{"name":"open-enthrium-ai-platform: Self-Host SKILL.md Agents and RAG Chat","description":"Open Enthrium AI Platform is a self-hosted web app built around SKILL.md agents and a built-in runtime, with RAG knowledge bases and private AI chat. It is aimed at teams that want to run agents and keep their AI data on their own infrastructure.","github":"https://github.com/enthrium/open-enthrium-ai-platform","url":"https://osrepos.com/repo/enthrium-open-enthrium-ai-platform","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/enthrium-open-enthrium-ai-platform","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/enthrium-open-enthrium-ai-platform.md","json":"https://osrepos.com/repo/enthrium-open-enthrium-ai-platform.json","topics":["ai","self-hosted","rag","agent-skills","knowledge-base","private-chat","connector-catalog"],"keywords":["ai","self-hosted","rag","agent-skills","knowledge-base","private-chat","connector-catalog"],"stars":null,"summary":"Open Enthrium AI Platform is a self-hosted web app built around SKILL.md agents and a built-in runtime, with RAG knowledge bases and private AI chat. It is aimed at teams that want to run agents and keep their AI data on their own infrastructure.","content":"## Overview\n\nOpen Enthrium AI Platform is a self-hosted web-based AI platform built around portable SKILL.md agents, which it runs through its built-in runtime. It also brings together document retrieval with RAG and a private chat assistant, addressing the need to use agents and knowledge-based AI while keeping the service and data on your own infrastructure.\n\nThe project is for teams that want a web interface for configuring AI providers, connectors, knowledge bases, and chat rather than building those pieces themselves. Its README describes a JavaScript application, with Node.js for source-based use and Docker as a deployment option. It does not name a required LLM provider or vector database.\n\n## Key Features\n\n- Run declarative agents defined in SKILL.md files through the platform's runtime.\n- Ingest documents in more than 24 formats for chunking, embedding, and retrieval with cited answers.\n- Offer a private AI chat assistant backed by configured LLMs, knowledge bases, and connectors.\n- Embed the chat assistant as a website widget or use it across workspaces.\n- Configure LLMs, embedding models, vector databases, and connectors through an admin panel.\n- Connect to a broad catalog of services, including databases, cloud storage, communication, developer tools, and CRM systems.\n- Deploy with Docker or run from source using Node.js and Yarn.\n\n## Use Cases\n\n- An organization can host an internal assistant that answers questions from its own documents, with retrieval and chat running on its infrastructure.\n- A team can package repeatable AI tasks as SKILL.md agents and run them through a shared web platform.\n- A product team can add a private AI chat widget backed by its configured knowledge base and connectors.\n- Developers can connect existing systems through the connector catalog instead of writing every integration from scratch.\n\n## Our Take\n\nThis is a broad, fast-changing platform with a promising self-hosted scope, but its short history and concentrated contributor base make it worth evaluating before relying on it for critical workflows.\n\n**Good fit if:**\n- You want a self-hosted web platform combining SKILL.md agents, RAG, and private chat.\n- Your team can operate a Node.js application or Docker deployment and configure its AI and storage services.\n- You value the README's stated Apache-2.0 terms and are prepared to verify the repository's license metadata.\n\n**Look elsewhere if:**\n- You need a mature project with a larger, less concentrated maintainer base: it is new, has two contributors, and most contributions come from one person.\n- You require visible automated test coverage; the project requirements data reports no tests.\n- You need evidence of established issue or pull-request throughput; none were closed or merged in the measured recent period.