Styx
AI gateway that auto-picks the right model for every request
What it does
Styx is an open-source AI gateway. Send "model": "styx:auto" and it picks the optimal model based on prompt complexity. Simple question → cheap model. Complex code → frontier model. 65+ models from OpenAI, Anthropic, Google, Mistral. Self-hosted with Docker in 5 minutes. Interactive setup wizard. Dashboard for costs and latency. Auto-failover between providers. Go router (<10ms overhead) + Python backend + Next.js dashboard. Apache 2.0.
Does the same job
all alternatives →
- SMSmart model routing directly in Claude, Codex and CursorJun 2026 · github.com · ▲216
We built a model router that plugs into coding agents (e.g. Claude Code, Codex, Cursor, etc.) and intelligently sends requests to the best model to serve them. Here's a quick demo of running it locally: https://www.youtube.com/watch?v=isKhAyivtfM. At Weave, we write most of our code with AI, and it's been getting more expensive. This came to a head when Opus 4.7 was released and, thanks to its tokenizer changes, our costs shot up. We knew we didn't need Opus for everything but we didn't want to lose out on the intelligence for the cases where you really need it. So we decided…
- SASteiner – An open-source reasoning model inspired by OpenAI o12024 · medium.com · ▲83
Steiner is a series of reasoning models trained on synthetic data using reinforcement learning. These models can explore multiple reasoning paths in an autoregressive manner during inference and autonomously verify or backtrack when necessary, enabling a linear traversal of the implicit search tree. Blog: https://medium.com/@peakji/a-small-step-towards-reproducing-... Hugging Face: https://huggingface.co/collections/peakji/steiner-preview-67...
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 · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
