{"id":49038854,"url":"https://github.com/AgentTeam-TaichuAI/ScienceClaw","last_synced_at":"2026-05-05T18:01:45.653Z","repository":{"id":344827552,"uuid":"1180557903","full_name":"AgentTeam-TaichuAI/ScienceClaw","owner":"AgentTeam-TaichuAI","description":"ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.","archived":false,"fork":false,"pushed_at":"2026-04-23T03:05:54.000Z","size":2235,"stargazers_count":518,"open_issues_count":9,"forks_count":53,"subscribers_count":23,"default_branch":"master","last_synced_at":"2026-04-23T04:24:23.623Z","etag":null,"topics":["ai-agent","bioinformatics","data-analysis","docker","drug-discovery","fastapi","feishu","langchain","langgraph","llm","mcp","multi-agent","pubmed","research-assistant","sandbox","scientific-research","self-hosted","tool-use","vue","wechat"],"latest_commit_sha":null,"homepage":"https://scienceclaw.taichuai.cn/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AgentTeam-TaichuAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-13T06:52:33.000Z","updated_at":"2026-04-23T03:05:58.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/AgentTeam-TaichuAI/ScienceClaw","commit_stats":null,"previous_names":["agentteam-taichuai/scienceclaw"],"tags_count":4,"template":false,"template_full_name":null,"purl":"pkg:github/AgentTeam-TaichuAI/ScienceClaw","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgentTeam-TaichuAI%2FScienceClaw","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgentTeam-TaichuAI%2FScienceClaw/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgentTeam-TaichuAI%2FScienceClaw/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgentTeam-TaichuAI%2FScienceClaw/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AgentTeam-TaichuAI","download_url":"https://codeload.github.com/AgentTeam-TaichuAI/ScienceClaw/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgentTeam-TaichuAI%2FScienceClaw/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32661193,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-05T11:29:49.557Z","status":"ssl_error","status_checked_at":"2026-05-05T11:29:48.587Z","response_time":54,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agent","bioinformatics","data-analysis","docker","drug-discovery","fastapi","feishu","langchain","langgraph","llm","mcp","multi-agent","pubmed","research-assistant","sandbox","scientific-research","self-hosted","tool-use","vue","wechat"],"created_at":"2026-04-19T14:00:38.745Z","updated_at":"2026-05-05T18:01:45.646Z","avatar_url":"https://github.com/AgentTeam-TaichuAI.png","language":"Python","funding_links":[],"categories":["生物医学研究"],"sub_categories":["其他国际设备（国内部分可用）"],"readme":"\u003cdiv align=\"center\"\u003e\n\n\u003ch1\u003e\u003cimg src=\"images/logo.png\" alt=\"ScienceClaw\" width=\"36\" style=\"vertical-align: middle;\" /\u003e\u0026nbsp;ScienceClaw\u003c/h1\u003e\n\n**[English](README.md)** | **[中文](README_zh.md)**\n\n\u003c/div\u003e\n\nScienceClaw is a personal research assistant built with [LangChain DeepAgents](https://github.com/langchain-ai/deepagents) and [AIO Sandbox](https://github.com/agent-infra/sandbox) infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.\n\n\u003cdiv align=\"center\"\u003e\n\n*1,900+ built-in scientific tools · Multi-format content generation · Fully local \u0026 privacy-first*\n\n[![Tools](https://img.shields.io/badge/Tools-e74c3c.svg)](./Tools) [![Skills](https://img.shields.io/badge/Skills-f39c12.svg)](./Skills) [![Frontend](https://img.shields.io/badge/Frontend-2ecc71.svg)](./ScienceClaw/frontend) [![Backend](https://img.shields.io/badge/Backend-3498db.svg)](./ScienceClaw/backend) [![Scheduler](https://img.shields.io/badge/Scheduler-9b59b6.svg)](./ScienceClaw/task-service) [![Sandbox](https://img.shields.io/badge/Sandbox-1abc9c.svg)](./ScienceClaw/sandbox) [![License](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)\n\n---\n\n\u003cvideo src=\"https://github.com/user-attachments/assets/2680110c-e9f6-4007-9c56-b923c35f9992\" controls width=\"800\" autoplay muted loop\u003e\u003c/video\u003e\n\n[Why ScienceClaw](#why-scienceclaw) · [Architecture](#architecture) · [News](#news) · [Quick Start](#quick-start) · [Demo](#demo) · [Free API Credits](#free-api-credits) · [Tools \u0026 Skills](#tools-skills) · [Features](#practical-features) · [Project