
• build real-time voice agents with low latency
• unify content handling across llm models and tools
• prototype generative ai apps with asyncio

When to choose

• you are building agents or pipelines on the Gemini API in Python
• you need low-latency streaming and time-to-first-token performance
• you want composable, reusable units for multimodal content processing
• you mix streaming and non-streaming code and want a unified abstraction

When to avoid

• you need a framework-agnostic solution independent of the Gemini/Google ecosystem
• your project is not Python-based
• you only need simple one-off LLM API calls without pipeline composition
• you require mature orchestration features like durable workflows or distributed execution

Facets

library · maturity active

agent-framework streaming llm-inference workflow-automation concurrency artificial-intelligence large-language-models developer-tools python cross-platform gemini multimodal asyncio composable-pipelines generative-ai real-time-streaming ai-agents

Member repositories

For agents

markdown · JSON · MCP: product_card(name="google-gemini/genai-processors")