All activity
Anandesh Sharmaleft a comment
I'm Anandesh, and along with my co-founder Shubham, we built Definable. Here's the truth - we got tired of stitching together 10 different AI tools just to get work done. One tab for ChatGPT, another for Midjourney, another for Zapier, another for our agent framework. It was chaos. So we built what we actually wanted: one platform that does it all. What you can do with Definable today: → Chat...
Definable AIAgents, studios & 50+ AI models - one platform, no stitching
Definable is India's open-source AI platform - built for builders and businesses alike. Chat with 50+ models. Generate photos and videos in AI studios. Automate workflows with 900+ app integrations. Build production agents with our Python SDK - complete with memory, guardrails, RAG, and multi-platform deployment. One platform that replaces your entire AI stack. Free to start. Open source at the core.
Definable AIAgents, studios & 50+ AI models - one platform, no stitching
Anandesh Sharmastarted a discussion
We replaced 11 AI subscriptions with one platform. Is the "all-in-one" era finally here?
My co-founder and I were paying for ChatGPT, Midjourney, Zapier, a vector database, a RAG tool, a separate agent framework, and five other AI services. Monthly total: $380+. For a two-person team from India, that's painful. So we built Definable - one platform with 50+ AI models, photo and video studios, 900+ app integrations, an open-source agent SDK, and a coding CLI. We cancelled everything...
Anandesh Sharmaleft a comment
Congrats on the launch, but I didn't get it, ain't you doing embedding in the backend from the VLM? you are basically transcribing each frame of video in a multi-threaded way and after you get text you are indexing those with the PTS of video. when user asks the question, it goes in the vector database and fetches the relevant frames based on the query with summary and timestamp. A human on the...
Memories.aiChatGPT for your video library, with unlimited video context