Structure](#project-structure) · [Commands](#commands) · [Community](#community) · [Acknowledgements](#acknowledgements)\n\n\u003c/div\u003e\n\n---\n\n\u003ca id=\"why-scienceclaw\"\u003e\u003c/a\u003e\n\n## ✨ Why ScienceClaw\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd width=\"37%\" valign=\"top\"\u003e\n\n### 🔒 Security First\n\nScienceClaw runs entirely inside **Docker containers**. The agent cannot access your host system, personal files, or environment variables. All code execution happens in an **isolated sandbox**, and generated data stays in a local `./workspace` directory — nothing is uploaded to external servers. Deploy with confidence on your own machine.\n\n\u003c/td\u003e\n\u003ctd width=\"32%\" valign=\"top\"\u003e\n\n### 👁️ Full Transparency\n\nEvery step of the agent's workflow is **visible and traceable** — from web search and data crawling, to reasoning and tool invocation, to final report generation. You always know where results come from, what actions were taken, and how conclusions were reached. Inspect any step at any time.\n\n\u003c/td\u003e\n\u003ctd width=\"31%\" valign=\"top\"\u003e\n\n### 🚀 Ready Out of the Box\n\nNo tedious configuration needed. ScienceClaw ships with curated tools and skill packages — launch the entire environment with **a single command**. Whether you're a researcher, developer, or student, you can get started immediately. Focus on real tasks, not setup.\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n---\n\n\u003ca id=\"architecture\"\u003e\u003c/a\u003e\n\n## 🏗️ Architecture\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"images/structure.png\" alt=\"Architecture\" width=\"100%\" /\u003e\n\u003c/div\u003e\n\n---\n\n\u003ca id=\"news\"\u003e\u003c/a\u003e\n\n## 📢 News\n\n- **[2026-03-13]** ScienceClaw v0.0.1 is officially released! Visit our website: [scienceclaw.taichuai.cn](https://scienceclaw.taichuai.cn/)\n\n---\n\n\u003ca id=\"quick-start\"\u003e\u003c/a\u003e\n\n## 📦 Quick Start\n\n###  Windows Users — Desktop App (One-Click Install)\n\nNo Docker required, no command-line needed. Download the desktop installer and get started instantly.\n\n**1. Download the installer**\n\n👉 [ScienceClaw Desktop v0.0.4 (.tar.gz)](https://gitee.com/zidongtaichu_beijing/scienceclaw/releases/download/v0.0.4/ScienceClaw-Desktop-Setup-0.0.4.tar.gz)\n\n**2. Extract and install**\n\nAfter downloading, extract the archive and run the installer. Follow the setup wizard to complete installation.\n\n**3. Launch**\n\nOnce installed, double-click the desktop shortcut to start ScienceClaw — ready to use out of the box.\n\n---\n\n###  macOS / Linux Users — Docker Deployment\n\n\u003e 📖 For a detailed step-by-step deployment guide, see [**Deployment Guide (中文)**](docs/deployment-guide-zh.md).\n\n#### Prerequisites\n\n- [Docker](https://docs.docker.com/get-docker/) \u0026 [Docker Compose](https://docs.docker.com/compose/install/) (Docker Desktop includes Compose)\n- Recommended system RAM ≥ 8 GB\n\n#### Install \u0026 Launch\n\n**1. Get the code**\n\n- **Fresh install:**\n\n```bash\ngit clone https://github.com/AgentTeam-TaichuAI/ScienceClaw.git\ncd ScienceClaw\n```\n\n- **Upgrade an existing installation:**\n\n```bash\ncd ScienceClaw\ngit pull\n```\n\n**2. Launch — pull pre-built images**\n\n```bash\ndocker compose -f docker-compose-release.yml up -d --pull always\n```\n\n\u003e Pulls pre-built images directly — no local compilation needed. Ready in a few minutes.\n\n\n**3. Open in browser**\n\n```\nhttp://localhost:5173\n```\n\n**4. Login**\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd width=\"60%\"\u003e\n\u003cimg src=\"images/login.jpeg\" alt=\"Login Page\" width=\"100%\" /\u003e\n\u003c/td\u003e\n\u003ctd width=\"40%\" valign=\"middle\" style=\"padding-left: 24px;\"\u003e\n\u003cbr/\u003e\u003cbr/\u003e\n\u003cp\u003e\u003cstrong\u003eDefault admin credentials:\u003c/strong\u003e\u003c/p\u003e\n\u003ctable\u003e\n\u003ctr\u003e\u003ctd\u003e\u003cstrong\u003eField\u003c/strong\u003e\u003c/td\u003e\u003ctd\u003e\u003cstrong\u003eValue\u003c/strong\u003e\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eUsername\u003c/td\u003e\u003ctd\u003e\u003ccode\u003eadmin\u003c/code\u003e\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003ePassword\u003c/td\u003e\u003ctd\u003e\u003ccode\u003eadmin123\u003c/code\u003e\u003c/td\u003e\u003c/tr\u003e\n\u003c/table\u003e\n\u003cblockquote\u003e⚠️ Please change the default password after your first login.