\n\n## Project Health\n\n| Signal | Value |\n|---|---|\n| Status | **New**: less than six months old and changing fast |\n| Last commit | 2026-09-09 (1 month ago) |\n| Commits, last 90 days | 100+ |\n| Releases, last 12 months | 63 (latest v1.9.3, 2026-09-09) |\n| Contributors | 2 (top contributor: 82% of commits) |\n| Issues closed, last 90 days | 0 |\n| Pull requests merged, last 90 days | 0 |\n| Project age | 3 months |\n\nChecked on 2026-10-15 with the GitHub API.\n\n## Project Facts\n\n- Language: JavaScript\n- Stars: 1\n- Forks: 0\n- Topics: agent-framework, agentic-ai, ai-framework, ai-orchestration, connector, developer-tools, docker, enterprise-ai\n- Website: https://www.openenthrium.com/\n- Archived: no\n\n## What You Need\n\nDetected in the repository:\n\n- Node.js (from package.json)\n- A Dockerfile, so it can run in a container\n- Automated checks on GitHub Actions\n\n## Getting Started\n\nStart the Docker image with the required admin credentials and a persistent data volume:\n\n```bash\ndocker run -d -p 3000:3000 -p 3001:3001 \\\n  -e JWT_SECRET=your-secret \\\n  -e SUPER_ADMIN_EMAIL=admin [at] example.com \\\n  -e SUPER_ADMIN_PASSWORD=your-password \\\n  -e LICENSE_TYPE=community \\\n  -v open-enthrium-data:/app/server/storage \\\n  jumbocoder/open-enthrium-ai-platform:latest\n```\n\nThen open `http://localhost:3000` and configure the AI and storage providers in the admin panel. See the [README](https://github.com/enthrium/open-enthrium-ai-platform#readme) for source installation and configuration details.\n\n## License in Plain Words\n\nNo standard license was detected. Without a license, the default copyright rules apply: you may read the code, but not reuse it. Check the repository or ask the authors.\n\n## Alternatives\n\n- [53AIHub](https://osrepos.com/repo/53ai-53aihub): 53AIHub manages agents, prompts, tools, and knowledge bases across connected platforms, while Open Enthrium provides its own SKILL.md runtime.\n- [rag-agent-platform](https://osrepos.com/repo/nedonion-rag-agent-platform): rag-agent-platform combines document retrieval with agents and MCP tools, rather than centering on SKILL.md agents and a built-in runtime.\n- [AingDesk](https://osrepos.com/repo/aingdesk-aingdesk): AingDesk offers a desktop and server assistant for model APIs or local models, with web search and shareable assistants alongside knowledge bases.\n- [cabinet](https://osrepos.com/repo/hilash-cabinet): Cabinet builds agent workflows around a local Markdown knowledge base and scheduled jobs, rather than a web platform with a built-in SKILL.md runtime.\n\n| Project | Language | License | Stars | Status |\n|---|---|---|---|---|\n| **open-enthrium-ai-platform** | JavaScript | – | 1 | New |\n| [53AIHub](https://osrepos.com/repo/53ai-53aihub) | Go | Other | 4.3k | Active |\n| [rag-agent-platform](https://osrepos.com/repo/nedonion-rag-agent-platform) | Java | MIT | 89 | Active |\n| [AingDesk](https://osrepos.com/repo/aingdesk-aingdesk) | TypeScript | MIT | 2.5k | Quiet |\n| [cabinet](https://osrepos.com/repo/hilash-cabinet) | TypeScript | MIT | 2.9k | Active |\n\n## Considerations\n\n- The project is new and changing quickly, with frequent recent commits and releases. That activity is encouraging, but its short history offers limited evidence of long-term stability.\n- Development is concentrated among two contributors, with most of the code attributed to one person. The measured recent period shows no issues closed or pull requests merged, so assess the project's maintenance responsiveness for your needs.\n- The requirements list Node.js and Docker, but not Compose or Helm. The README does not specify a required GPU; you will need to choose and configure your own LLM, embedding model, and vector database.\n- The README says Apache-2.0, while the repository metadata reports `NOASSERTION`. Review the repository's license file and confirm the applicable terms before adoption.","metrics":{"detailViews":5,"githubClicks":3},"dates":{"published":null,"modified":"2026-10-15T12:11:32.000Z"}}