{"id":50704591,"url":"https://github.com/Ontheia/ontheia","last_synced_at":"2026-06-26T10:01:07.370Z","repository":{"id":352421188,"uuid":"1206035130","full_name":"Ontheia/ontheia","owner":"Ontheia","description":"Self-hosted AI agent platform — multi-provider, MCP-native, GDPR by Design.","archived":false,"fork":false,"pushed_at":"2026-06-16T12:12:28.000Z","size":2209,"stargazers_count":6,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-06-16T13:24:47.875Z","etag":null,"topics":["agent-orchestration","ai-agents","anthropic","chain-of-thought","docker","gdpr","gemini","grok","llm","mcp","multi-agent","nodejs","ollama","openai","pgvector","postgresql","rag","self-hosted","typescript"],"latest_commit_sha":null,"homepage":"https://ontheia.ai/","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Ontheia.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":"ROADMAP.md","authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":"CLA.md"}},"created_at":"2026-04-09T14:09:09.000Z","updated_at":"2026-06-16T12:12:32.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/Ontheia/ontheia","commit_stats":null,"previous_names":["ontheia/ontheia"],"tags_count":6,"template":false,"template_full_name":null,"purl":"pkg:github/Ontheia/ontheia","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ontheia%2Fontheia","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ontheia%2Fontheia/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ontheia%2Fontheia/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ontheia%2Fontheia/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Ontheia","download_url":"https://codeload.github.com/Ontheia/ontheia/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ontheia%2Fontheia/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34811922,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-26T02:00:06.560Z","response_time":106,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["agent-orchestration","ai-agents","anthropic","chain-of-thought","docker","gdpr","gemini","grok","llm","mcp","multi-agent","nodejs","ollama","openai","pgvector","postgresql","rag","self-hosted","typescript"],"created_at":"2026-06-09T11:00:19.006Z","updated_at":"2026-06-26T10:01:07.334Z","avatar_url":"https://github.com/Ontheia.png","language":"TypeScript","funding_links":[],"categories":["🏗️ エージェントフレームワーク"],"sub_categories":["その他の標準"],"readme":"# Ontheia\n\n**Your Data. Your AI. Your Rules.**\n\nEvery time AI work runs on someone else's infrastructure, you give up more than privacy. You give up control over data, tools, workflows, and the rules that govern how work gets done.\n\n**Ontheia** is a self-hosted, open-source AI agent platform for work that stays under your control. It keeps AI capable and connected — within boundaries you set.\n\nMost AI setups stay fragmented: separate chats, tools, scripts, and automations with no shared memory, no continuity, and no operational boundaries. Ontheia brings specialized agents, tools, memory, scheduling, and delegation into one governed work context — on your own infrastructure.\n\n→ **[ontheia.ai](https://ontheia.ai)** · [Documentation](https://docs.ontheia.ai) · [Blog](https://ontheia.ai/blog)\n\n[![License: AGPL v3](https://img.shields.io/badge/License-AGPL_v3-blue.svg)](./LICENSE)\n[![License: Commercial](https://img.shields.io/badge/License-Commercial-green.svg)](./LICENSE-COMMERCIAL.md)\n![Self-hosted](https://img.shields.io/badge/self--hosted-yes-brightgreen)\n![Docker](https://img.shields.io/badge/docker-ready-blue?logo=docker)\n![TypeScript](https://img.shields.io/badge/TypeScript-5.x-3178c6?logo=typescript)\n![PostgreSQL](https://img.shields.io/badge/PostgreSQL-pgvector-336791?logo=postgresql)\n\n---\n\n## More than the sum of its parts\n\nNo single feature is the point. The shift comes from combining them.\n\nAn agent in Ontheia can break a request into subtasks and hand them to other specialized agents — each with its own tools, memory, and skills. They coordinate, remember across sessions, and act on their own schedule. A fresh install ships with two agents to start from: the **Ontheia Guide** walks you through setup, and a **Personal Assistant** is ready to work.