TL;DR: Osmosis is a Y Combinator Winter 2025 startup Reinforcement Learning (RL) for AI Agents, currently active with a team of 6.
Reinforcement Learning (RL) for AI Agents
Last verified:
Osmosis is a post-training platform that helps companies fine-tune language models using reinforcement learning. We work with fast-growing AI companies to train task/domain-specific models that beat foundation models on performance, cost, and latency. Our platform handles compute orchestration, reward modeling, and training run observability as a CLI-based product usable by developers and agents.
Built by LemStudio
Yes. Osmosis was funded by Y Combinator in the Winter 2025 batch. Reinforcement Learning (RL) for AI Agents
Osmosis is a post-training platform that helps companies fine-tune language models using reinforcement learning. We work with fast-growing AI companies to train task/domain-specific models that beat foundation models on performance, cost, and latency. Our platform handles compute orchestration, reward modeling, and tr…
Osmosis was part of Y Combinator's Winter 2025 batch.
Osmosis has a team of 6 people according to Y Combinator's directory.
Osmosis is currently listed as Active with a team of 6 in Y Combinator's directory.
Loading interactive view…