"text":"Conduct a research on https://github.com/bytedance/deer-flow"
}
],
"additional_kwargs":{},
"response_metadata":{},
"type":"human",
"name":null,
"id":"7da141e4-3ab2-43d0-8485-5128f623c0c4"
},
{
"content":"",
"additional_kwargs":{
"reasoning_content":"The user wants me to conduct research on the GitHub repository https://github.com/bytedance/deer-flow. This is a GitHub repository URL, which matches the github-deep-research skill. The skill is designed for comprehensive analysis of GitHub repos. I should first load the skill file to understand the workflow, then follow it.\n\nFirst, I need to check if there are any uploaded files. The system prompt mentions uploaded files are listed before each request, but I don't see an <uploaded_files> section. So I'll proceed.\n\nI should load the github-deep-research skill first. The path is /mnt/skills/public/github-deep-research/SKILL.md. Let me read it."
"content":"---\nname: github-deep-research\ndescription: Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams. Triggers on Github repository URL or open source projects.\n---\n\n# GitHub Deep Research Skill\n\nMulti-round research combining GitHub API, web_search, web_fetch to produce comprehensive markdown reports.\n\n## Research Workflow\n\n- Round 1: GitHub API\n- Round 2: Discovery\n- Round 3: Deep Investigation\n- Round 4: Deep Dive\n\n## Core Methodology\n\n### Query Strategy\n\n**Broad to Narrow**: Start with GitHub API, then general queries, refine based on findings.\n\n```\nRound 1: GitHub API\nRound 2: \"{topic} overview\"\nRound 3: \"{topic} architecture\", \"{topic} vs alternatives\"\nRound 4: \"{topic} issues\", \"{topic} roadmap\", \"site:github.com {topic}\"\n```\n\n**Source Prioritization**:\n1. Official docs/repos (highest weight)\n2. Technical blogs (Medium, Dev.to)\n3. News articles (verified outlets)\n4. Community discussions (Reddit, HN)\n5. Social media (lowest weight, for sentiment)\n\n### Research Rounds\n\n**Round 1 - GitHub API**\nDirectly execute `scripts/github_api.py` without `read_file()`:\n```bash\npython /path/to/skill/scripts/github_api.py <owner> <repo> summary\npython /path/to/skill/scripts/github_api.py <owner> <repo> readme\npython /path/to/skill/scripts/github_api.py <owner> <repo> tree\n```\n\n**Available commands (the last argument of `github_api.py`):**\n- summary\n- info\n- readme\n- tree\n- languages\n- contributors\n- commits\n- issues\n- prs\n- releases\n\n**Round 2 - Discovery (3-5 web_search)**\n- Get overview and identify key terms\n- Find official website/repo\n- Identify main players/competitors\n\n**Round 3 - Deep Investigation (5-10 web_search + web_fetch)**\n- Technical architecture details\n- Timeline of key events\n- Community sentiment\n- Use web_fetch on valuable URLs for full content\n\n**Round 4 - Deep Dive**\n- Analyze commit history for timeline\n- Review issues/PRs for feature evolution\n- Check contributor activity\n\n## Report Structure\n\nFollow template in `assets/report_template.md`:\n\n1. **Metadata Block** - Date, confidence level, subject\n2. **Executive Summary** - 2-3 sentence overview with key metrics\n3. **Chronological Timeline** - Phased breakdown with dates\n4. **Key Analysis Sections** - Topic-specific deep dives\n5. **Metrics & Comparisons** - Tables, growth charts\n6. **Strengths & Weaknesses** - Balanced assessment\n7. **Sources** - Categorized references\n8. **Confidence Assessment** - Claims by confidence level\n9. **Methodology** - Research approach used\n\n### Mermaid Diagrams\n\nInclude diagrams where helpful:\n\n**Timeline (Gantt)**:\n```mermaid\ngantt\n title Project Timeline\n dateFormat YYYY-MM-DD\n section Phase 1\n Development :2025-01-01, 2025-03-01\n section Phase 2\n Launch :2025-03-01, 2025-04-01\n```\n\n**Architecture (Flowchart)**:\n```mermaid\nflowchart TD\n A[User] --> B[Coordinator]\n B --> C[Planner]\n C --> D[Research Team]\n D --> E[Reporter]\n```\n\n**Comparison (Pie/Bar)**:\n```mermaid\npie title Market Share\n \"Project A\" : 45\n \"Project B\" : 30\n \"Others\":25\n```\n\n##ConfidenceScoring\n\nAssignconfidencebasedonsourcequality:\n\n|Confidence|Criteria|\n|------------|----------|\n|High(90%+)|Officialdocs,GitHubdata,multiplecorroboratingsources|\n|Medium(70-89%)|Singlereliablesource,recentarticles|\n|Low(50-69%)|Socialmedia,unverifiedclaims,outdatedinfo|\n\n##Output\n\nSavereportas:`research_{topic}_{YYYYMMDD}.md`\n\n###FormattingRules\n\n-Chinesecontent:Usefull-widthpunctuation（，。：；！？）\n-Technicalterms:ProvideWiki/docURLonfirstmention\n-Tables:Useformetrics,comparisons\n-Codeblocks:Fortechnicalexamples\n-Mermai
"additional_kwargs":{},
"response_metadata":{},
"type":"tool",
"name":"read_file",
"id":"4bf0cb1a-a66c-4eb9-81f9-5106f0e331a8",
"tool_call_id":"call_51eahgxphy8jjw9zqgvvihlz",
"artifact":null,
"status":"success"
},
{
"content":"",
"additional_kwargs":{
"reasoning_content":"Now I need to start the research on the DeerFlow repository. First, I should parse the GitHub URL to get owner and repo. The URL is https://github.com/bytedance/deer-flow, so owner is \"bytedance\" and repo is \"deer-flow\". I'll start with Round 1: GitHub API.\n\nLet me first check what scripts are available in the skill directory. I should list the directory to see the structure."
"reasoning_content":"Now I need to parse the GitHub URL to get owner and repo. The URL is https://github.com/bytedance/deer-flow. So owner is \"bytedance\", repo is \"deer-flow\". Let me start by creating a todo list for this multi-step research task."
"content":"Extract repository metadata using GitHub API",
"status":"in_progress"
},
{
"content":"Fetch README and repository information",
"status":"pending"
},
{
"content":"Analyze repository structure and languages",
"status":"pending"
},
{
"content":"Research DeerFlow project overview and purpose",
"status":"pending"
},
{
"content":"Investigate technical architecture and features",
"status":"pending"
},
{
"content":"Analyze community activity and contributors",
"status":"pending"
},
{
"content":"Research timeline and development history",
"status":"pending"
},
{
"content":"Compare with alternatives and assess market position",
"status":"pending"
},
{
"content":"Compile comprehensive research report",
"status":"pending"
}
]
},
"id":"call_b0zngt5ncnuy0bzs245pk4zl",
"type":"tool_call"
}
],
"invalid_tool_calls":[],
"usage_metadata":null
},
{
"content":"Updated todo list to [{'content': 'Extract repository metadata using GitHub API', 'status': 'in_progress'}, {'content': 'Fetch README and repository information', 'status': 'pending'}, {'content': 'Analyze repository structure and languages', 'status': 'pending'}, {'content': 'Research DeerFlow project overview and purpose', 'status': 'pending'}, {'content': 'Investigate technical architecture and features', 'status': 'pending'}, {'content': 'Analyze community activity and contributors', 'status': 'pending'}, {'content': 'Research timeline and development history', 'status': 'pending'}, {'content': 'Compare with alternatives and assess market position', 'status': 'pending'}, {'content': 'Compile comprehensive research report', 'status': 'pending'}]",
"additional_kwargs":{},
"response_metadata":{},
"type":"tool",
"name":"write_todos",
"id":"dde76919-20df-4225-bfcf-a8ec19d2a1d9",
"tool_call_id":"call_b0zngt5ncnuy0bzs245pk4zl",
"artifact":null,
"status":"success"
},
{
"content":"",
"additional_kwargs":{
"reasoning_content":"Now I need to start with Round 1: GitHub API. First extract the owner and repo from the URL: https://github.com/bytedance/deer-flow. Owner: bytedance, repo: deer-flow. Let's run the GitHub API commands."
