logo

software-mansion/react-native-executorch

High-performance, privacy-first on-device AI inference library for React Native, powered by PyTorch's ExecuTorch runtime

Owned by Software Mansion

View on GitHub ↗Jump to charts ↓Open shareable report →

software-mansion/react-native-executorch has 1.5k+ stars and 90+ forks on GitHub, is written in TypeScript, and was last pushed on Oct 16, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 14 minutes ago
Type:Library / SDKCategory(s):LLM Inference & Local ModelsCross-Platform & Desktop App FrameworksAI Agents & LLM Apps
Added to GitGenius on October 12th, 2026
Created on October 16th, 2024
Open Issues & Pull Requests: 51 (+0)
GitHub issues: Enabled
Number of forks: 97
Total Stargazers: 1,766 (+0)
Total Subscribers: 14 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 5.5 hours
Mean response time: 19.6 days
90th percentile: 72.1 days
Tracked items: 494

Most active contributors

Sign in to see contributor activity.
Sign in

Related repositories by overlapping contributors

Maintainer activity

11 people did triage or write work on this repository in the last 12 months.

Counts unlabeled, assigned, unassigned, milestoned, demilestoned, locked, unlocked over the last 12 months. These are issue and pull request events that require triage or write permission. Commits and code review are not counted. labeled and renamed are excluded because GitHub issue forms record the issue author as the actor. Figures from October 18, 2026. This count is not comparable across projects: each project's automation decides which of these events a person emits. How this is counted.

How this project is maintained

Practically every issue opened in the past year has drawn a reply. Only 23% of open issues come from outside the core team — the tracker reads mainly as internal planning. Work labelled "test" is answered fastest, typically in under an hour, while "improvement" waits about 6 days. 87% of issues opened in the past year have been closed, leaving a working backlog. Three people close 60% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 39
New in 7 days: 6
Closed in 7 days: 4
Avg open age: 119 days
Stale 30+ days: 19
Stale 90+ days: 5

Recent activity

Opened in 7 days: 6
Closed in 7 days: 4
Comments in 7 days: 2
Events in 7 days: 24

Top labels

  • model (74)
  • refactoring (50)
  • user exp (47)
  • documentation (41)
  • improvement (41)
  • performance (29)
  • idea (24)
  • 3rd party package (17)

Most active issues this week

Sign in to see which issues are moving.
Sign in
Explore full issue details

Detailed Description

react-native-executorch is a library that enables high-performance on-device AI inference in React Native applications using PyTorch's ExecuTorch runtime.

The library addresses the need to run machine learning models directly on mobile devices while preserving user privacy and reducing latency. Rather than sending data to remote servers, it executes AI models locally on the device. The tool leverages ExecuTorch, PyTorch's optimized runtime designed for mobile and edge inference, and exposes this capability through React Native bindings so developers can integrate on-device AI into their JavaScript-based mobile applications.

Developers should choose this tool when building React Native applications that require AI capabilities such as computer vision, object detection, optical character recognition, speech processing, or language model inference, and when keeping data on-device is a priority. The library suits projects where latency must be minimized and user data should not leave the device. It is particularly valuable for applications handling sensitive information or operating in environments with unreliable network connectivity.

The project shows active development with regular commits addressing bug fixes, feature additions, and improvements to the inference pipeline. Documentation is maintained and updated to reflect current capabilities and usage patterns. The codebase receives ongoing refinement to optimize performance and expand model support across different device architectures. Community engagement through issue tracking and pull request reviews indicates sustained attention to user needs and technical quality.