Narasimha Badrinath

I build AI agents that survive the real world.

I'm a Staff Developer Advocate at DigitalOcean. I build AI apps and agents, contribute to the open-source tools developers use to ship them, and write about what I learn.

See my work Read my latest writing

Selected work

Voice assistant for macOS

Nix

Nix lives in my Mac's menu bar. I say "Hey Nix", ask something, and it answers out loud. The thinking is done by whichever coding agent I'm signed in to (Claude Code, Codex or Antigravity), so it can read files, run commands and use my tools, within permissions I set. Speech recognition runs on the Mac with Whisper, five times faster than a hosted service (265ms against 1.3s), and the audio never leaves the machine.

500+ commits · Swift app with a local Node service

How it works

Official integration

langchain-gradient

I wrote DigitalOcean's official LangChain integration from the first commit, and I maintain it. LangChain apps use it to call models on Gradient serverless inference, and it streams responses and reports token usage. I added LangChain 1.x support, reviewed and released the 1.0 move to the new pydo SDK before the old SDK retired, and I review and merge community pull requests, such as the one that added tool calling.

18,000+ downloads · Python, on PyPI

Code PyPI 
$ pip install langchain-gradient

from langchain_gradient import ChatGradient

llm = ChatGradient(model="llama3.3-70b-instruct")

for chunk in llm.stream("What is RAG?"):
    print(chunk.content, end="")

Benchmark

Agent Memory Showdown

I benchmarked six agent memory backends over 50-turn conversations. Qdrant, pgvector and the LangGraph store kept 89 to 94% recall at turn 50, for a third of the cost of keeping the full history. Mem0 cost more than the full history, and a rolling summary came last on both recall and cost.

5 runs per backend · Claude Sonnet 5.5, MiniLM embeddings

Code
Recall at turn 50 and cost per 1,000 conversations. Highlighted rows are the best value.
BackendRecallCost
Buffer100%$1,437
Mem097%$1,865
LangGraph store (best value)94%$487
pgvector (best value)91%$493
Qdrant (best value)89%$476
Summary74%$3,619

Open source I maintain and contribute to

  • llama-index-retrievers-digitalocean-gradientai The matching LlamaIndex retriever integration for Gradient, for RAG on serverless inference.
  • ai-ml-bootstrapper Hands-on demos and best practices for running AI/ML workloads on DigitalOcean. Top contributor; 26 stars.
  • GuardianAI My MCP gateway that applies a YAML policy to agent tool calls. It can deny a call, hold it for approval, or redact the result. Has Python and TypeScript SDKs and a live demo.

Latest writing

Oct 2026

What Happens to Your AI App at 9am on Monday?

I made 20% of my LLM gateway's calls fail on purpose and it dropped none of 200. Then I simulated 50 clients at 9am on Monday and 20 of them got an error.

LLMs Claude Code
Read
Oct 2026

Is Your LLM Ticket Router Good Enough to Ship?

I built a support ticket router with Claude and tested it four ways. It scored about 92% on my 40 hand-picked tickets and about 60% on messy ones, so one accuracy number couldn't tell me whether it…

LLMs Claude Code
Read
Sep 2026

Jev Is Fast Enough to Check Every Tool Call Your Agents Make

TypeSafe shipped Jev in September 2026. It cannot write text. What it does instead is answer a list of questions about a piece of data, with probabilities attached, in about a…

AI agents Security
Read
Jul 2026

Finding My Parents in a 24-Year-Old Scanned Voter Roll

It still baffles me how many people use AI today only as a fancy autocomplete, when the thing in front of them can do so much more.

Claude Code AI agents
Read
All posts on the blog All articles Videos on Distilled AI

Live apps and side projects

AI projects

  • ArchitectAI LiveDescribe an app and watch agents plan, generate and check a cloud architecture for it.
  • Dead Startups Roast LivePick a failed startup, get it roasted by AI, then see how you'd rebuild it today.
  • Voice Course StudioAgents turn a raw recording into a finished explainer video, stopping three times for my review.

iOS apps

  • DailyBrickOffline habit tracker with streaks and widgets. No accounts, no subscription.
  • Silly DebatesPeople argue absurd topics for 24 hours, then AI reads every opinion and picks a winner.
  • FlipItCard-matching game with five themed decks and global leaderboards.

Speaking

Narasimha Badrinath on stage, presenting on running AI/ML workloads on DigitalOcean
Running AI/ML workloads on DigitalOcean

I give talks and run hands-on workshops on AI agents and taking LLM apps to production. I also review agent architectures for a few teams.

I'm always up for a meetup, conference or workshop. The easiest way to reach out is below.

Let's connect.

I'm always happy to talk about AI agents, developer tools, talks and workshops. Book a time, or pick whichever channel suits you.