Agnos LLM gateway
Contain LiteLLM, Bifrost, Portkey.. behind one control plane
What it does
Agnos is an OpenAI-compatible control plane that wraps the LLM gateway you already run. Keys stay in your encrypted vault (the gateway gets one per request and stores none); you get budgets, guardrails, routing, cost attribution and audit, and you can swap or combine gateways (litellm, bifrost, portkey etc) with a config change. MIT, self-hosted. Live demo, https://agnos-llm-gateway.site https://github.com/siva010928/agnos-proxy-oss
Agnos is a free, self-hosted, open-source AI gateway and LLM control plane - a gateway-agnostic, model-agnostic alternative to LiteLLM, Bifrost, Portkey and Kong. Keep provider keys in your own encrypted vault and run any gateway as a swappable, stateless, OpenAI-compatible translator - no lock-in, no fire drills.
Does the same job
all alternatives →
OpenLIT's Zero-code LLM ObservabilityOct 2025 · ▲136Trace LLM requests + costs with OpenTelemetry monitoring
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 1d ago · opentrailpaper.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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