ATH-MaaS/Marco-o1

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1538 stars · 81 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Marco-o1 is an open large reasoning model from Alibaba International Digital Commerce, designed for o1-like chain-of-thought reasoning across math, physics, coding, and open-ended tasks. The repository provides model weights, training data, and tooling for building agentic applications with planning and function-call capabilities.

Use cases

• run an open reasoning model for complex problem solving
• fine-tune a large reasoning model on custom data
• build agents with planning and function calling
• solve math and coding problems with chain-of-thought reasoning
• experiment with o1-style reasoning models
• evaluate multilingual reasoning performance

When to choose

• you need an open-weights reasoning model you can self-host
• you want to study or extend o1-like reasoning approaches
• you need an agentic model with function call abilities

When to avoid

• you need a small model for resource-constrained devices
• you only need simple chat without deep reasoning
• you require a permissive license without restrictions

Facets

library · maturity active

llm-inference llm-training machine-learning agent-framework large-language-models artificial-intelligence python reasoning-model open-weights reinforcement-learning chain-of-thought alibaba ai-agents natural-language-processing gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ATH-MaaS/Marco-o1")