"content":"{\n \"name\": \"bytedance/deer-flow\",\n \"description\": \"DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.\",\n \"url\": \"https://github.com/bytedance/deer-flow\",\n \"stars\": 19531,\n \"forks\": 2452,\n \"open_issues\": 196,\n \"language\": \"Python\",\n \"license\": \"MIT\",\n \"created_at\": \"2025-05-07T02:50:19Z\",\n \"updated_at\": \"2026-02-01T01:07:38Z\",\n \"pushed_at\": \"2026-01-30T00:47:23Z\",\n \"default_branch\": \"main\",\n \"topics\": [\n \"agent\",\n \"agentic\",\n \"agentic-framework\",\n \"agentic-workflow\",\n \"ai\",\n \"ai-agents\",\n \"bytedance\",\n \"deep-research\",\n \"langchain\",\n \"langgraph\",\n \"langmanus\",\n \"llm\",\n \"multi-agent\",\n \"nodejs\",\n \"podcast\",\n \"python\",\n \"typescript\"\n ],\n \"languages\": {\n \"Python\": 1292574,\n \"TypeScript\": 503143,\n \"CSS\": 15128,\n \"JavaScript\": 7906,\n \"Dockerfile\": 2197,\n \"Makefile\": 1352,\n \"Shell\": 1152,\n \"Batchfile\": 497\n },\n \"contributor_count\": 88\n}",
"additional_kwargs":{},
"response_metadata":{},
"type":"tool",
"name":"bash",
"id":"7ecf6cb9-abb9-44b9-bbef-743fd874c718",
"tool_call_id":"call_14ov252og9xq2jbzk6jw8ws6",
"artifact":null,
"status":"success"
},
{
"content":"",
"additional_kwargs":{
"reasoning_content":"Now I need to update the todo list and continue with the next steps. Let me mark the first task as completed and start the second one."
"content":"# 🦌 DeerFlow\n\n[](https://www.python.org/downloads/)\n[](https://opensource.org/licenses/MIT)\n[](https://deepwiki.com/bytedance/deer-flow)\n\n<!-- DeepWiki badge generated by https://deepwiki.ryoppippi.com/ -->\n\n[English](./README.md) | [简体中文](./README_zh.md) | [日本語](./README_ja.md) | [Deutsch](./README_de.md) | [Español](./README_es.md) | [Русский](./README_ru.md) | [Portuguese](./README_pt.md)\n\n> Originated from Open Source, give back to Open Source.\n\n> [!NOTE]\n> As we're [moving to DeerFlow 2.0](https://github.com/bytedance/deer-flow/issues/824) in February, it's time to wrap up DeerFlow 1.0 on the main branch.\n\n**DeerFlow** (**D**eep **E**xploration and **E**fficient **R**esearch **Flow**) is a community-driven Deep Research framework that builds upon the incredible work of the open source community. Our goal is to combine language models with specialized tools for tasks like web search, crawling, and Python code execution, while giving back to the community that made this possible.\n\nCurrently, DeerFlow has officially entered the [FaaS Application Center of Volcengine](https://console.volcengine.com/vefaas/region:vefaas+cn-beijing/market). Users can experience it online through the [experience link](https://console.volcengine.com/vefaas/region:vefaas+cn-beijing/market/deerflow/?channel=github&source=deerflow) to intuitively feel its powerful functions and convenient operations. At the same time, to meet the deployment needs of different users, DeerFlow supports one-click deployment based on Volcengine. Click the [deployment link](https://console.volcengine.com/vefaas/region:vefaas+cn-beijing/application/create?templateId=683adf9e372daa0008aaed5c&channel=github&source=deerflow) to quickly complete the deployment process and start an efficient research journey.\n\nDeerFlow has newly integrated the intelligent search and crawling toolset independently developed by BytePlus--[InfoQuest (supports free online experience)](https://docs.byteplus.com/en/docs/InfoQuest/What_is_Info_Quest)\n\n<a href=\"https://docs.byteplus.com/en/docs/InfoQuest/What_is_Info_Quest\" target=\"_blank\">\n <img\n src=\"https://sf16-sg.tiktokcdn.com/obj/eden-sg/hubseh7bsbps/20251208-160108.png\" alt=\"infoquest_bannar\"\n/>\n</a>\n\nPleasevisit[ourofficialwebsite](https://deerflow.tech/) for more details.\n\n## Demo\n\n### Video\n\n<https://github.com/user-attachments/assets/f3786598-1f2a-4d07-919e-8b99dfa1de3e>\n\nIn this demo, we showcase how to use DeerFlow to:\n\n- Seamlessly integrate with MCP services\n- Conduct the Deep Research pr
"additional_kwargs":{},
"response_metadata":{},
"type":"tool",
"name":"bash",
"id":"1568942a-e8ff-406e-a96d-0c2fd5da076a",
"tool_call_id":"call_semgkgyfsd7f76uzwzgk3ja9",
"artifact":null,
"status":"success"
},
{
"content":"",
"additional_kwargs":{
"reasoning_content":"Now I need to analyze the repository structure and get more details. Let me get the tree structure."
"reasoning_content":"Now I need to get more information about the repository. Let me get the languages breakdown and then start researching the project. First, I'll complete the current todo and move to research."
"reasoning_content":"Now I need to start the research phase. Let me begin with web searches to understand the project better. First, I'll search for DeerFlow overview and then dive deeper."
"content":"Extract repository metadata using GitHub API",
"status":"completed"
},
{
"content":"Fetch README and repository information",
"status":"completed"
},
{
"content":"Analyze repository structure and languages",
"status":"completed"
},
{
"content":"Research DeerFlow project overview and purpose",
"status":"in_progress"
},
{
"content":"Investigate technical architecture and features",
"status":"pending"
},
{
"content":"Analyze community activity and contributors",
"status":"pending"
},
{
"content":"Research timeline and development history",
"status":"pending"
},
{
"content":"Compare with alternatives and assess market position",
"status":"pending"
},
{
"content":"Compile comprehensive research report",
"status":"pending"
}
]
},
"id":"call_6jo3x6qwzw6sgneczzem8o97",
"type":"tool_call"
}
],
"invalid_tool_calls":[],
"usage_metadata":null
},
{
"content":"Updated todo list to [{'content': 'Extract repository metadata using GitHub API', 'status': 'completed'}, {'content': 'Fetch README and repository information', 'status': 'completed'}, {'content': 'Analyze repository structure and languages', 'status': 'completed'}, {'content': 'Research DeerFlow project overview and purpose', 'status': 'in_progress'}, {'content': 'Investigate technical architecture and features', 'status': 'pending'}, {'content': 'Analyze community activity and contributors', 'status': 'pending'}, {'content': 'Research timeline and development history', 'status': 'pending'}, {'content': 'Compare with alternatives and assess market position', 'status': 'pending'}, {'content': 'Compile comprehensive research report', 'status': 'pending'}]",
"additional_kwargs":{},
"response_metadata":{},
"type":"tool",
"name":"write_todos",
"id":"5b5482a7-3411-4f4e-96c8-662613afa062",
"tool_call_id":"call_6jo3x6qwzw6sgneczzem8o97",
"artifact":null,
"status":"success"
},
{
"content":"",
"additional_kwargs":{
"reasoning_content":"Now I need to research DeerFlow project overview and purpose. Let me start with web searches to understand the project better. First, I'll search for general information about DeerFlow."
