LightfieldAI-native CRM that builds itself and does work for you
Promoted
Launched this week
Experiential Labs
Open source AI gateway turning traffic into a better model
182 followers
Open source AI gateway turning traffic into a better model
182 followers
Experiential is the open source, zero markup gateway for BYOK, self-hosted and 1000+ marketplace models. It learns from your traffic to cut costs, recommend better models, and train a specialized model you own.
Experiential Labs
Hey Product Hunt 👋
We’re Kion and Silen, two AI researchers. Every time we wanted to try a new model, we had to create another account, manage another key, and track spend in another place.
We looked for an open source solution that combined model access, usage management, and a marketplace without adding another tax to every token. We couldn’t find one, so we built Experiential.
Experiential gives developers and companies one key for more than 1,000 models. You can use our marketplace, bring your own provider keys, or connect models running locally or in your cloud, all with zero token markup.
It's also more than just a gateway.
Every request shares one trace format, so the platform can catch cache misses and wasted tokens, recommend better models, identify work that should run asynchronously or in batches, and train specialized models that you own.
Since launching on Hacker News a week ago, more than 1000+ developers and 50+ companies have used Experiential to process over 10 billion tokens daily, and the repository has reached 880+ GitHub stars.
For the launch, GPT-6 Astra, DeepSeek V4 Flash, Qwen 3.8 27B, GPT-5.6 Luna, and Fable 5.1 on release are free through the end of the week 🎁
We’d love your feedback - experientiallabs.ai
And a star - github.com/experientiallabs/experiential
@silennai are there any plans to easily support custom local models that aren't on the marketplace yet?
Experiential Labs
@priya_kushwaha1 Local models are supported by default!
@silennai The parts learn from traffic is what caught my attentions, it could be really useful for finding waste tokens are hard to identify manually.
Congratulation on the launch team!
Congrats on the launch! Is cache locality part of routing cost? At want point warm cache outweigh routing gains?
Experiential Labs
@dmytriis It is, cache is prioritized when possible. Requests remember when the cache is warm and prefer retries over routing depending on if cost or availability is more important to you.
I want to ask if its secure and safe to actually entering our bank account to use most of model?
Experiential Labs
@an_nguyen44 Yes, we use Stripe for maximum security.
Taika
Excited to try this out - how well does it work through Codex vs. Claude Code?
Experiential Labs
@kalfreese Both are native integrations https://platform.experientiallabs.ai/docs/coding-agents
How are you guys able to get the GPT Astra and Claude Fable 5.1 free of cost? Just curious to know the token usage limit for that
It's open router without the 5% markup. If you use an api for model calls this couldn't be easier to slip in between and manage all your models in one place. It's greatly reduced my downtime, and cost me nothing.
Experiential Labs
@anstewe You're amazing Andrew, thanks for being a beta tester!
Tadata
@anstewe I was wondering about this comparison. thanks!
How does Experiential handle sensitive prompts and traffic data when learning from usage?
Experiential Labs
@lonny_shatzel We offer ZDR and allow you to host in your own cloud!
@lonny_shatzel our open source repo contains embedded guardrails models in the gateway to strip PII/sensitive content in prompts and responses. Incorporating it into the web platform shortly.