# google-gemini/genai-processors

GenAI Processors is a lightweight Python library that enables efficient, parallel content processing.

Repository: https://github.com/google-gemini/genai-processors
Canonical: https://ross.abutalabs.com/products/genai-processors
Homepage: https://google-gemini.github.io/genai-processors/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, ai, asyncio, gemini, genai, generative-ai, language-model, multimodal, python, realtime
Last push: 2026-08-04T23:30:53+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 74, longevity 35
- inputs: {"age_days": 491, "days_push": 29, "days_rel": 176, "gap_med": 12, "n_releases_24m": 8}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2120, forks 227 (observed 2026-08-28T04:06:16.540541+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: agent-framework, streaming, llm-inference, workflow-automation, concurrency
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform
- tags: gemini, multimodal, asyncio, composable-pipelines, generative-ai, real-time-streaming, ai-agents

## Member repositories
- google-gemini/genai-processors (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:16.540541+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:52:54.024622+00:00, confidence not recorded.
  - readme: https://github.com/google-gemini/genai-processors (fetched 2026-08-28T04:06:16.540541+00:00, sha 485a457f4335)
  - homepage: https://google-gemini.github.io/genai-processors/ (fetched 2026-08-29T10:32:58.092777+00:00, sha 841656919fac)
  - registry_pypi: https://pypi.org/pypi/genai-processors/json (fetched 2026-08-29T10:32:58.101994+00:00, sha 51597cf5e1e6)
- Data as of 2026-08-30T08:39:29.467469+00:00.