"query":"DeerFlow bytedance deep research framework"
},
"id":"call_hgpz1sygmlmflx6f326qc8tp",
"type":"tool_call"
}
],
"invalid_tool_calls":[],
"usage_metadata":null
},
{
"content":"[\n {\n \"title\": \"Create Your Own Deep Research Agent with DeerFlow\",\n \"url\": \"https://thesequence.substack.com/p/the-sequence-engineering-661-create\",\n \"snippet\": \"DeerFlow (Deep Exploration and Efficient Research Flow) is an open-source multi-agent research automation framework developed by ByteDance.\"\n },\n {\n \"title\": \"ByteDance DeerFlow - (Deep Research Agents with a LOCAL LLM!)\",\n \"url\": \"https://www.youtube.com/watch?v=Ui0ovCVDYGs\",\n \"snippet\": \"ByteDance DeerFlow - (Deep Research Agents with a LOCAL LLM!)\\nBijan Bowen\\n40600 subscribers\\n460 likes\\n14105 views\\n13 May 2025\\nTimestamps:\\n\\n00:00 - Intro\\n01:07 - First Look\\n02:53 - Local Test\\n05:00 - Second Test\\n08:55 - Generated Report\\n10:10 - Additional Info\\n11:21 - Local Install Tips\\n15:57 - Closing Thoughts\\n\\nIf you're a business looking to integrate AI visit https://bijanbowen.com to book a consultation.\\n\\nIn this video, we take a first look at the newly released DeerFlow repository from ByteDance. DeerFlow is a feature-rich, open-source deep research assistant that uses a local LLM to generate detailed, source-cited research reports on nearly any topic. Once deployed, it can search the web, pull from credible sources, and produce a well-structured report for the user to review.\\n\\nIn addition to its core research functionality, DeerFlow includes support for MCP server integration, a built-in coder agent that can run and test Python code, and even utilities to convert generated reports into formats like PowerPoint presentations or audio podcasts. The system is highly modular and is designed to be flexible enough for serious research tasks while remaining accessible to run locally.\\n\\nIn this video, we walk through a functional demo, test its capabilities across multiple prompts, and review the output it generates. We also explore a few installation tips, discuss how it integrates with local LLMs, and share some thoughts on how this kind of tool might evolve for research-heavy workflows or automation pipelines.\\n\\nGithub Repo: https://github.com/bytedance/deer-flow\\n98 comments\\n\"\n },\n {\n \"title\": \"Navigating the Landscape of Deep Research Frameworks - Oreate AI\",\n \"url\": \"https://www.oreateai.com/blog/navigating-the-landscape-of-deep-research-frameworks-a-comprehensive-comparison/0dc13e48eb8c756650112842c8d1a184\",\n \"snippet\": \"HomeContentNavigating the Landscape of Deep Research Frameworks: A Comprehensive Comparison. # Navigating the Landscape of Deep Research Frameworks: A Comprehensive Comparison. In recent years, the emergence of deep research frameworks has transformed how we approach complex inquiries. Let's explore six standout frameworks specifically optimized for deep research: DeerFlow by ByteDance, OpenDeepResearch from HuggingFace and LangChain, DeepResearchAgent by SkyworkAI, AutoDeepResearch from HKUDS, and Researcher developed by zhu-minjun. LangChain's OpenDeepResearch is another noteworthy contender that integrates reflection capabilities within its architecture; however, it holds a lower star count at 4.3k compared to others in our lineup. Lastly, Researcher brings forth unique elements such as CycleReviewer aimed at enhancing peer review processes but remains less popular among users given its modest star count of just 0.2k on GitHub. The core principles outlined by OpenAI serve as foundational guidelines across these frameworks: break down complex tasks into manageable parts using a three-step process—Plan -> Execute -> Synthesize—to maximize efficiency while minimizing costs associated with API usage during extensive research endeavors.\"\n },\n {\n \"title\": \"ByteDance DeerFlow: Multi AI Agent framework for Deep ...\",\n \"url\": \"https://medium.com/data-science-in-your-pocket/bytedance-deerflow-multi-ai-agent-framework-for-deep-research-acfbc4d90fbd\",\n \"snippet\": \"Acommunity-drivenmulti-agentresearchframework.Itcombineslanguagemodels,searchengines,webcrawlers,andtext-to
"content":"# The Sequence Engineering #661: Create Your Own Deep Research Agent with DeerFlow\n\n[](https://thesequence.substack.com/)\n\n# [TheSequence](https://thesequence.substack.com/)\n\nSubscribeSign in\n\n# The Sequence Engineering \\#661: Create Your Own Deep Research Agent with DeerFlow\n\n### The frameworks allows the creation of end-to-end research workflows.\n\nJun 11, 2025\n\n∙ Paid\n\n17\n\nShare\n\n[](https://substackcdn.com/image/fetch/$s_!7eiP!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2e659a3c-cf66-40ee-9d86-dd8ff2167881_1536x1024.png) Created Using GPT-4o\n\n[DeerFlow (Deep Exploration and Efficient Research Flow)](https://deerflow.tech/) is an open-source multi-agent research automation framework developed by ByteDance and released under the MIT license in 2025. Designed to address the increasing demand for scalable, auditable, and extensible research workflows, DeerFlow goes beyond the conventional single-agent LLM wrappers. It implements a graph-based orchestration of specialized agents that automate research pipelines end-to-end. Whether the task involves web search, data analysis, report generation, or podcast creation, DeerFlow delivers structured and multimodal outputs with minimal human intervention. This essay explores DeerFlow's architectural underpinnings, key capabilities, and use cases, offering a technical perspective ideal for AI developers, research engineers, and MLOps practitioners.\n\n## **1\\. Architectural Overview**\n\n## This post is for paid subscribers\n\n[Subscribe](https://thesequence.substack.com/subscribe?simple=true&next=https%3A%2F%2Fthesequence.substack.com%2Fp%2Fthe-sequence-engineering-661-create&utm_source=paywall&utm_medium=web&utm_content=165620307)\n\n[Already a paid subscriber? **Sign in**](https://substack.com/sign-in?redirect=%2Fp%2Fthe-sequence-engineering-661-create&for_pub=thesequence&change_user=false)",
"additional_kwargs":{},
"response_metadata":{},
"type":"tool",
"name":"web_fetch",
"id":"15217f79-cc31-4db1-b9be-7d6d7c1020bb",
"tool_call_id":"call_t01ba41is01zr7fksmio9uju",
"artifact":null,
"status":"success"
},
{
"content":"",
"additional_kwargs":{
"reasoning_content":"Now I need to search for more information about DeerFlow's technical details and features. Let me search for more comprehensive information."
