Wallie is an open-source AI streamer that actually feels alive. It reacts to your screen, reads live chat on Twitch/YouTube/Kick, animates a Live2D avatar with real lipsync, and never repeats itself — all running locally on your machine. Swap LLM and TTS providers freely. Start free with Groq + Piper. Zero cloud lock-in.
Hey Product Hunt! 👋
I've been obsessed with AI streamers for a while — but every existing solution felt the same: robotic narration, endless question loops, zero personality. They didn't feel alive.
So I built Wallie — an open-source AI streamer framework designed from the ground up to actually behave like a real person streaming.
Not just "AI reads text out loud." Wallie:
Develops thoughts over time instead of resetting every sentence
Reacts to your screen — notices when you switch games, start typing, or go idle
Reads live chat on Twitch, YouTube, and Kick — and responds in character
Remembers topics across a session (and across sessions)
Animates a Live2D avatar with real lipsync, mood-reactive expressions, and natural idle behavior
Never repeats itself — a deduplication engine catches paraphrased repetition within the same stream
And it runs on your machine. Your API keys stay local. You can even run it fully offline with Ollama + Piper — zero cloud, zero cost.
I've been building this for the past few months. It's fully open-source, MIT licensed, and genuinely free to start with Groq's free tier.
Would love to hear what you think — especially from VTubers and streamers who've tried other AI tools before. What made you give up on them? That's exactly what Wallie is designed to fix.
The deduplication engine catching paraphrased repetition is the detail that stood out most to me — that’s a genuinely hard problem. Most AI streamers sound like a broken record within 30 minutes. How does it handle the edge case where the same topic comes up organically in chat but from a different angle — does it detect the topic or the phrasing?
Also curious about the offline Ollama + Piper stack in practice. What’s the quality gap between the full cloud version and running fully local?
the reacts to your screen feature is the interesting differentiator here. most AI streamers just respond to chat which is a solved problem. an avatar that can comment on what's actually happening in the game or on screen is a different kind of presence. curious how the screen reading works, is it vision model calls on a frame interval or something else, and what the latency looks like between something happening on screen and Wallie actually reacting to it
About Wallie V2 on Product Hunt
“The open-source AI streamer that actually feels alive”
Wallie V2 launched on Product Hunt on June 3rd, 2026 and earned 73 upvotes and 7 comments, placing #26 on the daily leaderboard. Wallie is an open-source AI streamer that actually feels alive. It reacts to your screen, reads live chat on Twitch/YouTube/Kick, animates a Live2D avatar with real lipsync, and never repeats itself — all running locally on your machine. Swap LLM and TTS providers freely. Start free with Groq + Piper. Zero cloud lock-in.
Wallie V2 was featured in Open Source (68.5k followers), Developer Tools (513.4k followers), Artificial Intelligence (470k followers) and GitHub (41.2k followers) on Product Hunt. Together, these topics include over 202.2k products, making this a competitive space to launch in.
Who hunted Wallie V2?
Wallie V2 was hunted by Yelkhan . A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Wallie V2 stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Yelkhan