Viewing profile — sivasurend

Our Anthropic bill started zooming toward $1 million. So we built a system to manage coding agents. Meet BaseCode - MDM for coding agents. Here is how it works: 1. Engineers run Cl…

You're right, the name 'Claw' creates a lot of hesitation among enterprises. But it's also the best way to convey what you're trying to build, especially if you're building a file …

We built GitAgent because we kept seeing the same problem: every agent framework defines agents differently, and switching frameworks means rewriting everything. GitAgent is a spec…

We just hit $3M in Contracted ARR in under 8 months at Lyzr AI! Here’s our journey Lyzr began as an AI data analysis app(PowerBI+ ChatGPT). The name Lyzr comes from the last four l…

We took an open challenge on Twitter to a post by Jason Lemkin of SaaStr. The ask was to refer/build an AI that can replace a SDR / AE role. Here is the tweet - https://x.com/siva_…

Lyzr is a low-code agent framework, building fully-integrated private agent SDKs for the 99% of the business who do not have the liberty of time, talent, need to build on complex o…

Lyzr Automata. New kid on the block. Multi-agent Automation Framework. Ultra low-code. Open-source. https://github.com/LyzrCore/lyzr-automata Here is the demo video of how we manag…

Convert your 'one line' prompt to a 'best practice' prompt. Inspired by recent research papers on prompt engineering. The base prompt is open-sourced here - https://github.com/Lyzr…

Perplexity API costs for open-source LLMs are insanely low. Compare your LLM costs for various popular Generative AI use cases like Chatbots, QA, and Knowledge Search. #GPT4Turbo v…

Not much, actually. For lower volumes of documents, vector stores like Chroma or Weaviate provide inbuilt RAG. Things get messy when the number and type of documents increase. Belo…