zeetay/self-improving-agent

fix: swap decommissioned llama-3.3-70b-versatile for openai/gpt-oss-120b

fix: correct local NEXT_PUBLIC_API_URL example to port 8000

docs: update deploy references from Vercel to Netlify

build: set Netlify publish to .next (base-relative)

build: fix Netlify publish dir for Next.js (web/.next)

build: add Netlify config for the web frontend

ui: add favicon; trim footer to model line

docs: use custom domain for live demo link

docs: add live demo URL to README

prep for hf deploy

style: replace box diagram with a list, normalize unicode to ASCII, trim comments

perf: use CPU-only torch in Docker image (8.9GB -> 2.3GB)

feat: Hugging Face Spaces Docker deployment config

update readme

feat: Next.js frontend for hosted demo + README live-demo section

feat: backend updates for hosted demo (CORS, stats, seed, rate limit, Procfile)

update env.ex

update

Initial commit: self-improving ad copy agent eval harness