technorage

Hi, I'm Deepu K Sasidharan 👋

Polyglot developer · Local AI tinkerer · Creator of LlamaStash, KDash and JDL Studio · Co-chair of JHipster · Linux enthusiast · Java Champion · Published author · International speaker

GitHub LinkedIn BlueSky Mastodon Twitter Dev.to SpeakerDeck

Open-source projects

LlamaStash Terminal-native local-LLM orchestrator. Run any engine, any model.
rust llamacpp localllm tui
KDash A Kubernetes dashboard that runs in the terminal.
rust kubernetes tui monitoring
Pi Automode Classifier Claude Code like auto mode for Pi, that works with any LLM or classifier including local models.
ai pi classifier llm
JHipster Rapid application development platform for modern Java fullstack applications.
java spring-boot angular react
JDL Studio The editor for JDL, the schema language JHipster generates applications from.
javascript react jhipster dsl
JWT UI Decodes and encodes JSON Web Tokens in the terminal
rust jwt tui cli
auth0-token-vault-cli Lets an agent call Google, GitHub, or Slack through Auth0 Token Vault.
typescript auth0 oauth ai-agents
Auth0 Assistant0 Sample AI assistant that reaches Gmail and Slack over OAuth 2.0 with Auth0.
typescript ai auth0 langchain

Latest writing

All posts →
Qwen3.8-Flash-Next vs Claude Opus 5.5: Six-way benchmark on a real Rust feature
·Local AI

Qwen3.8-Flash-Next vs Claude Opus 5.5: Six-way benchmark on a real Rust feature

A controlled comparison of Qwen3.8-Flash-Next and Claude Opus 5.5 on one LlamaStash feature, across Claude Code and Pi, at medium and xhigh effort

Forget Claude Code. All you need is Qwen3.8-Flash-Next running locally for agentic coding
·Local AI

Forget Claude Code. All you need is Qwen3.8-Flash-Next running locally for agentic coding

Agentic coding on a Strix Halo laptop with Qwen3.8-Flash-Next. Going head to head with Opus 5.5

Can Qwen 3.8 running on your laptop really replace Claude Opus for Agentic coding?
·Local AI

Can Qwen 3.8 running on your laptop really replace Claude Opus for Agentic coding?

Agentic coding on a Strix Halo laptop with Qwen3.8-27B and Flash-Next, the LlamaStash and Pi setup behind it, and the tuning

How fast is LlamaStash? Overhead, throughput, and a fair comparison with Ollama and LM Studio
·Local AI

How fast is LlamaStash? Overhead, throughput, and a fair comparison with Ollama and LM Studio

A reproducible benchmark of LlamaStash against raw llama-server, Ollama, and LM Studio on AMD APU, Apple Silicon, and NVIDIA
Also on the Auth0 blog My professional articles on identity, AI agents, and developer experience at Auth0 / Okta.

Bio

Full CV →
  • Principal Developer Advocate at Auth0 (Okta), covering identity for AI agents. 16+ years in the industry, before that at Adyen, XebiaLabs, and TCS.
  • Creator of LlamaStash, KDash, JWT UI, and JDL Studio. Most of it is Rust, most of it runs in a terminal.
  • Co-chair and vice-president of JHipster, a core maintainer since 2015.
  • Java Champion and author of Full Stack Development with JHipster (Packt, two editions).
  • I run local models for my daily coding setup and write up the benchmarks and the tuning that made it usable. See the local AI posts.
  • 80+ conference talks. Event list.
  • Long-time Linux user, currently on Arch with Niri.

Deep-dive series

All series →
Languages 8 posts Concurrency in Modern Programming Languages 7 posts GNU/Linux Environment for Developers 6 posts Local AI 6 posts Memory Management 6 posts Functional Programming 4 posts

Upcoming events

All events →

Nothing on the calendar right now. Check the past events list, or follow me on Linkedin for the next announcement.

esc

Type to search the blog.