mw00

project-maya

Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.

AI & Agents新星 (90天内)
Stars
0
全站累计星标
Forks0社区衍生分支
LanguageCuda核心开发语言
Created2026-10-06已持续演进 0.1 年
Last push2026-10-30最新代码推送

Plain Talk · What Does It Actually Do?

Jargon-free breakdown of core value and use cases

project-maya is an open-source technical solution designed to automate workflows and save development hours.

Domain

AI & LLMs

Deliverable

Self-Hosted Service

Core Stack

Cuda

Milestone Forecast

Projected by recent velocity

Next Target5.0k ⭐
31% · 2.8k left
ETA
0d
2026.11.28
Velocity
+0/d
Avg rate
Rank
0%
Top tier

Star history

已连续追踪 28 天真实快照走势

区间净增势能+2.3k (225000.0%)
01.1k2.3k2026-10-032026-10-172026-10-30
TOPICS#cuda#deepseek#deepseek-v4#glm#glm-5#llm#llm-inference#local-llm

Vitality Telemetry

Emerging Star
Vitality Score
0/ 100A+
Strong momentum, production-ready
Commit Velocity99%
Very frequent recent commits
Community Resonance98%
High engagement & fork activity(Fork 率 13.2%)
Growth Momentum92%
~ +94 stars/day velocity

Quick-Start Console

1-click clone & package installation

CLI Ready
gitrank@pulse:~/project-mayaREADY
❯git clone https://github.com/mw00/project-maya.git

Trending in this topic

See more →
1
morluto

rea

+235/h Surging98 Vitality

Use AI agents to reverse engineer app behavior and native binaries with tool integrations.

TypeScript410k
+39k
2
Gathin23

cleanyourtv

+113/h Surging98 VitalityNEW

Debloat any Android or Google TV over Wi-Fi and get a clean Apple TV-style home screen.

Python46k
+19k
3
Ebony-Vinyl

dsh-our-free-model

+84/h Surging92 VitalityNEW

A dsh plugin that lets you use DeepSeek, Kimi and other frontier models free, with no login or API key.

JavaScript52k
+14k
4
Zagitta

gpu-unlock

+76/h Surging98 VitalityNEW

Unlocks limited FP16/BF16/TF32 tensor throughput on GeForce 20/30/40 series, up to 2× faster.

C13k
+13k