"query":"DeerFlow architecture multi-agent LangGraph research framework"
},
"id":"call_bsh4c16e3tbovbf0mfy48xsp",
"type":"tool_call"
}
],
"invalid_tool_calls":[],
"usage_metadata":null
},
{
"content":"[\n {\n \"title\": \"fanqingsong/deer-flow - GitHub\",\n \"url\": \"https://github.com/fanqingsong/deer-flow\",\n \"snippet\": \"DeerFlow implements a modular multi-agent system architecture designed for automated research and code analysis. ... DeerFlow uses LangGraph for its workflow\"\n },\n {\n \"title\": \"DeerFlow: A Modular Multi-Agent Framework Revolutionizing Deep ...\",\n \"url\": \"https://www.linkedin.com/pulse/deerflow-modular-multi-agent-framework-deep-research-ramichetty-pbhxc\",\n \"snippet\": \"# DeerFlow: A Modular Multi-Agent Framework Revolutionizing Deep Research Automation. Released under the MIT license, DeerFlow empowers developers and researchers to automate complex workflows, from academic research to enterprise-grade data analysis. DeerFlow overcomes this limitation through a multi-agent architecture, where each agent specializes in a distinct function, such as task planning, knowledge retrieval, code execution, or report generation. This architecture ensures that DeerFlow can handle diverse research scenarios, such as synthesizing literature reviews, generating data visualizations, or drafting multimodal content. These integrations make DeerFlow a powerful tool for research analysts, data scientists, and technical writers seeking to combine reasoning, execution, and content creation in a single platform. DeerFlow represents a significant advancement in research automation, combining the power of multi-agent coordination, LLM-driven reasoning, and human-in-the-loop collaboration. Its modular architecture, deep tool integrations, and developer-friendly design make it a compelling choice for researchers and organizations seeking to accelerate complex workflows.\"\n },\n {\n \"title\": \"DeerFlow: Multi-Agent AI For Research Automation 2025 - FireXCore\",\n \"url\": \"https://firexcore.com/blog/what-is-deerflow/\",\n \"snippet\": \"What is DeerFlow? DeerFlow is an open-source multi-agent AI framework for automating complex research tasks, built on LangChain and LangGraph.\"\n },\n {\n \"title\": \"DeerFlow: A Game-Changer for Automated Research and Content ...\",\n \"url\": \"https://medium.com/@mingyang.heaven/deerflow-a-game-changer-for-automated-research-and-content-creation-83612f683e7a\",\n \"snippet\": \"# DeerFlow: A Game-Changer for Automated Research and Content Creation. How this open-source multi-agent framework is revolutionizing the way we conduct research and generate content. Picture this: You need a comprehensive research report on quantum computing, cryptocurrency market trends, or the latest AI developments. Instead of spending days gathering information, analyzing data, and writing a structured report, you simply input your research topic and let an intelligent system handle the entire process for you. As someone who’s spent weeks investigating AI research tools, I can confidently say that DeerFlow represents one of the most impressive open-source implementations of a multi-agent research system I’ve encountered. ## What Makes DeerFlow Special? At its core, DeerFlow (Deep Exploration and Efficient Research Flow) is a community-driven framework that combines the power of language models with specialized tools for tasks like web searching, content crawling, and even Python code execution. But what truly sets it apart is its thoughtfully designed multi-agent architecture. > “DeerFlow implements a modular multi-agent system architecture designed for automated research and code analysis.\"\n },\n {\n \"title\": \"ByteDance Open-Sources DeerFlow: A Modular Multi-Agent ... - Reddit\",\n \"url\": \"https://www.reddit.com/r/machinelearningnews/comments/1kj3in1/bytedance_opensources_deerflow_a_modular/\",\n \"snippet\": \"ByteDance has open-sourced DeerFlow, a modular multi-agent framework built on LangChain and LangGraph to streamline complex research workflows.\"\n }\n]",
"content":"#DeerFlow:AGame-ChangerforAutomatedResearchandContentCreation|byheavendai|Medium\n\n[Sitemap](https://medium.com/sitemap/sitemap.xml)\n\n[Open in app](https://play.google.com/store/apps/details?id=com.medium.reader&referrer=utm_source%3DmobileNavBar&source=post_page---top_nav_layout_nav-----------------------------------------)\n\nSign up\n\n[Sign in](https://medium.com/m/signin?operation=login&redirect=https%3A%2F%2Fmedium.com%2F%40mingyang.heaven%2Fdeerflow-a-game-changer-for-automated-research-and-content-creation-83612f683e7a&source=post_page---top_nav_layout_nav-----------------------global_nav------------------)\n\n[Medium Logo](https://medium.com/?source=post_page---top_nav_layout_nav-----------------------------------------)\n\n[Write](https://medium.com/m/signin?operation=register&redirect=https%3A%2F%2Fmedium.com%2Fnew-story&source=---top_nav_layout_nav-----------------------new_post_topnav------------------)\n\n[Search](https://medium.com/search?source=post_page---top_nav_layout_nav-----------------------------------------)\n\nSign up\n\n[Sign in](https://medium.com/m/signin?operation=login&redirect=https%3A%2F%2Fmedium.com%2F%40mingyang.heaven%2Fdeerflow-a-game-changer-for-automated-research-and-content-creation-83612f683e7a&source=post_page---top_nav_layout_nav-----------------------global_nav------------------)\n\n\n\nMember-only story\n\n# DeerFlow: A Game-Changer for Automated Research and Content Creation\n\n[](https://medium.com/@mingyang.heaven?source=post_page---byline--83612f683e7a---------------------------------------)\n\n[heavendai](https://medium.com/@mingyang.heaven?source=post_page---byline--83612f683e7a---------------------------------------)\n\n5 min read\n\n·\n\nMay 10, 2025\n\n--\n\nShare\n\nHow this open-source multi-agent framework is revolutionizing the way we conduct research and generate content\n\nPicture this: You need a comprehensive research report on quantum computing, cryptocurrency market trends, or the latest AI developments. Instead of spending days gathering information, analyzing data, and writing a structured report, you simply input your research topic and let an intelligent system handle the entire process for you.\n\nThis isn’t science fiction — it’s the reality of what [DeerFlow](https://deerflow.tech/) brings to the table. As someone who’s spent weeks investigating AI research tools, I can confidently say that DeerFlow represents one of the most impressive open-source implementations of a multi-agent research system I’ve encountered.\n\nPress enter or click to view image in full size\n\n\n\nDeerFlow’s modular multi-agent architecture\n\n## What Makes DeerFlow Special?\n\nAt its core, DeerFlow (Deep Exploration and Efficient Research Flow) is a community-driven framework that combines the power of language models with specialized tools for tasks like web searching, content crawling, and even Python code execution. But what truly sets it apart is its thoughtfully designed multi-agent architecture.\n\n> “DeerFlow implements a modular multi-agent system architecture designed for automated research and code analysis. The system is built on LangGraph, enabling a flexible state-based workflow where components communicate through a well-defined message passing system.”\n\nRather than relying on a single large language model to handle everything, DeerFlow breaks down the research process into manageable phases, each handled by specialized AI agents:\n\n- **Coordinator**: The entry point that manages the workflow lifecycle, initiating the research process and delegating tasks.\n- **Planner**: The strategic component that analyzes research objectives and creates structured execution plans.\n- **Research Team**: A collection of specialized agents including a Researcher (for web searches and informati
"additional_kwargs":{},
"response_metadata":{},
"type":"tool",
"name":"web_fetch",
"id":"9ee06fbe-aabc-4c8e-b437-19241597eb36",
"tool_call_id":"call_e91r6sqp57hjufu0jh10ejw2",
"artifact":null,
"status":"success"
},
{
"content":"",
"additional_kwargs":{
"reasoning_content":"Now I need to research more about DeerFlow's technical architecture and features. Let me continue with web searches."
