The Y Combinator Summer 2026 startup is betting that production traces can push routine work onto cheaper models customers own.
By Ryan Merket · Published
Primary source: Hacker News
Why it matters #
Model gateways are becoming control points for enterprise AI spending. Experiential Labs is betting that owning the traffic layer also creates the data needed to reduce dependence on rented frontier models.
Kion Fallah and Silen Naihin (@silennai) open-sourced a model router in July that uses an AI agent's production history to decide which model should handle each new request. Their larger bet is that the inference bill can eventually finance its own replacement.
The two founders are building Experiential Labs, a San Francisco company in Y Combinator's Summer 2026 batch. Experiential Labs sits between an agent and the models it calls, offering one OpenAI-compatible endpoint for hosted providers, customer-owned API keys, local models and custom models. The gateway also records the traces needed to evaluate cheaper alternatives and train specialized models.
Fallah came to the problem from autonomous driving. He earned a machine learning Ph.D. at Georgia Tech, then led development of a mixed-reality simulator at Waabi for testing autonomous vehicles. His thesis at Experiential Labs carries that method into software agents: simulate the environment, replay difficult cases and test proposed changes before putting them into production.
Naihin approached the same problem through open-source agents and continual learning. Y Combinator's profile credits him with helping AutoGPT grow to about 160,000 GitHub stars. His personal biography says he later worked with the U.S. Department of Energy on AI for scientific discovery and spent two years running Stackwise, a YC Winter 2024 company.
Those backgrounds explain why Experiential Labs is trying to build an improvement loop rather than another static proxy for model APIs.
A gateway with memory
In a July Hacker News post, Naihin introduced World Model Optimizer, an open-source tool that ingests agent traces and constructs text simulations of the tools and environments an agent encounters. It runs candidate models against those simulated tasks, embeds the requests and fits a K-nearest-neighbor router that selects a model based on similar past work.
The router can optimize for cost or quality and accounts for prompt caching when estimating the effective price of a request. Confidence gates keep it from switching away from the strongest known model when the available evidence is weak or when a request looks unlike the router's training examples.
That process gives Experiential Labs a path beyond ordinary provider routing. A conventional gateway can send a request to the cheapest available host, fail over during an outage or enforce a budget. Experiential Labs wants the gateway to learn which classes of work can move to cheaper open models and, eventually, to a specialized model trained on the customer's own traces.
The current open-source repository combines the gateway and optimization workflow. Developers can run the gateway locally, connect provider keys and build a router from OpenTelemetry traces. The repository had more than 380 GitHub stars at the time of the supplied research.
Experiential Labs says customers will own the weights produced through its training workflow. That ownership pitch gives the founders a direct answer to the recurring complaint that companies spend heavily on frontier inference while accumulating little infrastructure they can operate independently.
The benchmarks still belong to Experiential Labs
Experiential Labs reported three self-run routing results in its July post. On RouterBench, the router cut cost by 66.5% while performance fell 1.7%. On TauBench, Experiential Labs reported 44.5% lower cost and 6.3% higher performance. On Terminal Bench 2, Experiential Labs reported a 64% cost reduction and an 8% performance increase.
Those figures measure configurations chosen and run by Experiential Labs. They are not independent validation, and they do not establish that a router trained on one customer's traces will deliver similar savings on another customer's workload.
The launch discussion exposed the more important proof gap. One commenter asked Experiential Labs to release a model trained with the method and show the improvement over its base model.
Experiential Labs makes broader claims elsewhere, including up to 97% lower cost on some tasks and a guarantee of 50% savings at equal or better quality. Those claims remain company assertions. Experiential Labs has not published customer counts, revenue or the contract terms behind the guarantee.
The gateway is the wedge
The gateway market already has well-funded incumbents. OpenRouter provides unified access, routing and failover across model providers. In its May 2026 financing announcement, OpenRouter said it raised a $113 million Series B and was processing 25 trillion tokens a week for more than 8 million developers.
LiteLLM offers a self-hosted open-source gateway, while Vercel AI Gateway bundles hundreds of models behind one endpoint with budgets, observability and provider failover. Portkey raised a $15 million Series A in February to expand its enterprise gateway and governance products.
Experiential Labs cannot win by offering another menu of models. Its stated distinction is an optimization layer that uses agent traces and simulations to build a customer-specific router or specialized model. If that loop works, each production request becomes evidence for moving future work away from expensive frontier capacity.
Open source helps lower the trust barrier. Developers can inspect and run the routing code locally before sending production traces to a hosted service. Experiential Labs can then sell managed training, serving and continual optimization to customers that do not want to operate the pipeline themselves.
Naihin says Experiential Labs has backing from Y Combinator and angels affiliated with Meta, Google DeepMind, Nvidia and Waabi. Experiential Labs has not announced the amount raised or named the individual angel investors.
The founders have picked a problem with clear economics: agents generate repetitive work, frontier models charge for every repetition, and production traces contain evidence about which requests need expensive reasoning. Experiential Labs now has to prove that its simulations reflect real environments closely enough to make routing and training decisions customers can trust. The open-source release gives developers the machinery to test that claim rather than taking another AI cost-saving promise at face value.