Sideko – Hybrid deterministic/LLM generator for API SDKs and docs
Hi HN, I’m Patrick. Elias, Kevin, and I are building Sideko (https://sideko.dev), a new type of code generator for building and maintaining API client SDKs from OpenAPI specs. Traditional SDK generators rely on static templates that produce rigid, machine-generated code. When the API changes, these generators completely overwrite the SDK, destroying any custom modifications developers have made. The result is brittle code that looks artificial and requires constant manual rework. Our approach uses structured pattern matching queries instead of templates. These queries analyze the…
In plain words
Sideko is a code generator that creates and maintains API client SDKs from OpenAPI specifications. Unlike traditional generators that overwrite code with each update, Sideko uses pattern matching to understand existing codebases and make incremental changes while preserving custom developer modifications. It combines deterministic logic with language models to produce natural-looking code that doesn't require constant manual rework when APIs change.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN, I’m Patrick. Elias, Kevin, and I are building Sideko (https://sideko.dev), a new type of code generator for building and maintaining API client SDKs from OpenAPI specs. Traditional SDK generators rely on static templates that produce rigid, machine-generated code. When the API changes, these generators completely overwrite the SDK, destroying any custom modifications developers have made. The result is brittle code that looks artificial and requires constant manual rework. Our approach uses structured pattern matching queries instead of templates. These queries analyze the existing codebase to understand its structure and intent, then make small updates while preserving custom changes. When we regenerate code, the system recognizes what developers have modified and works around those changes rather than overwriting them. The pattern matching enables our hybrid workflow where deterministic codegen establishes the foundation, LLMs enhance specific components, and the system maintains both the automatically generated and the human-modified code. Our Hybrid SDK Generation Approach Workflow: Our system starts with deterministic codegen that generates the base SDK structure, then uses LLMs to enhance specific components where adaptability adds measurable value, while agent rules enforce consistency through type checking and integration tests against mock servers. Summary: The key advantage is that LLM edits are retained across code regenerations while the deterministic code stays automatically synced with API changes. Language-specific rules for Python and TypeScript guide both LLM modifications and testing to ensure quality and consistency throughout the development cycle. You can quickly try it out from your terminal: Install: npm install -g @sideko/cli Login: sideko login Initialize: sideko sdk init Prompt: “Add a new function that…” Repo is here: https://github.com/Sideko-Inc/sideko We’d love to hear your thoughts!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2025
the whole month →
- IS
I built the world's most impractical 1000-pixel display and anyone in the world can draw on it. It draws a single pixel at a time and takes 30-60 minutes to complete a single image. Anyone can participate in the project by voting for the next image to be drawn, and submitting images. https://kilopx.com/
Work · 2025 · benholmen.com
- KT
Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…
Dev tools · 2025 · github.com
- IW
I was wondering how I can arrange objects along a spherical helix path, and read some articles on it. I ended up learning about parametric equations again, and make this visualization to document what I learned: https://visualrambling.space/moving-objects-in-3d/ feel free to visit and let me know what you think!
Life & fun · 2025 · visualrambling.space
- TC
For HTML Day 2025 [1], I made a web service that displays the current sky at your approximate location as a CSS gradient. Colours are simulated on-demand using atmospheric absorption and scattering coefficients. Updates every minute, without the use of client-side JavaScript. Source code and additional information is available on GitHub: https://github.com/dnlzro/horizon [1] https://html.energy/html-day/2025/index.html
Dev tools · 2025 · sky.dlazaro.ca