[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72303":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":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":15,"stars30d":17,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":31,"readmeContent":32,"aiSummary":33,"trendingCount":16,"starSnapshotCount":16,"syncStatus":15,"lastSyncTime":34,"discoverSource":35},72303,"ii-agent","Intelligent-Internet\u002Fii-agent","Intelligent-Internet","II-Agent: a new open-source framework to build and deploy intelligent agents","https:\u002F\u002Fii.inc\u002Fweb\u002Fblog\u002Fpost\u002Fii-agent",null,"Python",3347,510,47,2,0,10,30.13,"Apache License 2.0",false,"main",true,[24,25,26,27,28,29,30],"agent","agentic-ai","ai","ai-agent","ai-agent-framework","llm","manus","2026-06-12 02:03:01","\u003Cdiv align=\"center\">\n\u003Cimg width=\"1200\" height=\"630\" alt=\"ii-agent-banner\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F7b61e0c0-0d98-495f-a126-6f1b92990631\" \u002F>\n\n\n# II Agent\n\n[![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FIntelligent-Internet\u002Fii-agent?style=social)](https:\u002F\u002Fgithub.com\u002FIntelligent-Internet\u002Fii-agent\u002Fstargazers)\n[![Discord Follow](https:\u002F\u002Fdcbadge.limes.pink\u002Fapi\u002Fserver\u002FyDWPsshPHB?style=flat)](https:\u002F\u002Fdiscord.gg\u002FyDWPsshPHB)\n[![License](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-Apache%202.0-blue.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FApache-2.0)\n[![Blog](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FBlog-II--Agent-blue)](https:\u002F\u002Fii.inc\u002Fweb\u002Fblog\u002Fpost\u002Fii-agent)\n[![GAIA Benchmark](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FGAIA-Benchmark-green)](https:\u002F\u002Fii-agent-gaia.ii.inc\u002F)\n[\u003Cimg src=\"https:\u002F\u002Fdevin.ai\u002Fassets\u002Fdeepwiki-badge.png\" alt=\"Ask DeepWiki.com\" height=\"20\"\u002F>](https:\u002F\u002Fdeepwiki.com\u002FIntelligent-Internet\u002Fii-agent)\n\n\u003C\u002Fdiv>\n\nII-Agent is an open-source AI agent built for real work — now out of beta. 100% open source under the Apache-2.0 license.\n\nWhether you're a solo developer, a research team, or an enterprise building internal tooling — you can run it, fork it, and extend it. No black boxes. No vendor lock-in. Bring your own API keys (BYOK) for full control over cost and model providers.\n\n[**Try the web app**](https:\u002F\u002Fagent.ii.inc\u002F) | [**Join our Discord**](https:\u002F\u002Fdiscord.gg\u002FyDWPsshPHB)\n\n## Introduction\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F430425c4-2352-4101-9fdb-46bdfc63d26a\n\n## Key Features\n\n### Build\n\n* **Mobile App Development** — Go from a short prompt to a full mobile application\n* **Website App Development** — Go from a short prompt to a full website application\n* **Storybook Generation** — Create fully illustrated picture books from a single prompt\n* **Video & Image Generation** — Multiple model support within one workflow\n* **Live Editing** — Real-time editing for websites, slides, and storybooks\n* **Plan Mode** — Visual project planning before building\n\n\n### Research\n\n* **Fast Research & Deep Research** — Quick answers or multi-step investigations\n* **Interactive Website Generation** — Turn research briefs into complete websites with structure, visuals, citations, and embedded Q&A\n\n### Automate & Integrate\n\n* **Built-in & Custom Skills** — Reuse workflows and connect GitHub-based processes\n* **App Integrations** — Gmail, Slack, GitHub, Notion, Google Calendar, Discord, Dropbox, Canva, and more\n* **Faster Execution** — Significantly improved speed compared to earlier beta iterations\n\n### Everything Else\n\n| Domain | Capabilities |\n| :--- | :--- |\n| **Chat** | Multi-model conversations (switch providers mid-thread), file attachments, code interpreter, text file search |\n| **Agent** | General tasks with multi-step task planning |\n| **Documents** | PDF extraction & creation, Excel formulas & charts, Word editing, PowerPoint manipulation |\n| **Slides** | Prompt-to-deck creation with live collaborative editing and templates |\n\n\n## Installation\n\n### Prerequisites\n\n- **Docker** — [Install Docker](https:\u002F\u002Fdocs.docker.com\u002Fget-docker\u002F)\n- **uv** — `curl -LsSf https:\u002F\u002Fastral.sh\u002Fuv\u002Finstall.sh | sh`\n- **Node.js & npm** — [Install Node.js](https:\u002F\u002Fnodejs.org\u002F) (or use nvm)\n\n### Quick Start\n\n```bash\n# 1. Clone the repository\ngit clone https:\u002F\u002Fgithub.com\u002FIntelligent-Internet\u002Fii-agent.git\ncd ii-agent\n\n# 2. Run first-time setup (creates .env files + installs deps)\nmake setup\n\n# 3. Configure your LLM API keys\n#    Edit .env and set at least one LLM provider:\n\n#    Option A: Inline JSON in .env\n#    MODEL_CONFIGS='[{\"model_id\":\"claude-sonnet-4-6\",\"provider\":\"Anthropic\",\"api_key\":\"sk-ant-...\",\"display_name\":\"Claude Sonnet 4\",\"is_default\":true}]'\n\n#    Option B: YAML config file\n#    Copy model_configs.example.yaml to model_configs.yaml, fill in your keys,\n#    then set MODEL_CONFIGS_FILE=model_configs.yaml in .env\n\n# 4. Start everything (infra + backend + frontend)\nmake dev-all\n```\n\nThis starts:\n- **Backend** at http:\u002F\u002Flocalhost:8000\n- **Frontend** at http:\u002F\u002Flocalhost:1420\n- **PostgreSQL** at localhost:5432\n- **Redis** at localhost:6379\n- **MinIO** (S3-compatible storage) at http:\u002F\u002Flocalhost:9001 (minioadmin\u002Fminioadmin)\n\n### Configuration Files\n\n| File | Created from | Purpose |\n|------|-------------|---------|\n| `.env` | `.env.example` | Backend config: database, Redis, storage, auth, LLM keys |\n| `frontend\u002F.env` | `frontend\u002F.env.example` | Frontend config: API URL, Google OAuth, theme |\n| `model_configs.yaml` | `model_configs.example.yaml` | LLM model definitions (alternative to inline JSON in `.env`) |\n\n### LLM Providers\n\nII-Agent supports multiple LLM providers. Configure them in `model_configs.yaml` or via `MODEL_CONFIGS` in `.env`:\n\n| Provider | Example model_id | Notes |\n|----------|-----------------|-------|\n| OpenAI | `gpt-5.4` | Requires `api_key` |\n| Anthropic | `claude-opus-4-6` | Direct API or Vertex AI |\n| Google | `gemini-3.1-pro-preview` | Direct API or Vertex AI |\n\nSee [`model_configs.example.yaml`](model_configs.example.yaml) for full configuration options including Vertex AI, Azure, and self-hosted models.\n\n### Useful Make Commands\n\n```bash\nmake help             # Show all available commands\nmake dev-all          # Start everything (infra + backend + frontend)\nmake infra            # Start only Postgres, Redis, MinIO\nmake backend-dev      # Start backend only (port 8000)\nmake frontend-dev     # Start frontend only (port 5173)\nmake db-migrate       # Run database migrations\nmake lint             # Lint backend + frontend\nmake format           # Auto-format backend + frontend\nmake test             # Run all tests\nmake stack            # Start full stack via Docker Compose\n```\n\n### Docker Compose (Full Stack)\n\nTo run everything in Docker (no local Python\u002FNode required):\n\n```bash\n# Copy and edit the stack env file\ncp docker\u002F.stack.env.example docker\u002F.stack.env\n# Edit docker\u002F.stack.env with your credentials\n\nmake stack            # Start full stack\nmake stack-build      # Start with --build (rebuild images)\nmake stack-down       # Stop and clean up\nmake stack-logs       # Tail all logs\n```\n\n### Additional Resources\n\nFor more details, refer to our [official guide](https:\u002F\u002Fintelligent-internet.github.io\u002Fii-agent-prod\u002F)\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fd1fa7cde-06cc-4103-bed0-d4ad5e640de4\n","II-Agent 是一个用于构建和部署智能代理的新开源框架。它支持从简短提示生成完整的移动应用、网站应用及故事书，提供视频与图像生成、实时编辑等功能，并且能够快速进行研究调查或生成交互式网站。项目采用Python语言编写，具有高度的灵活性和可扩展性，允许用户自定义技能并集成多种应用程序接口如Gmail、Slack等。适用于个人开发者、研究团队以及需要内部工具建设的企业，在保证透明度的同时避免了供应商锁定的问题。","2026-06-11 03:41:14","high_star"]