Experiential: Route AI model requests through one controlled gateway
Added · Updated
Made by Experiential Labs
View profile on GitHub (opens in a new tab)Send requests to hosted, your-own-key, or local AI models through one gateway.
For developers running AI agents who want spending and access controls.
What it does
Experiential sits between your apps and AI models. It offers one OpenAI-compatible API, meaning tools built for OpenAI's request format can talk to it. It reaches hosted models, models paid through your own provider keys (BYOK, bring your own key), and local models. It can also turn recorded traffic into a custom router that picks models for quality, speed and cost.
How to use it
Start the local gateway; on first run a setup wizard asks you to pick providers and models, shows a default budget, then prints a one-time key. Send requests with that key. A hosted gateway on the creator's platform also exists, separate from the local version.
Common use cases
- Point a coding agent such as Claude Code or Cursor at the gateway, so its model calls follow your budget and access rules.
- Give the build command a file of recorded agent traces and get a project router that chooses models for your tasks.
- Decide which users and agents may use which models and how much they can spend, then send their requests through the gateway.
Can I use this?
Requirements Follow Getting Started in the project's documentation to run the local gateway, or create an account on the hosted platform. SETUP.md has copy-paste prompts you can hand to a coding agent so it runs setup for you.
Caveat Capturing desktop app traffic is experimental, and macOS network reliability is still under investigation. Anonymous telemetry is enabled by default; the source says it never includes prompts, traces or credentials.
Worth knowing Traffic capture is experimental and needs macOS and Python 3.13 or newer. Anonymous product telemetry is on by default. Hardware requirements are not documented. Licensed under Apache License 2.0.
Why it's here
Not trending this week
Last seen on the GitHub trending list on 25 October 2026. It stays on BuildTube so you can still find it.
- 15,251 people have starred it on GitHub.
Numbers checked on 8 November 2026; not refreshed since.
Behind it
View setup guideBuildTube has not run or verified this project. Everything above is written from what the creator published.
Made this?
Quick questions
- What is Experiential?
- Experiential sits between your apps and AI models.
- What can I use Experiential for?
- Point a coding agent such as Claude Code or Cursor at the gateway, so its model calls follow your budget and access rules; Give the build command a file of recorded agent traces and get a project router that chooses models for your tasks; Decide which users and agents may use which models and how much they can spend, then send their requests through the gateway
- Can I run Experiential on my computer?
- It runs from a terminal on your own computer. Capturing desktop app traffic is experimental, and macOS network reliability is still under investigation. Traffic capture is experimental and needs macOS and Python 3.13 or newer. Hardware requirements are not documented.
- What do I need to use Experiential?
- A computer to run the local gateway, or an account on the hosted platform. Your own provider keys if you bring them.
- What license does Experiential use?
- Licensed under Apache License 2.0.
More from this week
- agent-desktop Let AI agents read and click desktop apps
For developers building computer-use agents: agent-desktop lets an AI agent read and operate desktop apps on Mac, Windows or Linux from a command line.
- Auto-Ontology Give AI agents checked business meanings for your database
Help AI agents answer questions about company databases using reviewed definitions and SQL, with each answer showing its steps.
- Spec Kit Turn a written spec into plans, tasks and code
Spec Kit gives your AI coding agent a step-by-step process to build a feature, fix a bug or assess an idea.
Explore by topic
Post this
Download share imageFor makers
Made this? Show it’s on BuildTube — add the badge to your README or embed the card on your site.
README badge (Markdown)
[](https://buildtube.app/p/gh-experientiallabs-experiential/)Embed card (HTML)
<iframe src="https://buildtube.app/embed/gh-experientiallabs-experiential/" width="560" height="240" style="border:0;max-width:100%" loading="lazy" title="Experiential on BuildTube"></iframe>