\u003c/blockquote\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n---\n\n### 🛠️ Developers — Build from Source\n\n```bash\ndocker compose up -d --build\n```\n\n\u003e Builds all images from source code. Ideal for developers who need to modify the code. The first build downloads dependencies and may take longer.\n\n---\n\n\u003ca id=\"demo\"\u003e\u003c/a\u003e\n\n## 🎬 Demo\n\n\u003cvideo src=\"https://github.com/user-attachments/assets/9cf07107-4820-4a0e-af3d-e95a17417156\" controls width=\"800\" autoplay muted loop\u003e\u003c/video\u003e\n\n---\n\n\u003ca id=\"free-api-credits\"\u003e\u003c/a\u003e\n\n## 🎁 Free LLM API Credits for Early Users\n\nTo lower the barrier for new users, a limited batch of LLM API resources:\n\n| Offer | Details |\n|---|---|\n| SCNet (National Supercomputing Internet) | **10M free tokens** ([Claim here](https://www.scnet.cn/ui/mall/en)) |\n| Zidong Taichu Cloud | **10M free tokens** ([Claim here](https://gateway.taichuai.cn/modelhub/apply)) |\n\n\u003e Limited availability — first come, first served. We will continue to secure more compute resources for the community.\n\n---\n\n\u003ca id=\"tools-skills\"\u003e\u003c/a\u003e\n\n## 🔧 Tools \u0026 Skills System\n\n### 🧪 1,900+ Built-in Scientific Tools\n\nScienceClaw integrates **ToolUniverse**, a unified ecosystem of 1,900+ scientific tools spanning **multiple disciplines**:\n\n| Domain | Capabilities |\n|---|---|\n| 💊 **Drug Discovery \u0026 Biomedicine** | Target identification (OpenTargets), ADMET prediction, drug safety (FAERS), protein analysis (UniProt, PDB, AlphaFold), genomics (GWAS, GTEx), clinical trials |\n| 🔭 **Astronomy \u0026 Space Science** | SIMBAD astronomical objects, SDSS sky survey, NASA exoplanet archive, JPL Horizons ephemeris, NASA DONKI solar events, small body database |\n| 🌍 **Earth \u0026 Environmental Science** | USGS earthquakes \u0026 hydrology, ERDDAP ocean/climate data, SoilGrids, air quality (WAQI), OpenMeteo weather/climate, marine regions |\n| ⚗️ **Chemistry \u0026 Materials** | COD crystal structures, molecular property prediction, SMILES-based analysis, compound similarity, chemical computation |\n| 🌱 **Biodiversity \u0026 Ecology** | GBIF species records, OBIS marine biodiversity, POWO plant taxonomy, WoRMS marine species, eBird taxonomy, paleobiology database |\n| 📊 **Social Science \u0026 Statistics** | World Bank indicators, Eurostat, US Census population data, Wikidata knowledge graph, DBpedia |\n| 📚 **Academic Literature** | Multi-source search (PubMed, arXiv, OpenAlex, Semantic Scholar, DBLP, INSPIRE-HEP, Crossref, DOAJ, CORE) |\n| 🤖 **Data Science \u0026 Computing** | HuggingFace models/datasets, OpenML, GitHub repositories, scientific computing software, image processing |\n\n### 🛠️ Four-Layer Tool Architecture\n\n| Layer | Description | Examples |\n|---|---|---|\n| 🔧 **Built-in Tools** | Core search \u0026 crawl capabilities | `web_search`, `web_crawl` |\n| 🧪 **ToolUniverse** | 1,900+ scientific tools, ready to use | UniProt, OpenTargets, FAERS, PDB, ADMET, etc. |\n| 📦 **Sandbox Tools** | File operations \u0026 code execution | `read_file`, `write_file`, `execute`, `shell` |\n| 🛠️ **Custom @tool** | User-defined Python functions, hot-loaded from `Tools/` | Your own tools |\n\n### 🎨 Custom Tools\n\nScienceClaw makes it easy to extend with your own tools:\n\n- **Natural language creation** — Simply describe what you want in chat, and the agent will create, test, and save a new tool for you automatically.\n- **Manual mounting** — Drop any Python file with `@tool` decorated functions into the `Tools/` directory; they are auto-detected and hot-loaded without restart.\n\n### 🧠 Skill System\n\nSkills are **structured instruction documents (SKILL.md)** that guide the Agent through complex, multi-step workflows. Unlike tools (executable code), skills act as the Agent's \"playbook\" — defining strategies, rules, and best practices.