npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

openclaw-sarvam-provider

v1.0.1

Published

Sarvam provider for OpenClaw with multiple models, wiki_grounding, and Indian language support

Readme

OpenClaw Sarvam Provider

npm License: MIT TypeScript Node

Official Sarvam provider for OpenClaw - Enterprise-grade integration with wiki_grounding, strong Indian language support, and dynamic model switching.

Features

  • 🌏 Strong Indian Language Support - Optimized for Hindi, Tamil, Telugu, Kannada, and more
  • 📚 Wiki Grounding - Built-in RAG-based Wikipedia retrieval for enhanced factual accuracy
  • 🔄 Dynamic Model Switching - Seamlessly switch between Lite, M, and Pro models
  • Streaming Support - Real-time streaming responses for faster user experience
  • 🔒 Enterprise Security - Environment variable support, input validation, secure communication
  • 🎯 Multiple Models - Choose the right model for your use case
  • 🛠️ Developer-Friendly - TypeScript with full type definitions
  • 📦 Easy Installation - Single command setup with OpenClaw

Requirements

Installation

Install the provider globally:

npm install -g openclaw-sarvam-provider

Alternative package managers: pnpm add -g, bun add -g, or yarn global add

Configuration

Get Your API Key

Visit docs.sarvam.ai to sign up and generate an API key.

Configure OpenClaw

Set your API key as an environment variable (recommended):

export SARVAM_API_KEY="your-sarvam-api-key-here"

Or use interactive setup:

openclaw setup sarvam

Usage

Basic Usage

Use the provider with OpenClaw:

openclaw agent --model "sarvam/sarvam-m" --message "Your question here"

Model Selection

Choose the right model for your needs:

  • sarvam/sarvam-lite (16K context) - Quick responses, simple tasks
  • sarvam/sarvam-m (32K context) - General use, balanced performance
  • sarvam/sarvam-pro (64K context) - Complex tasks, deep analysis

Wiki Grounding

Enable wiki_grounding for enhanced factual accuracy:

openclaw agent --model "sarvam/sarvam-m" --wiki-grounding true --message "Your question"

Available Models

| Model ID | Context | Features | Best For | |----------|---------|----------|-----------| | sarvam/sarvam-lite | 16K | wiki_grounding, streaming | Quick responses, simple tasks | | sarvam/sarvam-m | 32K | wiki_grounding, streaming, Indian languages | General use, balanced performance | | sarvam/sarvam-pro | 64K | wiki_grounding, streaming, advanced reasoning, Indian languages | Complex tasks, deep analysis |

Configuration Options

API Parameters

  • model - Model selection (default: sarvam/sarvam-m)
  • temperature - Controls randomness (0.0 - 2.0, default: 0.2)
  • top_p - Nucleus sampling (0.0 - 1.0, default: 1.0)
  • max_tokens - Maximum response length
  • wiki_grounding - Enable Wikipedia RAG (default: false)
  • stream - Enable streaming (default: true)

Indian Language Support

Sarvam excels at Indian languages including Hindi, Tamil, Telugu, Kannada, and more. Use any supported language in your requests.

Security

  • ✅ Use environment variables for API keys
  • ✅ Never commit API keys to version control
  • ✅ Rotate API keys regularly
  • ✅ HTTPS-only communications
  • ✅ Input validation and sanitization

Development

Building from Source

git clone https://github.com/rnagarajanmca/openclaw-sarvam-provider.git
cd openclaw-sarvam-provider
npm install
npm run build

Running Tests

npm test

Documentation

Links

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support


Made with ❤️ for the OpenClaw and Sarvam communities