"query":"DeerFlow features web search crawling MCP integration"
},
"id":"call_hpyb8pfq0jkykts3xxhw28vx",
"type":"tool_call"
}
],
"invalid_tool_calls":[],
"usage_metadata":null
},
{
"content":"[\n {\n \"title\": \"fanqingsong/deer-flow - GitHub\",\n \"url\": \"https://github.com/fanqingsong/deer-flow\",\n \"snippet\": \"In this demo, we showcase how to use DeerFlow to: Seamlessly integrate with MCP services; Conduct the Deep Research process and produce a comprehensive report\"\n },\n {\n \"title\": \"DeerFlow: Multi-Agent AI For Research Automation 2025 - FireXCore\",\n \"url\": \"https://firexcore.com/blog/what-is-deerflow/\",\n \"snippet\": \"Web Search & Crawling: Pulls real-time data from external sources ... MCP Integration: Connects with ByteDance's internal Model Control\"\n },\n {\n \"title\": \"bytedance/deer-flow: DeerFlow is a community-driven framework for ...\",\n \"url\": \"https://app.daily.dev/posts/bytedance-deer-flow-deerflow-is-a-community-driven-framework-for-deep-research-combining-language--mzmdyvbbj\",\n \"snippet\": \"# bytedance/deer-flow: DeerFlow is a community-driven framework for deep research, combining language models with tools like web search, crawling, and Python execution, while contributing back to the op. DeerFlow is an open-source research framework combining language models with tools like web search, crawling, and Python execution. It integrates with multiple MCP services, supports human-in-the-loop collaboration, and has both console and web UI options. Installation requires Python 3.12+, Node.js, and tools such as uv and. •12m read time• From github.com. Demo📑 Table of ContentsQuick StartSupported Search EnginesFeaturesArchitectureText-to-Speech IntegrationDevelopmentExamplesFAQLicenseAcknowledgmentsStar History.\"\n },\n {\n \"title\": \"DeerFlow\",\n \"url\": \"https://deerflow.tech/\",\n \"snippet\": \"Meet DeerFlow, your personal Deep Research assistant. With powerful tools like search engines, web crawlers, Python and MCP services, it delivers instant\"\n },\n {\n \"title\": \"ByteDance Opens Source Deep Research Framework DeerFlow\",\n \"url\": \"https://news.aibase.com/news/17928\",\n \"snippet\": \"Integration of Multiple Tools: Supports web search, Arxiv academic resource retrieval, crawling, and Python code execution, providing strong\"\n }\n]",
"additional_kwargs":{},
"response_metadata":{},
"type":"tool",
"name":"web_search",
"id":"4415f97a-aeb3-41a5-8144-bccf4f6b5c2c",
"tool_call_id":"call_hpyb8pfq0jkykts3xxhw28vx",
"artifact":null,
"status":"success"
},
{
"content":"",
"additional_kwargs":{
"reasoning_content":"Now I need to understand the technical architecture better and research the community activity. Let me fetch more information."
"content":"# 🦌 DeerFlow\n\n# Deep Researchat Your Fingertipsat Your Fingertips\n\nMeet DeerFlow, your personal Deep Research assistant. With powerful tools like search engines, web crawlers, Python and MCP services, it delivers instant insights, comprehensive reports, and even captivating podcasts.\n\n[Get Started](https://github.com/bytedance/deer-flow)\n\n\\\\* DEER stands for Deep Exploration and Efficient Research.\n\n## Case Studies\n\nSee DeerFlow in action through replays.\n\n[**How tall is Eiffel Tower compared to tallest building?** \\\\\nThe research compares the heights and global significance of the Eiffel Tower and Burj Khalifa, and uses Python code to calculate the multiples.](https://deerflow.tech/chat?replay=eiffel-tower-vs-tallest-building)\n\n[Click to watch replay](https://deerflow.tech/chat?replay=eiffel-tower-vs-tallest-building)\n\n[**What are the top trending repositories on GitHub?** \\\\\nThe research utilized MCP services to identify the most popular GitHub repositories and documented them in detail using search engines.](https://deerflow.tech/chat?replay=github-top-trending-repo)\n\n[Click to watch replay](https://deerflow.tech/chat?replay=github-top-trending-repo)\n\n[**Write an article about Nanjing's traditional dishes** \\\\\nThe study vividly showcases Nanjing's famous dishes through rich content and imagery, uncovering their hidden histories and cultural significance.](https://deerflow.tech/chat?replay=nanjing-traditional-dishes)\n\n[Click to watch replay](https://deerflow.tech/chat?replay=nanjing-traditional-dishes)\n\n[**How to decorate a small rental apartment?** \\\\\nThe study provides readers with practical and straightforward methods for decorating apartments, accompanied by inspiring images.](https://deerflow.tech/chat?replay=rental-apartment-decoration)\n\n[Click to watch replay](https://deerflow.tech/chat?replay=rental-apartment-decoration)\n\n[**Introduce the movie 'Léon: The Professional'** \\\\\nThe research provides a comprehensive introduction to the movie 'Léon: The Professional', including its plot, characters, and themes.](https://deerflow.tech/chat?replay=review-of-the-professional)\n\n[Click to watch replay](https://deerflow.tech/chat?replay=review-of-the-professional)\n\n[**How do you view the takeaway war in China? (in Chinese)** \\\\\nThe research analyzes the intensifying competition between JD and Meituan, highlighting their strategies, technological innovations, and challenges.](https://deerflow.tech/chat?replay=china-food-delivery)\n\n[Click to watch replay](https://deerflow.tech/chat?replay=china-food-delivery)\n\n[**Are ultra-processed foods linked to health?** \\\\\nThe research examines the health risks of rising ultra-processed food consumption, urging more research on long-term effects and individual differences.](https://deerflow.tech/chat?replay=ultra-processed-foods)\n\n[Click to watch replay](https://deerflow.tech/chat?replay=ultra-processed-foods)\n\n[**Write an article on \"Would you insure your AI twin?\"**\\\\\nTheresearchexplorestheconceptofinsuringAItwins,highlightingtheirbenefits,risks,ethicalconsiderations,andtheevolvingregulatory.](https://deerflow.tech/chat?replay=ai-twin-insurance)\n\n[Click to watch replay](https://deerflow.tech/chat?replay=ai-twin-insurance)\n\n## Multi-Agent Architecture\n\nExperience the agent teamwork with our Supervisor + Handoffs design pattern.\n\nStart\n\nCoordinator\n\nPlanner\n\nReporter\n\nHuman Feedback\n\nResearch Team\n\nResearcher\n\nCoder\n\nEnd\n\nPress enter or space to select a node.You can then use the arrow keys to move the node around. Press delete to remove it and escape to cancel.\n\nPress enter or space to select an edge. You can then press delete to remove it or escape to cancel.\n\n## Core Features\n\nFind out what makes DeerFlow effective.\n\n[**Dive Deeper and Reach Wider** \\\\\nUnlock deeper insights with advanced tools. Our powerful search + crawling and Python tools gathers comprehensive data, delivering in-depth reports to enhance your study.](https://githu
"additional_kwargs":{},
"response_metadata":{},
"type":"tool",
"name":"web_fetch",
"id":"bb556bbf-840f-4ca6-937d-0a81915ae961",
"tool_call_id":"call_13utybv555uqnm2ijodwli3d",
"artifact":null,
"status":"success"
},
{
"content":"",
"additional_kwargs":{
"reasoning_content":"Now I need to investigate the technical architecture and features more deeply. Let me also check the community activity and contributors."