\n\n#### Built-in Skills\n\n| Skill | Purpose |\n|---|---|\n| 📄 **pdf** | Read, create, merge, split, OCR, and generate professional PDF research reports |\n| 📝 **docx** | Create and edit Word documents with cover pages, TOC, tables, and charts |\n| 📊 **pptx** | Generate and edit PowerPoint slide decks |\n| 📈 **xlsx** | Create and manipulate Excel spreadsheets, CSV/TSV data processing |\n| 🛠️ **tool-creator** | Create \u0026 upgrade custom @tool functions (write → test → save) |\n| 📝 **skill-creator** | Create \u0026 refine skills with draft → test → review → iterate |\n| 🔍 **find-skills** | Search, discover \u0026 install community skills from the open ecosystem |\n| 🧪 **tooluniverse** | Unified access to 1,900+ scientific tools |\n\n#### Multi-Format Report Generation\n\nScienceClaw can produce professional research deliverables in **4 document formats**:\n\n| Format | Features |\n|---|---|\n| **PDF** | Cover page, table of contents, charts (bar/pie/line), in-text citations, references, academic styling |\n| **DOCX** | Cover page, TOC, tables, images, blue-superscript citations, Word-native formatting |\n| **PPTX** | Slide decks with titles, bullet points, images, speaker notes |\n| **XLSX** | Data tables, charts, multi-sheet workbooks, CSV/TSV export |\n\n#### Custom Skills\n\n- **Natural language creation** — Describe your workflow in chat, and the agent will draft, test, and save a new skill for you.\n- **Manual installation** — Place a folder with a `SKILL.md` file into the `Skills/` directory. The agent automatically matches and loads relevant skills based on user intent.\n- **Community ecosystem** — Discover and install skills from the open community with the built-in `find-skills` capability.\n\n---\n\n\u003ca id=\"practical-features\"\u003e\u003c/a\u003e\n\n## 💡 Practical Features\n\n| Feature | Description |\n|---|---|\n| 📨 **One-Click Feishu (Lark) Integration** | Configure Feishu webhook notifications in settings — receive task results, alerts, and reports directly in your Feishu group chat. |\n| ⏰ **Scheduled Tasks** | Set up recurring or one-time tasks with cron-like scheduling. The agent runs automatically at the specified time and delivers results via Feishu or in-app notifications. |\n| 📁 **File Management System** | Built-in file panel for browsing, previewing, and downloading all workspace files generated during agent sessions — no need to dig through directories. |\n| 📊 **Resource Monitoring** | Real-time system resource dashboard showing LLM resource consumption and service health — stay informed about your deployment status at a glance. |\n\n---\n\n\u003ca id=\"project-structure\"\u003e\u003c/a\u003e\n\n## 📂 Project Structure\n\n```\nScienceClaw/\n├── docker-compose.yml              # 10-service orchestration\n├── docker-compose-release.yml      # Pre-built image orchestration (for end users)\n├── docker-compose-china.yml        # China mirror acceleration\n├── images/                         # Static assets (logo, screenshots)\n├── videos/                         # Demo videos\n├── Tools/                          # Custom tools (hot-reload)\n├── Skills/                         # User \u0026 community skill packages\n├── workspace/                      # 🔒 Local workspace (data never leaves your machine)\n└── ScienceClaw/\n    ├── backend/                    # FastAPI backend\n    │   ├── deepagent/              # Core AI agent engine (LangGraph)\n    │   ├── builtin_skills/         # 9 built-in skills (pdf, docx, pptx, xlsx, tooluniverse, ...)\n    │   ├── route/                  # REST API routes\n    │   ├── im/                     # IM integrations (Feishu / Lark)\n    │   ├── mongodb/                # Database access layer\n    │   ├── user/                   # User management\n    │   ├── scripts/                # Utility scripts (Feishu setup, etc.)