discover · compare · collections · requirements · contribute · feed · watching · stats · help with your tokens
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 BrowseComp and BrowseComp Zh, respectively.
History and source changes · Reports and owner responses · Compare
Similar
- 666ghj/BettaFish
微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。
Why this match
topics agent-framework, deep-research; license differs: Apache-2.0 → GPL-2.0
- Alibaba-NLP/DeepResearch
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Why this match
topics agent, deep-research
- datawhalechina/happy-llm
📚 从零开始构建大模型
Why this match
topics agent; language differs: Python → Jupyter Notebook
- aden-hive/hive
Multi-Agent Harness for Production AI
Why this match
topics agent, agent-framework
- shaxiu/XianyuAutoAgent
智能闲鱼客服机器人系统：专为闲鱼平台打造的AI值守解决方案，实现闲鱼平台7×24小时自动化值守，支持多专家协同决策、智能议价和上下文感知对话。
Why this match
topics agent; license differs: Apache-2.0 → GPL-3.0
- open-slide/open-slide
A slide framework built for agents.
Why this match
topics agent; language differs: Python → TypeScript; license differs: Apache-2.0 → MIT
- bytedance/deer-flow
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
Why this match
topics agent, deep-research; license differs: Apache-2.0 → MIT
- bytedance/trae-agent
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
Why this match
topics agent; license differs: Apache-2.0 → MIT