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.
🏆 Top-1 on 5+ benchmarks | Web UI | Supports MiroThinker, Claude, Kimi, OpenAI
A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.
An autonomous research colleague — from a question to a compiled manuscript, while you sleep.
900+ pure-markdown skills for autonomous AI research, organized as 9 freely-composable packages over a 4-layer hierarchy (Campaign → Strategy → Tactic → SOP). Non-linear orchestration with backtracking, 6 MCP integrations. The AI is the researcher — you set the direction.
[ICML 2025] ResearchTown: Simulator of Human Research Community
DeepEvolve is a research and coding agent for new algorithm discovery in different science domains with Deep Research and AlphaEvolve.
Pressure-test research claims with falsifiable evidence plans, adversarial checks, frozen verifiers, and proof ledgers.
Idea-Catalyst is a metacognition-driven framework for helping humans and LLMs boost their creativity during the scientific brainstorming process.
Privacy-safe Hermes researcher agent for public-source research, document ingestion, evidence grading, and decision-ready briefs
Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.
AI dev that actually gets things done
🔍 AI-powered deep research agent with Web UI. Built on smolagents, featuring process-based architecture, MetaSo/DuckDuckGo search, and Docker deployment. Apache 2.0 licensed.
An agentic AI tool for searching, screening, and ranking NIH funding opportunities based on research interests and proposal relevance.
Configurable deep research assistant
DeFi protocol research agent for Solana. Scores protocols on security, traction, tokenomics, team, and moat using Claude.
TreeThinkerAgent is a lightweight orchestration layer that turns any LLM into an autonomous multi-step reasoning agent. It supports multi-step planning, tool execution, and final synthesis while exposing the entire reasoning process as a tree you can explore.
Reliable research infrastructure for AI agents. Evidence-backed web search with citations, confidence scores, and Clarity anti-hallucination. MCP server, REST API, Python SDK.
Open Source Deep Research and Learning Agent (Perplexity Pro Alternative). Orchestrates autonomous researchers using LangGraph, Python, and Next.js for students, developers, and lifelong learners.
Add a description, image, and links to the research-agent topic page so that developers can more easily learn about it.
To associate your repository with the research-agent topic, visit your repo's landing page and select "manage topics."