A daily podcast that generates itself — and improves itself based on your feedback.

Fork this val, add your API keys, and you have a personal daily audio briefing that gets better over time.

1. generate-daily.ts runs on a schedule (interval)
2. It checks for any unprocessed feedback and feeds it to the AI agent
3. The agent can edit the val's own source code (e.g. add new data sources, change the script format)
4. Then generate-podcast.ts fetches live data and generates a TTS episode via ElevenLabs
5. The episode is stored as a blob and served via feed.ts as an RSS feed

Subscribe in any podcast app. Leave feedback via the web form. The AI agent processes it before the next episode.

File	Type	What it does
generate-daily.ts	interval	Cron trigger — processes feedback, then generates today's episode
generate-podcast.ts	script	Fetches data sources, builds script, calls ElevenLabs TTS
feed.ts	http	RSS feed, episode audio serving, feedback form (/feedback)
podcast-player.ts	http	Simple web audio player
agent.ts	script	Self-improving AI agent — reads own source, calls Claude, applies code edits
cover-art.ts	http	Podcast cover art
changelog.md	file	Log of all agent-applied changes
feature-ideas.md	file	Future ideas

Out of the box, the podcast script includes:

• Weather — via Open-Meteo (free, no API key). Default: New York. Edit WEATHER_LOCATIONS in generate-podcast.ts to change.
• Prediction markets — via Polymarket Gamma API (free, no API key). Empty by default — uncomment or add event slugs in POLYMARKET_EVENTS.

Want more? Just submit feedback like "Add top Hacker News stories" or "Include Bitcoin price" and the agent will wire it up.

1. Visit /feedback on the feed endpoint (linked in each episode description)
2. Submit text feedback — it's saved as a blob instantly
3. Next time generate-daily.ts runs, the agent reads all unprocessed feedback
4. The agent calls Claude with the full val source + your feedback
5. Claude outputs edit blocks → agent applies them via the Val Town API
6. Changes are logged in changelog.md
7. The (potentially updated) generate-podcast.ts runs to create that day's episode

1. Fork this val
2. Add environment variables:

Key	Description
ELEVEN_LABS_API_KEY	ElevenLabs text-to-speech API key
ANTHROPIC_API_KEY	Anthropic API key for Claude (used by agent)
TOWNIE_TOKEN	Val Town API token with write access (used by agent to edit its own files)

3. Update agent.ts — change VAL_UUID to your forked val's UUID
4. Set the interval schedule on generate-daily.ts (e.g. daily at 7am)
5. Subscribe to the RSS feed URL in your podcast app

Edit the constants at the top of each file:

• generate-podcast.ts — WEATHER_LOCATIONS, POLYMARKET_EVENTS, ELEVENLABS_VOICE_ID
• feed.ts — PODCAST_TITLE, PODCAST_DESCRIPTION, PODCAST_AUTHOR

Or just submit feedback and let the agent do it for you!

self-improving-podcast/
  episodes/       — MP3 files (2026-03-25-1711234567890.mp3)
  feedback/       — Feedback JSON blobs (timestamp.json)
  agent-runs/     — Agent execution logs