MiroMindAI/MiroThinker

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the...

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 7 minutes ago
Added to GitGenius on January 9th, 2026
Created on August 7th, 2025
Open Issues & Pull Requests: 2 (+0)
Number of forks: 642
Total Stargazers: 8,361 (+0)
Total Subscribers: 91 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 3.8 days
Mean response time: 19.6 days
90th percentile: 64.9 days
Tracked items: 71

How this project is maintained

Around half of the issues opened in the past year never receive a reply. Only 19% of issues opened in the past year have been closed. Three people close 69% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 3
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 6 days
Stale 30+ days: 2
Stale 90+ days: 1

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • enhancement (4)
  • question (1)

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

MiroThinker is a deep research agent optimized for complex research and prediction tasks.

The tool addresses the need for autonomous systems capable of conducting thorough research and making informed predictions by combining language model reasoning with web search and document analysis capabilities. It operates as an agent framework that can process queries, search for relevant information, and synthesize findings into coherent research outputs. The system supports multiple document formats and can generate research reports that users can preview and share.

Developers should consider MiroThinker if they need to build applications requiring deep research capabilities or predictive analysis at scale. The project offers both open-source models of varying sizes and a proprietary agent, allowing teams to choose between parameter efficiency and maximum performance depending on their constraints. The tool is accessible through an online interface for experimentation before integration, making it suitable for teams evaluating research agent functionality without immediate infrastructure investment.

The project typically responds to issues and pull requests within one to two weeks. Development activity centers on enhancement requests and user questions, indicating ongoing refinement of existing capabilities and community engagement around usage patterns.