"reasoning_content":"Now I need to check issues and PRs to understand community activity and development timeline. Let me also search for more information about DeerFlow 2.0 and alternatives."
"query":"DeerFlow alternatives deep research frameworks 2025 comparison"
},
"id":"call_uz1r6yqbc0s9hlm5fleds6cj",
"type":"tool_call"
}
],
"invalid_tool_calls":[],
"usage_metadata":null
},
{
"content":"[\n {\n \"title\": \"[Up-to-date] Awesome Agentic Deep Research Resources - GitHub\",\n \"url\": \"https://github.com/DavidZWZ/Awesome-Deep-Research\",\n \"snippet\": \"DeerFlow: ByteDance's research and analysis solution (May 9, 2025); Deep Research: Alibaba's Qwen-powered research assistant (May 14, 2025); Kimi\"\n },\n {\n \"title\": \"A Live Benchmark for User-Centric Deep Research in the Wild - arXiv\",\n \"url\": \"https://arxiv.org/html/2510.14240v1\",\n \"snippet\": \"We conduct a comprehensive evaluation of 17 state-of-the-art open-sourced and proprietary agentic systems, which can usually be grouped into three categories: (1) Single-agent systems with web search capabilities, including GPT-5 (OpenAI, 2025a) , GPT-4.1 (OpenAI, 2024), GPT-5-mini (OpenAI, 2025b), Gemini 2.5 Pro (DeepMind, 2025b), Gemini 2.5 Flash (DeepMind, 2025a), Claude 4 Sonnet (Anthropic, 2025a), Claude 4.1 Opus (Anthropic, 2025b), Perplexity Sonar Reasoning (Perplexity, 2025a), and Perplexity Sonar Reasoning Pro (Perplexity, 2025b); (2) Single-agent deep research systems, which feature extended reasoning depth and longer thinking time, including OpenAI o3 Deep Research (OpenAI, 2025c), OpenAI o4-mini Deep Research (OpenAI, 2025d), Perplexity Sonar Deep Research (AI, 2025b), Grok-4 Deep Research (Expert) (xAI, 2025b), and Gemini Deep Research (DeepMind, 2025c); (3) Multi-agent deep research systems, which coordinate a team of specialized agents to decompose complex queries. With these changes, Deerflow+ completed the full evaluation suite without token-limit failures and produced higher-quality reports: better retention of retrieved evidence, improved formatting and factual consistency, and more reliable performance on presentation checks tied to citation management, particularly P4 (Citation Completeness) and P9 (Format Consistency) in Figure 22 Deerflow (vanilla) ‣ Appendix C Deerflow+ ‣ LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild\\\").\"\n },\n {\n \"title\": \"Comparative Analysis of Deep Research Tools\",\n \"url\": \"https://trilogyai.substack.com/p/comparative-analysis-of-deep-research\",\n \"snippet\": \"Both tech giants and open-source communities have introduced solutions in late 2024 and early 2025 – notably all branding this feature as **“Deep Research.”** This analysis compares **proprietary solutions** (Google’s *Gemini Deep Research*, OpenAI’s *ChatGPT Deep Research*, *Perplexity AI Deep Research*, and xAI’s *Grok 3 DeepSearch*) against prominent **open-source projects** (e.g. OpenAI’s Deep Research is similar in concept: it is an **agentic mode in ChatGPT** that autonomously searches the web, analyzes data (including the ability to use tools like Python code if needed), and returns a detailed report. Most of the proprietary tools focus on textual analysis of web content, but OpenAI and some open-source ones extend to analyzing **local documents** provided by the user, enabling custom data to be included in the research. The development of deep research tools in this short span has **set new standards for AI-assisted research**: it’s no longer impressive for an AI to just answer questions – it should show its work, cite sources, handle multiple modalities, possibly use external tools, and integrate into workflows.\"\n },\n {\n \"title\": \"DeerFlow vs. OpenAI deep research Comparison - SourceForge\",\n \"url\": \"https://sourceforge.net/software/compare/DeerFlow-vs-OpenAI-deep-research/\",\n \"snippet\": \"Compare DeerFlow vs. OpenAI deep research using this comparison chart. Compare price, features, and reviews of the software side-by-side to make the best\"\n },\n {\n \"title\": \"Navigating the Landscape of Deep Research Frameworks - Oreate AI\",\n \"url\": \"https://www.oreateai.com/blog/navigating-the-landscape-of-deep-research-frameworks/c6ebff6d21ddce5a1c238b680171fe77\",\n \"snippet\": \"DeerFlowstandsoutwithitscompletewebuserinterface(WEBUI)andintegratedcodercapabilitiesforar
"additional_kwargs":{},
"response_metadata":{},
"type":"tool",
"name":"web_search",
"id":"5037c63c-1cee-4181-acb5-641ffeca6cfa",
"tool_call_id":"call_uz1r6yqbc0s9hlm5fleds6cj",
"artifact":null,
"status":"success"
},
{
"content":"",
"additional_kwargs":{
"reasoning_content":"Now I need to check the report template to understand the structure I should follow. Let me read the template file."
"reasoning_content":"Now I need to gather more specific information about DeerFlow's technical architecture, features, and market position. Let me search for more detailed technical information."