\n    │   └── translations/           # i18n language packs\n    ├── frontend/                   # Vue 3 + Tailwind frontend\n    ├── sandbox/                    # Isolated code execution environment\n    ├── task-service/               # Scheduled task service (cron jobs)\n    └── websearch/                  # Search \u0026 crawl microservice\n```\n\n---\n\n\u003ca id=\"commands\"\u003e\u003c/a\u003e\n\n## 🧑‍💻 Useful Commands\n\n```bash\n# First launch (recommended for most users) — pull pre-built images, no local compilation\ndocker compose -f docker-compose-release.yaml up -d\n\n# First launch (for developers) — build from source and start all services\ndocker compose up -d --build\n\n# First launch (for developers in China) — build with Chinese mirror sources for faster downloads\ndocker compose -f docker-compose-china.yml up -d --build\n\n# Daily launch — fast startup, no rebuild needed\ndocker compose up -d\n\n# Check service status\ndocker compose ps\n\n# View logs (-f to follow in real time)\ndocker compose logs -f backend     # Backend logs\ndocker compose logs -f frontend    # Frontend logs\ndocker compose logs -f sandbox     # Sandbox logs\n\n# Restart a single service\ndocker compose restart backend\n\n# Stop all services\ndocker compose down\n\n# Stop a single service\ndocker compose stop backend\n```\n\n---\n\n## 🗑️ Uninstall\n\nScienceClaw is built entirely on Docker, so uninstalling it is clean and simple — it has **no side effects on your host system**.\n\n```bash\n# Stop and remove all containers\ndocker compose down\n\n# (Optional) Remove downloaded images to free up disk space\ndocker compose down --rmi all --volumes\n```\n\nThen simply delete the project folder:\n\n```bash\nrm -rf /path/to/ScienceClaw\n```\n\nThat's it. No residual files, no registry entries, no system-level changes.\n\n---\n\n## 🏛️ Built By\n\n**Zhongke Zidong Taichu (Beijing) Technology Co., Ltd.**\n\n---\n\n\u003ca id=\"community\"\u003e\u003c/a\u003e\n\n## 🤝 Community\n\nWe welcome contributions, feedback, and discussions! Join our community:\n\n- Submit issues and feature requests via [GitHub Issues](https://github.com/AgentTeam-TaichuAI/ScienceClaw/issues)\n- Share your custom tools and skills with the community\n\n---\n\n## 📄 License\n\n[MIT License](LICENSE)\n\n---\n\n\u003ca id=\"acknowledgements\"\u003e\u003c/a\u003e\n\n## 🙏 Acknowledgements\n\nScienceClaw is built on the shoulders of excellent open-source projects. We would like to express our sincere gratitude to:\n\n- **[LangChain DeepAgents](https://github.com/langchain-ai/deepagents)** — The batteries-included agent harness built on LangChain and LangGraph. ScienceClaw's core agent engine is powered by the DeepAgents architecture, which provides planning, filesystem access, sub-agent delegation, and smart context management out of the box.\n\n- **[AIO Sandbox](https://github.com/agent-infra/sandbox)** — The all-in-one agent sandbox environment that combines Browser, Shell, File, and MCP operations in a single Docker container. ScienceClaw relies on AIO Sandbox to provide secure, isolated code execution with a unified file system.\n\n- **[ToolUniverse](https://github.com/ZitnikLab/ToolUniverse)** — A unified ecosystem of 1,900+ scientific tools developed by the Zitnik Lab at Harvard. ToolUniverse powers ScienceClaw's multi-disciplinary research capabilities across drug discovery, genomics, astronomy, earth science, and more.\n\n- **[SearXNG](https://github.com/searxng/searxng)** — A privacy-respecting, hackable metasearch engine. ScienceClaw uses SearXNG as the backbone of its `web_search` tool, aggregating results from multiple search engines without tracking.\n\n- **[Crawl4AI](https://github.com/unclecode/crawl4ai)** — An open-source, LLM-friendly web crawler. ScienceClaw's `web_crawl` tool is powered by Crawl4AI, enabling intelligent content extraction from web pages for research and analysis.\n\n---\n\n## ⭐ Star History\n\n\u003cdiv align=\"center\"\u003e\n\n[![Star History Chart](https://api.star-history.com/svg?repos=AgentTeam-TaichuAI/ScienceClaw\u0026type=Date)](https://star-history.com/#AgentTeam-TaichuAI/ScienceClaw\u0026Date)\n\n\u003c/div\u003e\n\n## Contributors\n\n- [Zhiyuan Li](https://github.com/Zhiyuan-Li-John)\n- [Guangchuan Guo](https://github.com/meizhuhanxiang)\n- [Shaoling Lin](https://github.com/SharryLin)\n- [Songsong Lei](https://github.com/slei)\n- [Zhidong Zhang](https://github.com/mumudd)\n\n**Technical Support:** NLP Group, Institute of Automation, Chinese Academy of Sciences\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAgentTeam-TaichuAI%2FScienceClaw","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FAgentTeam-TaichuAI%2FScienceClaw","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAgentTeam-TaichuAI%2FScienceClaw/lists"}