The Curious Engineer

All blogs / AI / ML

HelixML

blog.helix.ml

Helix brings the best of open source AI to your business. Click to read HelixML, a Substack publication with thousands of subscribers.

AI / MLDevOps / SRE / infrastructure

’23’24’25’26
Posts
58 from 2 Dec 2023 to 29 Sep 2026
Posting
monthly (15 in the last year)
Kind
company blog
Feed
https://blog.helix.ml/feed

2026 10

  1. Meet Your Chief of Staff
  2. The Subtraction Dividend: Helix Runs Inference on AWS Trainium
  3. Working with the Garage Door Up, Without a Door
  4. I benchmarked two approaches to code indexing for Kodit (which powers Helix Code Intelligence). The smarter one lost.
  5. Why Benchmarking AI Code Tools Is Harder Than You Think
  6. What a control room for AI coding agents actually looks like
  7. Porting a Code RAG system from Python to Go: What the AI got wrong
  8. How We Forked Zed and Added Remote Control for Agent Fleet Orchestration
  9. How We Made Docker Builds 193x Faster: From 45 Minutes to 14 Seconds
  10. GPU Virtualization Architecture for Multi-Desktop Containers

2025 20

  1. Bringing AI to Where Your Enterprise Lives: Helix + Microsoft 365
  2. We Mass-Deployed 15-Year-Old Screen Sharing Technology and It's Actually Better
  3. We Killed WebRTC (And Nobody Noticed)
  4. Why I've Joined HelixML
  5. Dynamically presenting MCP clients as tools to LLMs in Go
  6. Technical Deep Dive on Streaming AI Agent Desktop Sandboxes: When Gaming Protocols Meet Multi-User Access
  7. Is MCP authentication that complicated?
  8. GPU-Accelerated AI Agent Sandboxes: Rethinking How We Interact with Coding Agents
  9. Kodit 0.5: All Things Git
  10. Kodit 0.4: Hosting a SaaS, Smarter APIs, and Scaling the Future
  11. Bootstrapped Private GenAI Startup Hits $1M Annual Revenue, Launches Helix 2.0
  12. Kodit 0.3: 10x Faster Indexing and Enterprise-Grade New Features
  13. Helix Kodit: Open Source MCP Server to Index External Repositories
  14. The Blind Spot in AI That No One Was Talking About – Until Now
  15. Stop Hoarding GPUs Already
  16. The Unexpected Benefits of Self-Hosting Your LLM
  17. YOLO Prompt Engineering Is Not OK
  18. Conversations as Data: My Path to Building a Call Analysis Assistant with Helix
  19. You should run local models: run Deepseek-R1 on Helix 1.5.0 now
  20. Building a Natural Language Interface for GitHub Issues: A Developer's Journey with Helix and Llama 3

2024 27

  1. Running GenAI on Supercomputers: Bridging HPC and Modern AI Infrastructure
  2. GPTScript Helix Apps: For Fun and Profit
  3. Building a Local LLM-Powered Kubernetes Debugger
  4. Building Reliable GenAI Applications: A Hands-on Testing & CI Workshop
  5. From ClickOps to GitOps: The Evolution of AI App Development
  6. Announcing Helix 1.4 – CI/CD for Cloud-Native GenAI Apps
  7. Building in the open: Revenue and Pipeline for Private GenAI
  8. We can all be AI engineers – and we can do it with open source models
  9. HelixML Brings Enterprise-Grade CI/CD to Private GenAI as Global Companies Rush to Repatriate AI Infrastructure
  10. Join the "Private ChatGPT" workshop at AI for the Rest of Us!
  11. Tamao Nakahara joins Helix as advisor
  12. Workshop invite: Install your own private chatGPT (with private data) with Helix.ml! 😃
  13. LLM App Challenge with Helix 1.0
  14. I need your help
  15. HelixML Announces 1.0 Release
  16. Rescale and AWA Partner with Helix for Secure Enterprise GenAI
  17. The Open Source AI Revolution: How Regulation Is Reshaping Enterprise GenAI
  18. Announcing Helix 1.0 – Secure Local GenAI for Serious People
  19. `helix apply -f` lets you deploy yaml-defined GenAI apps with RAG and APIs on local open models
  20. 10 Minute Live-coding Demo of Building a Helix App with RAG and Website Embed
  21. Can we help you build your AI App?
  22. Join us on the GPTScript live stream in 15 minutes
  23. Bootstrapped SaaS startup: New limits on fine tuning on Helix free plan
  24. Introducing the Helix CLI and Dagger module
  25. Integrating business APIs with open source LLMs: Announcing Helix Tools
  26. Running Ollama server-side
  27. How we got fine-tuning Mistral-7B to not suck: Helix Project Report, Feb 2024

2023 1

  1. Building a Generative AI platform in the open