"content":"[\n {\n \"title\": \"DeerFlow\",\n \"url\": \"https://deerflow.tech/\",\n \"snippet\": \"Multi-Agent Architecture. Experience the agent teamwork with our Supervisor + ... Build with confidence using the LangChain and LangGraph frameworks.\"\n },\n {\n \"title\": \"Create Your Own Deep Research Agent with DeerFlow\",\n \"url\": \"https://thesequence.substack.com/p/the-sequence-engineering-661-create\",\n \"snippet\": \"At the heart of DeerFlow lies a modular agent orchestration architecture powered by LangGraph and LangChain. This structure enables\"\n },\n {\n \"title\": \"DeerFlow: A Modular Multi-Agent Framework Revolutionizing Deep ...\",\n \"url\": \"https://www.linkedin.com/pulse/deerflow-modular-multi-agent-framework-deep-research-ramichetty-pbhxc\",\n \"snippet\": \"# DeerFlow: A Modular Multi-Agent Framework Revolutionizing Deep Research Automation. Released under the MIT license, DeerFlow empowers developers and researchers to automate complex workflows, from academic research to enterprise-grade data analysis. DeerFlow overcomes this limitation through a multi-agent architecture, where each agent specializes in a distinct function, such as task planning, knowledge retrieval, code execution, or report generation. This architecture ensures that DeerFlow can handle diverse research scenarios, such as synthesizing literature reviews, generating data visualizations, or drafting multimodal content. These integrations make DeerFlow a powerful tool for research analysts, data scientists, and technical writers seeking to combine reasoning, execution, and content creation in a single platform. DeerFlow represents a significant advancement in research automation, combining the power of multi-agent coordination, LLM-driven reasoning, and human-in-the-loop collaboration. Its modular architecture, deep tool integrations, and developer-friendly design make it a compelling choice for researchers and organizations seeking to accelerate complex workflows.\"\n },\n {\n \"title\": \"ByteDance DeerFlow: Multi AI Agent framework for Deep Research\",\n \"url\": \"https://medium.com/data-science-in-your-pocket/bytedance-deerflow-multi-ai-agent-framework-for-deep-research-acfbc4d90fbd\",\n \"snippet\": \"A community-driven multi-agent research framework. It combines language models, search engines, web crawlers, and text-to-speech features to automate deep\"\n },\n {\n \"title\": \"Build multi-agent systems with LangGraph and Amazon Bedrock\",\n \"url\": \"https://aws.amazon.com/blogs/machine-learning/build-multi-agent-systems-with-langgraph-and-amazon-bedrock/\",\n \"snippet\": \"The framework provides fine-grained control over both the flow and state of your agent applications. LangGraph models agent workflows as graphs.\"\n }\n]",
"content":"<citations>\n{\"id\": \"cite-1\", \"title\": \"DeerFlow GitHub Repository\", \"url\": \"https://github.com/bytedance/deer-flow\", \"snippet\": \"Community-driven Deep Research framework combining language models with tools like web search, crawling, and Python execution\"}\n{\"id\": \"cite-2\", \"title\": \"Create Your Own Deep Research Agent with DeerFlow\", \"url\": \"https://thesequence.substack.com/p/the-sequence-engineering-661-create\", \"snippet\": \"Open-source multi-agent research automation framework developed by ByteDance\"}\n{\"id\": \"cite-3\", \"title\": \"DeerFlow: A Game-Changer for Automated Research and Content Creation\", \"url\": \"https://medium.com/@mingyang.heaven/deerflow-a-game-changer-for-automated-research-and-content-creation-83612f683e7a\", \"snippet\": \"Open-source multi-agent framework revolutionizing research and content creation\"}\n{\"id\": \"cite-4\", \"title\": \"ByteDance DeerFlow - (Deep Research Agents with a LOCAL LLM!)\", \"url\": \"https://www.youtube.com/watch?v=Ui0ovCVDYGs\", \"snippet\": \"Video demonstration of DeerFlow capabilities and local LLM integration\"}\n{\"id\": \"cite-5\", \"title\": \"DeerFlow Official Website\", \"url\": \"https://deerflow.tech/\", \"snippet\": \"Official platform showcasing DeerFlow features, case studies, and architecture\"}\n{\"id\": \"cite-6\", \"title\": \"Navigating the Landscape of Deep Research Frameworks\", \"url\": \"https://www.oreateai.com/blog/navigating-the-landscape-of-deep-research-frameworks-a-comprehensive-comparison/0dc13e48eb8c756650112842c8d1a184\", \"snippet\": \"Comparative analysis of deep research frameworks including DeerFlow\"}\n{\"id\": \"cite-7\", \"title\": \"DeerFlow: Multi-Agent AI For Research Automation 2025\", \"url\": \"https://firexcore.com/blog/what-is-deerflow/\", \"snippet\": \"Overview of DeerFlow features and capabilities for research automation\"}\n</citations>\n#DeerFlowDeepResearchReport\n\n-**ResearchDate:**2026-02-01\n-**Timestamp:**2026-02-01,Sunday\n-**ConfidenceLevel:**High(90%+)\n-**Subject:**ByteDance'sOpen-SourceMulti-AgentDeepResearchFramework\n\n---\n\n##RepositoryInformation\n\n-**Name:**bytedance/deer-flow\n-**Description:**DeerFlowisacommunity-drivenDeepResearchframework,combininglanguagemodelswithtoolslikewebsearch,crawling,andPythonexecution,whilecontributingbacktotheopen-sourcecommunity[DeerFlowGitHubRepository](https://github.com/bytedance/deer-flow)\n- **URL:** https://github.com/bytedance/deer-flow\n- **Stars:** 19,531\n- **Forks:** 2,452\n- **Open Issues:** 196\n- **Language(s):** Python (1,292,574 bytes), TypeScript (503,143 bytes), CSS (15,128 bytes), JavaScript (7,906 bytes), Dockerfile (2,197 bytes), Makefile (1,352 bytes), Shell (1,152 bytes), Batchfile (497 bytes)\n- **License:** MIT\n- **Created At:** 2025-05-07T02:50:19Z\n- **Updated At:** 2026-02-01T01:07:38Z\n- **Pushed At:** 2026-01-30T00:47:23Z\n- **Topics:** agent, agentic, agentic-framework, agentic-workflow, ai, ai-agents, bytedance, deep-research, langchain, langgraph, langmanus, llm, multi-agent, nodejs, podcast, python, typescript\n\n---\n\n## Executive Summary\n\nDeerFlow (Deep Exploration and Efficient Research Flow) is an open-source multi-agent research automation framework developed by ByteDance and released under the MIT license in May 2025 [Create Your Own Deep Research Agent with DeerFlow](https://thesequence.substack.com/p/the-sequence-engineering-661-create). The framework implements a graph-based orchestration of specialized agents that automate research pipelines end-to-end, combining language models with tools like web search engines, crawlers, and Python execution. With 19,531 stars and 2,452 forks on GitHub, DeerFlow has established itself as a significant player in the deep research automation space, offering both console and web UI options with support for local LLM deployment and extensive tool integrations [DeerFlow: A Game-Changer for Automated Research and Content Creation](https://medium.com/@mingyang.heaven/deer
},
"id":"call_l2m5ymrn2iwc1k3wnnirveue",
"type":"tool_call"
}
],
"invalid_tool_calls":[],
"usage_metadata":null
},
{
"content":"OK",
"additional_kwargs":{},
"response_metadata":{},
"type":"tool",
"name":"write_file",
"id":"a6d352e9-ae98-4c3c-9d9a-5bccbff4d732",
"tool_call_id":"call_l2m5ymrn2iwc1k3wnnirveue",
"artifact":null,
"status":"success"
},
{
"content":"",
"additional_kwargs":{
"reasoning_content":"Now I need to copy the report to the outputs directory and present it to the user. Let me first check if the outputs directory exists, then copy the file there."
"content":"The complete research report has been saved to `/mnt/user-data/outputs/research_deerflow_20260201.md` and is now available for your review. The report includes detailed analysis of the technical architecture, development timeline, community metrics, comparative analysis with alternatives, and confidence assessments for all claims.",
"text":"Great job! Then make a cool webpage according to your report."
}
],
"additional_kwargs":{},
"response_metadata":{},
"type":"human",
"name":null,
"id":"6f621f69-d5b7-40c4-b812-3de65e029821"
},
{
"content":"",
"additional_kwargs":{
"reasoning_content":"The user wants me to create a cool webpage based on the DeerFlow research report I just generated. This is a perfect use case for the frontend-design skill. Let me load that skill first to understand the workflow and best practices."
