MasterAgent

Build AI agents that run 100% on-device. Sub-100ms latency on Qualcomm NPU. Zero cloud dependency.

OpenSparX/MasterAgent

View on GitHub ↗

Build AI agents that run 100% on-device. Sub-100ms latency on Qualcomm NPU. Zero cloud dependency.

MasterAgent grew +7.7% in the last 30 days, ranks 40th of 171 in Web / Edge / On-Device Runtime, last commit 48 days ago.

Star trajectory

90 days tracked
2026-08-16976 stars today2026-11-15
Momentum

+7.7% in 30d, above the Web / Edge / On-Device Runtime median of +2.0%.

Maintenance

Last commit 48 days ago, staler than the median of 7d.

How it compares in Web / Edge / On-Device Runtime

MasterAgent
976
stars
+7.7% 30d
commit 48 days ago
Web / Edge / On-Device Runtime median
315
stars
+2.0% 30d
commit ~7d ago
Leader · mlc-llm
23.4k
stars
+0.8% 30d
commit today

Ranked 40th of 171 by stars.

Ranked by shared tags, then keywords, then stars
  1. Run local LLM from Huggingface in React-Native or Expo using onnxruntime.

    +0 (+0.0%) in 30d · Committed 490d ago · TypeScript · MIT

    Shares Web / Edge / On-Device Runtime, Inference Optimization, Local Runtime / Inference Engine

  2. A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX…

    +218 (+2.7%) in 30d · Committed today · Python · MIT

    Shares Local Runtime / Inference Engine, Web / Edge / On-Device Runtime, Inference Optimization

  3. Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

    +452 (+6.5%) in 30d · Committed today · Swift · Apache-2.0

    Shares Web / Edge / On-Device Runtime, Inference Optimization, Local Runtime / Inference Engine

  4. A high-performance inference engine for AI models

    +987 (+42%) in 30d · Committed today · Rust · MIT

    Shares Local Runtime / Inference Engine, Inference Optimization, Web / Edge / On-Device Runtime

  5. The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in…

    +119 (+4.6%) in 30d · Committed 7d ago · Python · Apache-2.0

    Shares Local Runtime / Inference Engine, Inference Optimization, Web / Edge / On-Device Runtime

  6. Instant, controllable, local pre-trained AI models in Rust

    +10 (+0.4%) in 30d · Committed 21d ago · Rust · Apache-2.0

    Shares Local Runtime / Inference Engine, Inference Optimization, Web / Edge / On-Device Runtime

  7. Run LLMs on AMD Ryzen™ AI NPUs in minutes; purpose-built and deeply optimized for the AMD NPUs.

    +91 (+4.6%) in 30d · Committed today · C++ · Other license

    Shares Web / Edge / On-Device Runtime, Local Runtime / Inference Engine, Inference Optimization

  8. NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.

    +101 (+6.4%) in 30d · Committed yesterday · Rust · EUPL-1.2

    Shares Local Runtime / Inference Engine, Web / Edge / On-Device Runtime, Inference Optimization

  9. Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable

    +173 (+17%) in 30d · Committed 8d ago · Python · MIT

    Shares Local Runtime / Inference Engine, Inference Optimization, Web / Edge / On-Device Runtime

  10. Run full Kimi K3 on a single device. And an OpenAI-compatible API server for local chat and coding agents.

    +9 (+1.1%) in 30d · Committed 42d ago · Rust · Other license

    Shares Local Runtime / Inference Engine, Inference Optimization, Web / Edge / On-Device Runtime

Language
C++
License
Apache License 2.0
Contributors
4
Forks
37
Watchers
0
Open issues
0
Releases
3
Created
2026-08-10
Stars this week
-4

You've seen where MasterAgent stands today.

Get the moves before everyone else: the 5 Web / Edge / On-Device Runtime repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain MasterAgent?

Claim this page to add your own call-to-action.

Claim this page