rajatsandeepsen/sarvam-adk — explained in plain English
Analysis updated 2026-05-18
Build an AI agent with Google's ADK framework that uses Sarvam's language models instead of Google's own.
Swap Sarvam models into an existing ADK agent setup with minimal code changes.
Prototype a chat assistant powered by Sarvam using the ADK command line tools.
| rajatsandeepsen/sarvam-adk | 0xradioac7iv/tempfs | abboskhonov/hermium | |
|---|---|---|---|
| Stars | 0 | 0 | 0 |
| Language | TypeScript | TypeScript | TypeScript |
| Setup difficulty | easy | moderate | moderate |
| Complexity | 2/5 | 3/5 | 4/5 |
| Audience | developer | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires a Sarvam API key from the Sarvam Dashboard.
Sarvam ADK is a small TypeScript plugin that connects Sarvam's language models to Google's Agent Development Kit, known as ADK. ADK is a framework for building AI agents, and this project adds Sarvam as a model provider inside that framework, so developers who already use ADK can plug in Sarvam's models without switching tools. To use it, you install two packages with npm: sarvam-adk itself and Google's adk package. You also need an API key from the Sarvam Dashboard, which you save in a local .env file. From there, you create a simple agent file where you import the Sarvam class from this plugin along with the LlmAgent class from ADK. You define an agent with a name, tell it to use a Sarvam model such as sarvam-30b, and give it an instruction describing how it should behave, for example acting as a helpful assistant. Once the agent file is set up, you run it using the ADK command line tool, either through a web interface with npx adk web or directly from the terminal with npx adk run. This means no custom server code is needed to get a working agent talking to Sarvam's models. The README is short and focused entirely on installation and basic setup, pointing to Sarvam's own API documentation and ADK's TypeScript docs for anything beyond the basics. There is no description of specific use cases, limitations, or advanced configuration options, so this project should be understood as a thin connector piece rather than a full application. It is best suited for developers who are already building with Google's ADK framework and want an easy way to swap in Sarvam as their model of choice.
A plugin that lets developers use Sarvam AI's language models inside Google's ADK agent-building framework.
Mainly TypeScript. The stack also includes TypeScript, Node.js, npm.
Setup difficulty is rated easy, with roughly 30min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.