"content":"---\nname: frontend-design\ndescription: Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.\nlicense: Complete terms in LICENSE.txt\n---\n\nThis skill guides creation of distinctive, production-grade frontend interfaces that avoid generic \"AI slop\"aesthetics.Implementrealworkingcodewithexceptionalattentiontoaestheticdetailsandcreativechoices.\n\nTheuserprovidesfrontendrequirements:acomponent,page,application,orinterfacetobuild.Theymayincludecontextaboutthepurpose,audience,ortechnicalconstraints.\n\n##OutputRequirements\n\n**MANDATORY**:TheentryHTMLfileMUSTbenamed`index.html`.Thisisastrictrequirementforallgeneratedfrontendprojectstoensurecompatibilitywithstandardwebhostinganddeploymentworkflows.\n\n##DesignThinking\n\nBeforecoding,understandthecontextandcommittoaBOLDaestheticdirection:\n-**Purpose**:Whatproblemdoesthisinterfacesolve?Whousesit?\n-**Tone**:Pickanextreme:brutallyminimal,maximalistchaos,retro-futuristic,organic/natural,luxury/refined,playful/toy-like,editorial/magazine,brutalist/raw,artdeco/geometric,soft/pastel,industrial/utilitarian,etc.Therearesomanyflavorstochoosefrom.Usetheseforinspirationbutdesignonethatistruetotheaestheticdirection.\n-**Constraints**:Technicalrequirements(framework,performance,accessibility).\n-**Differentiation**:WhatmakesthisUNFORGETTABLE?What'stheonethingsomeonewillremember?\n\n**CRITICAL**:Chooseaclearconceptualdirectionandexecuteitwithprecision.Boldmaximalismandrefinedminimalismbothwork-thekeyisintentionality,notintensity.\n\nThenimplementworkingcode(HTML/CSS/JS,React,Vue,etc.)thatis:\n-Production-gradeandfunctional\n-Visuallystrikingandmemorable\n-Cohesivewithaclearaestheticpoint-of-view\n-Meticulouslyrefinedineverydetail\n\n##FrontendAestheticsGuidelines\n\nFocuson:\n-**Typography**:Choosefontsthatarebeautiful,unique,andinteresting.AvoidgenericfontslikeArialandInter;optinsteadfordistinctivechoicesthatelevatethefrontend'saesthetics;unexpected,characterfulfontchoices.Pairadistinctivedisplayfontwitharefinedbodyfont.\n-**Color&Theme**:Committoacohesiveaesthetic.UseCSSvariablesforconsistency.Dominantcolorswithsharpaccentsoutperformtimid,evenly-distributedpalettes.\n-**Motion**:Useanimationsforeffectsandmicro-interactions.PrioritizeCSS-onlysolutionsforHTML.UseMotionlibraryforReactwhenavailable.Focusonhigh-impactmoments:onewell-orchestratedpageloadwithstaggeredreveals(animation-delay)createsmoredelightthanscatteredmicro-interactions.Usescroll-triggeringandhoverstatesthatsurprise.\n-**SpatialComposition**:Unexpectedlayouts.Asymmetry.Overlap.Diagonalflow.Grid-breakingelements.GenerousnegativespaceORcontrolleddensity.\n-**Backgrounds&VisualDetails**:Createatmosphereanddepthratherthandefaultingtosolidcolors.Addcontextualeffectsandtexturesthatmatchtheoverallaesthetic.Applycreativeformslikegradientmeshes,noisetextures,geometricpatterns,layeredtransparencies,dramaticshadows,decorativeborders,customcursors,andgrainoverlays.\n\nNEVERusegenericAI-generatedaestheticslikeoverusedfontfamilies(Inter,Roboto,Arial,systemfonts),clichedcolorschemes(particularlypurplegradientsonwhitebackgrounds),predictablelayoutsandcomponentpatterns,andcookie-cutterdesignthatlackscontext-specificcharacter.\n\nInterpretcreativelyandmakeunexpectedchoicesthatfeelgenuinelydesignedforthecontext.Nodesignshouldbethesame.Varybetweenlightanddar
"additional_kwargs":{},
"response_metadata":{},
"type":"tool",
"name":"read_file",
"id":"f75ca681-b1e7-425a-b34b-835c4fac153b",
"tool_call_id":"read_file:31",
"artifact":null,
"status":"success"
},
{
"content":"I'll create a stunning, distinctive webpage based on the DeerFlow research report. Let me design something bold and memorable that captures the essence of this multi-agent research framework.",
"additional_kwargs":{
"reasoning_content":"Now I have the guidelines for creating the webpage. I need to create a cool, distinctive webpage based on the DeerFlow research report. Let me think about the design direction:\n\n1. **Purpose**: Showcase the DeerFlow research report in an engaging, interactive way\n2. **Tone**: Tech-forward, modern, research-focused, with a hint of futuristic/agentic theme (since DeerFlow is about multi-agent AI)\n3. **Differentiation**: I should create something that feels like a premium research presentation - maybe with:\n - A dark theme with accent colors\n - Interactive elements for the timeline\n - Animated metrics counters\n - A sophisticated multi-agent visual representation\n - Smooth scroll-triggered animations\n\nLet me create a bold, distinctive design. I'll go with:\n- **Theme**: Dark, sophisticated tech aesthetic with electric blue/teal accents\n- **Typography**: Distinctive fonts - maybe something like \"Space Grotesk\" for headers (actually, the skill says to avoid common choices like Space Grotesk), so let me pick something more unique. Maybe \"DM Serif Display\" for headlines and \"JetBrains Mono\" for code/metrics.\n- **Visual Style**: Multi-layered with subtle gradients, glassmorphism effects, and dynamic data visualizations\n- **Animations**: Scroll-triggered reveals, staggered content entry, animated numbers for metrics\n\nLet me create this as a single HTML file with embedded CSS and JavaScript."
"content":"I've created a **stylish, production-grade webpage** based on the DeerFlow research report. Here's what makes it stand out:\n\n## Design Highlights\n\n**Visual Aesthetic**\n- **Dark tech theme** with electric teal/cyan accents that evoke an agentic, futuristic feel\n- **Dynamic background** with floating glow effects and a subtle grid pattern\n- **Sophisticated typography** using Playfair Display for headlines (elegant, editorial feel) and JetBrains Mono for technical elements\n\n**Interactive Features**\n- **Animated counters** that count up when scrolling into view (19,531 stars, 2,452 forks, 88 contributors)\n- **Scroll-triggered fade-in animations** for smooth content reveals\n- **Hover effects** on cards, navigation links, and architecture nodes\n- **Smooth scroll navigation** between sections\n\n**Content Sections**\n1. **Hero** - Dramatic intro with live metrics\n2. **Executive Summary** - Key insights in a glassmorphic card\n3. **Development Timeline** - Visual timeline with phases\n4. **Multi-Agent Architecture** - Interactive flow diagram showing Coordinator → Planner → Research Team → Reporter\n5. **Feature Grid** - 6 key capabilities with icons\n6. **Competitive Comparison** - Side-by-side feature table\n7. **Strengths & Considerations** - Balanced SWOT analysis\n8. **Conclusion** - Final assessment\n\n**Responsive Design**\n- Fully responsive layout that adapts from desktop to mobile\n- Flexible grid systems and overflow handling for tables\n- Touch-friendly navigation and interactions\n\nThe page includes the \"Created By Deerflow\" badge in the bottom-right corner that links to [deerflow.tech](https://deerflow.tech). You can view the rendered page by opening the file!",
"additional_kwargs":{
"reasoning_content":"The webpage has been created and presented. Let me provide a summary of what was built."
