Show HN: Imagent – agentic image/video/speech generation
Imagent is a tool that lets AI agents generate images, video, and speech as a native step within their workflows, offering a unified interface that abstracts away provider and model differences.
Background
- Imagent is an open-source tool that lets AI agents (like LLM-based assistants) generate images, video, and speech on the fly, as part of their normal reasoning steps — not just text.
- It wraps many different AI generation models (OpenAI, Replicate, ElevenLabs, etc.) behind one universal interface, so an agent doesn't need to know which provider is being used.
- The project is aimed at developers building autonomous agents that need multimodal output (e.g., a coding agent that also creates diagrams, or a customer-service agent that speaks replies).
- This sits in a broader trend: moving LLMs from pure text chatbots toward multimodal agents that can see, hear, and create media directly.