platoseed
Live Environments for Training AI Agents
Powering frontier AI labs with real world MCP environments and complex, long-horizon agentic tool-use data.
Klavis AI provides live environments for training AI agents, offering realistic, long-horizon tasks and multi-app state for agentic workflows. They position themselves as live infrastructure for frontier AI labs with MCP-based tooling and plug-and-play simplicity.
Live sandboxes with auth, seeded state, state export, resets, and parallel isolation for training and evaluation runs; managed sandboxes with full environment fidelity across 300+ services; supports long-horizon, complex agentic tasks that span browser sessions, code repos, SaaS tools, and MCP servers; includes a View Sandbox API and an Eval Protocol (MCP) framework to run RL on production agents and expose state, traces, and rewards.
Who itβs for: AI labs and organizations building/benchmarking agents that require realistic, long-horizon, multi-app environments and MCP-based tool-use data.
Funding from YC and seed investors; SOC 2 Type II and GDPR compliant; open-source and community mentions; active documentation and pricing pages.
Co-founder @ Klavis AI. Previously Senior Software Engineer on Google Gemini at Google Deepmind. Co-authored Gemini paper. I have a CS MS from Carnegie Mellon University. I have a Bachelor of Engineering in Computer Science and Technology from Beihang University.
Co-Founder at Klavis AI 1. Senior Software Engineer at Lyft, tech lead at Lyft recommendation team and Nordstrom data infra team, building product supports millions of users in the last 5 years. 2. CS MS from Northeastern University, Bachelor of Engineering in Computer Science and Technology from Beihang University. 3. The President of the Computer Science Student Council (CSSC) at Beihang University. Research Experience at the NLP Lab and Internship at Baidu.
Klavis AI is open source MCP integrations for AI Applications. Our API provides hosted, secure MCP servers, eliminating auth management and client-side code.
Klavis AI offers open-source MCP integrations for AI applications, with hosted, enterprise-grade MCP servers that provide built-in OAuth and multi-tenancy authentication. It enables immediate secure connections to external MCP servers via API or pre-built clients, reducing client-side development and supporting scalable use.

Environments for Long Horizon Tool Use

RL environments for long horizon AI Agents