RunAnywhere is a Y Combinator W26 company building infrastructure for deploying multimodal AI on edge devices at scale. Its platform includes a unified SDK for on-device model execution across iOS, Android, React Native, and Flutter, plus a control plane that enables hybrid routing between local and cloud inference based on device capabilities and policies. The company maintains an open-source SDK on GitHub. RunAnywhere is based in the San Francisco Bay Area and was founded in 2025.
RunAnywhere
ActiveThe default way of running on-device AI at Scale
Total raised
$500K
1 round
Stage
Seed
Jan 2026
Team
1-10
since 2026
Pricing
—
Founded
2026
San Francisco, United States
Agent-ready
—
Infrastructure for running multimodal AI on-device at scale
Unified SDK across iOS, Android, React Native, and Flutter
Control plane for hybrid local and cloud inference routing
Routing decisions based on device capabilities and policies
On-device model execution for multimodal workloads
Open-source SDK maintained on GitHub
Cross-platform deployment from a single integration
Scaling of edge AI across diverse devices
12/100
Early
MCP server
Public API
Webhooks
OAuth 2.0
SDKs
No public agent surfaces detected yet.
Jan 2026 Seed $500K ● Y Combinator
Capital network
$500K raised ·1 backer·10 network links
- Backers1
- Shared portfoliocompanies these backers also fund
- Extended networkfunds that co-invest alongside them
Databricks
The data + AI company
AI AgentsAI Infrastructure
Figure AI
General-purpose humanoid robots
AI InfrastructureAI Robotics
Upscale AI
Pure-play AI networking infrastructure
AI Developer ToolsAI Infrastructure
Dash0
AI-native observability platform built on OpenTelemetry
AI InfrastructureAI Data Engineering
Noma Security
End-to-end security for agentic AI
AI InfrastructureAI for Cyber Defense
Ineffable Intelligence
An AI research company building a superlearner to achieve superintelligence through reinforcement learning
Foundation ModelsAI Infrastructure
- What is RunAnywhere?
- RunAnywhere provides infrastructure for running multimodal AI on-device at scale, with a unified SDK across iOS, Android, React Native, and Flutter and a control plane for hybrid inference routing.
- How does hybrid routing work?
- A control plane routes inference between local and cloud based on device capabilities and policies, balancing performance, cost, and privacy.
- Is RunAnywhere open source?
- The company maintains an open-source SDK on GitHub for on-device model execution.
- Which platforms does the SDK support?
- The unified SDK supports iOS, Android, React Native, and Flutter.
Discussion
Sign in to join the discussion.
Sign inExplore more around RunAnywhere
Contextual paths to related AI startups, deals and rankings.