project-maya
project-maya is MiniMax-M3.1-Flash in Project Maya's own quants: the whole model in a 128 GB PC. MiniMax-M3.1-Flash-Maya-XS and -Maya-S on Maya: ./setup.sh --model minimax-maya-xs (or minimax-maya-s) runs our GGU.... It is ranked #45 on the Vibe Coding Radar, in Coding agents, first seen 18 h ago and shared in 2 posts (4k views).
Release v1.1.30 · mw00/project-maya · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation v1.1.30 Latest Latest Compare Choose a tag to compare Sorry, something went wrong. Filter Loading Sorry, something went wrong. Uh oh! There was an error while loading. Please reload this page . No results found View all…
What people said about project-maya on X
Project Maya v1.1.55 is out 🫡 🧑💻 Codex CLI now works with Maya: its grouped tools, reasoning and built-in tools are all handled. Tested with Codex CLI 0.160.0 on GLM-5.3-Flash, DeepSeek-V4.1-Flash and Qwen-3.8-Flash-Next 💬 Web chat: an answer always runs to its end unless you press Stop, even when you leave, and…
— @PeasantSmith, 18 h ago · 56 likes · see the post
Project Maya v1.1.55 is out !! Key updates: - DeepSeek-V4.1-Flash reads long prompts up to 4% faster on multi-GPU NVIDIA (prefill vs v1.1.54, same answers; decode unchanged) - DeepSeek-V4.1-Flash loads 31% faster on a Gorgon Halo - GLM-5.3-Flash keeps its attention cache in 8 bits by default: half the memory, the…
— @ItsmeAjayKV, 18 h ago · 17 likes · see the post
Alternatives to project-maya
- harness-lens — Harness Lens
- harness-leaderboard — Which coding-agent harness should you use for your model?
- opencode notes — stable release now available
- oh-my-hermes — ⚚ The coding harness with Hermes Agent wired into IDE. - rlaope/oh-my-hermes
- Devin Docs — Available AI models in Devin Desktop including SWE-2, Claude, and GPT. Compare model capabilities, pricing, credit…
- claude-code — 原 Issue：
project-maya in numbers
- Rank on the Vibe Coding Radar: #45 of 2591
- Shared in 2 posts by 2 accounts: @PeasantSmith, @ItsmeAjayKV
- 4k views on those posts
- First seen 18 h ago, last shared 18 h ago
- Pricing seen by AGK Intelligence: open source
- Market: Coding agents
FAQ
What is project-maya?
MiniMax-M3.1-Flash in Project Maya's own quants: the whole model in a 128 GB PC. MiniMax-M3.1-Flash-Maya-XS and -Maya-S on Maya: ./setup.sh --model minimax-maya-xs (or minimax-maya-s) runs our GGU... It was first shared on X 18 h ago and is ranked #45 on the Vibe Coding Radar.
Is project-maya free?
It is open source.
Who shared project-maya?
2 accounts on X, including @PeasantSmith, @ItsmeAjayKV, in 2 posts totalling 4k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 7.9k posts from 5k X accounts over the last 14 days, 2.6k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 12:43 UTC. Full method.