Ross ROSS = Recommend OSS · open-source software intelligence for agents

modular/modular

The Modular Platform (includes MAX & Mojo) observed · 2026-08-28

github.com/modular/modular · homepage · Mojo · NOASSERTION (other) observed · 2026-08-28

Health v2 · maintenance only

92/100

  • Activity 99
  • Release rhythm 85
  • Longevity 87

Flags: no_license

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 48
  • age_days: 1223
  • days_rel: 22
  • days_push: 7
  • n_releases_24m: 14

Full methodology

Adoption not part of the score

29225 stars · 3109 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Modular Platform hosting the MAX AI serving framework and the Mojo systems programming language. It provides an OpenAI-compatible inference server, GPU kernels, and a Pythonic systems language for high-performance AI development.

Use cases

  • serve llm inference with openai-compatible api
  • write fast gpu kernels for ai
  • accelerate python code with a systems language
  • deploy models across nvidia and amd gpus
  • build custom model pipelines

When to choose

  • you need high-performance llm serving on diverse gpu hardware
  • you want a pythonic systems language for ai kernels

When to avoid

  • you need a fully permissive license for all components
  • you only need a simple python inference setup

Facets

framework · maturity active

llm-inference llm-training compiler programming-language gpu-computing machine-learning artificial-intelligence machine-learning large-language-models programming-languages gpu-computing python cross-platform mojo max-framework inference-server ai-platform openai-compatible gpu linux macos

3 sources

Member repositories

RepositoryRoleHealth v2
modular/modularmain92

For agents

markdown · JSON · MCP: product_card(name="modular/modular")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem