[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-73854":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":17,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":19,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":34,"readmeContent":35,"aiSummary":36,"trendingCount":16,"starSnapshotCount":16,"syncStatus":37,"lastSyncTime":38,"discoverSource":39},73854,"codel","semanser\u002Fcodel","semanser","✨ Fully autonomous AI Agent that can perform complicated tasks and projects using terminal, browser, and editor.","https:\u002F\u002Fdiscord.gg\u002FuMaGSHNjzc",null,"TypeScript",2454,202,30,28,0,1,8,3,62.22,"GNU Affero General Public License v3.0",false,"main",[25,26,27,28,29,30,31,32,33],"agent","ai","autonomous-agents","bot","devin","llama2","llms","ollama","openai","2026-06-12 04:01:12","\u003Cimg src=\".\u002F.github\u002Fdemo.png\" \u002F>\n\u003Cdiv align=\"center\">Fully autonomous AI Agent that can perform complicated tasks and projects using terminal, browser, and editor.\u003C\u002Fdiv>\n\u003C\u002Fbr>\n\n**Discord: https:\u002F\u002Fdiscord.gg\u002FuMaGSHNjzc**\n\n# Features\n- 🔓 Secure. Everything is running in a sandboxed Docker environment.\n- 🤖 Autonomous. Automatically detects the next step and performs it.\n- 🔍 Built-in browser. Fetches latest information from the web (tutorials, docs, etc.) if needed.\n- 📙 Built-in text editor. View all the modified files right in your browser.\n- 🧠 All the history commands and outputs are saved in the PostgreSQL database.\n- 📦 Automatic Docker-image picker based on the user task.\n- 🤳 Self-hosted\n- 💅 Modern UI\n\n# Getting started\nThe simplest way to run Codel is to use a pre-built Docker image. You can find the latest image on the [Github Container Registry](https:\u002F\u002Fgithub.com\u002Fsemanser\u002Fcodel\u002Fpkgs\u002Fcontainer\u002Fcodel).\n\n\n> [!IMPORTANT]\n> You need to use a corresponding environment variable in order to use any of the supported language models.\n\nYou can run the Docker image with the following command. Remove or change the environment variables according to your needs.\n```bash\ndocker run \\\n  -e OPEN_AI_KEY=your_open_ai_key \\\n  -e OPEN_AI_MODEL=gpt-4-0125-preview \\\n  -e OLLAMA_MODEL=llama2 \\\n  -p 3000:8080 \\\n  -v \u002Fvar\u002Frun\u002Fdocker.sock:\u002Fvar\u002Frun\u002Fdocker.sock \\\n  ghcr.io\u002Fsemanser\u002Fcodel:latest\n```\n\nAlternatively, you can create a `.env` file and run the Docker image with the `--env-file` flag. More information can be found [here](https:\u002F\u002Fdocs.docker.com\u002Freference\u002Fcli\u002Fdocker\u002Fcontainer\u002Frun\u002F#env)\n\nNow you can visit [localhost:3000](localhost:3000) in your browser and start using Codel.\n\n\u003Cdetails>\n    \u003Csummary>Supported environment variables\u003C\u002Fsummary>\n\n    * `OPEN_AI_KEY` - OpenAI API key. You can get the key [here](https:\u002F\u002Fplatform.openai.com\u002Faccount\u002Fapi-keys).\n    * `OPEN_AI_MODEL` - OpenAI model (default: gpt-4-0125-preview). The list of supported OpenAI models can be found [here](https:\u002F\u002Fpkg.go.dev\u002Fgithub.com\u002Fsashabaranov\u002Fgo-openai#pkg-constants).\n    * `OPEN_AI_SERVER_URL` - OpenAI server URL (default: https:\u002F\u002Fapi.openai.com\u002Fv1). Change this URL if you are using an OpenAI compatible server.\n    * `OLLAMA_MODEL` - locally hosted Ollama model (default: https:\u002F\u002Follama.com\u002Fmodel). The list of supported Ollama models can be found [here](https:\u002F\u002Follama.com\u002Fmodels).\n    * `OLLAMA_SERVER_URL` - Ollama server URL (default: https:\u002F\u002Fhost.docker.internal:11434). Change this URL if you are using an Ollama compatible server.\n    See backend [.env.example](.\u002Fbackend\u002F.env.example) for more details.\n\n\u003C\u002Fdetails>\n\n# Development\n\nCheck out the [DEVELOPMENT.md](.\u002FDEVELOPMENT.md) for more information.\n\n# Roadmap\n\nYou can find the project's roadmap [here](https:\u002F\u002Fgithub.com\u002Fsemanser\u002Fcodel\u002Fmilestones).\n\n# Credits\nThis project wouldn't be possible without:\n- https:\u002F\u002Farxiv.org\u002Fabs\u002F2308.00352\n- https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.08299\n- https:\u002F\u002Fwww.cognition-labs.com\u002Fintroducing-devin\n- https:\u002F\u002Fgithub.com\u002Fgo-rod\u002Frod\n- https:\u002F\u002Fgithub.com\u002Fsemanser\u002FJsonGenius\n","Codel 是一个完全自主的AI代理，能够利用终端、浏览器和编辑器执行复杂的任务和项目。它具有安全性和自主性，运行在沙箱化的Docker环境中，并能自动检测并执行下一步操作。内置浏览器可从网络获取最新信息（如教程、文档等），内置文本编辑器允许用户直接在浏览器中查看所有修改过的文件。此外，Codel支持多种语言模型，包括OpenAI的GPT-4和Ollama的Llama2，且所有历史命令和输出都保存在PostgreSQL数据库中。此工具非常适合需要自动化处理复杂开发任务或项目的场景，特别是对于那些希望提高工作效率同时保持环境安全性的开发者而言。",2,"2026-06-11 03:47:39","high_star"]