\n\nThis isn't a chat UI with plugins, prompt-based automation, or a bare agent runtime — it's an operational layer for sovereign AI work: agents that use your tools, retain context, coordinate capabilities, and operate over time, all inside one system you control.\n\n---\n\n## What's inside\n\n- **Specialized capabilities** — use agents and Agent Skills instead of one generic assistant. Skills are reusable modules based on the open Agent Skills standard, and the built-in **skill-creator** can build and test new ones directly in chat.\n- **Delegation \u0026 coordination** — hand work off across specialists with the `delegate-to-agent` tool, either autonomously or as declarative Chain steps.\n- **Tools \u0026 external systems** — Ontheia is **MCP-native**, so agents can connect to tools and services over an open standard instead of proprietary integrations.\n- **Persistent memory** — built-in RAG with **pgvector**, isolated by user and namespace, so agents can remember and reuse knowledge over time.\n- **Workflows** — the visual **Chain Engine** turns multi-step logic into no-code pipelines.\n- **Scheduling** — run recurring or one-time jobs automatically, including jobs that resume an existing chat where it left off.\n- **Vendor-agnostic** — Claude, ChatGPT, Gemini, Grok, Ollama, or any OpenAI-compatible model. Switch providers without rewriting agents.\n- **Governance \u0026 control** — self-hosted and **GDPR-compliant by architecture** — data never leaves your servers. Role-based access enforced with PostgreSQL Row Level Security; you decide *per agent* which model can access which data.\n\n---\n\n## How it works\n\n```mermaid\nflowchart TB\n    subgraph infra[\"🔒 Your Infrastructure\"]\n        UI[WebUI / Chat] --\u003e A1[Agent]\n        A1 --- SK[Skills]\n        A1 --- MEM[Memory / RAG]\n        MEM --- DB[(PostgreSQL + pgvector)]\n        A1 --\u003e|delegate-to-agent| A2[Sub-Agent]\n        A1 --\u003e CE[Chain Engine]\n        A1 --\u003e SCH[Scheduler]\n        A1 --\u003e TOOLS[MCP Tools / External Systems]\n        A1 --\u003e OLLAMA[Ollama\u003cbr/\u003elocal models]\n    end\n    A1 -.-\u003e PROV[Cloud AI Providers\u003cbr/\u003eClaude · GPT · Gemini · Grok]\n\n    classDef external fill:#fff3cd,stroke:#d4a017,stroke-width:1px,color:#5c4400,font-weight:bold;\n    class PROV external;\n```\n\nEverything that matters — chat history, memory, skills, workflows, schedules, tool connections — stays inside your infrastructure. Only the model inference call crosses the boundary, and you choose which provider gets it.\n\n---\n\n## Screenshots\n\n| Chat \u0026 Agents | MCP Tools in Action |\n|---|---|\n|![Chat](https://ontheia.ai/screenshots/ontheia_chat_en.png) | ![MCP](https://ontheia.ai/screenshots/ontheia_exa_en.png) |\n| *What can I use Ontheia for?* | *Exa search → PDF summary → email — in one step.* |\n\n---\n\n## Requirements\n\n| Requirement | Minimum | Notes |\n|---|---|---|\n| **OS** | Linux / macOS | Windows via WSL2 |\n| **Docker** | 24+ | Rootless mode recommended |\n| **Docker Compose** | v2 (plugin) | `docker compose` (not `docker-compose`) |\n| **RAM** | 2 GB | 4 GB recommended |\n| **Disk** | 5 GB free | 10 GB recommended |\n| **Ports** | 8080, 5173 | Configurable during setup |\n| **openssl** | any | For secret generation (`apt install openssl`) |\n| **curl** | any | For health checks |\n| **jq** | any | For JSON parsing (`apt install jq`) |\n\nAt least one AI provider API key is required to chat (e.g. Anthropic, OpenAI, or a local Ollama instance). Memory/RAG features additionally require an embedding-capable provider.\n\n---\n\n## Quick Start\n\n**Guided setup** (recommended) — one command, configures everything interactively:\n\n```bash\ncurl -fsSL https://get.ontheia.ai | bash\n```\n\nThis downloads Ontheia to `~/ontheia` and runs the installer, which handles `.env` creation, secret generation, Docker builds, database migrations, and bootstraps the first admin account.\n\nPrefer to inspect the script first? Clone and run it from the repository:\n\n```bash\ngit clone https://github.com/Ontheia/ontheia.git\ncd ontheia\nbash scripts/install.sh\n```\n\n**Manual setup:**\n\n```bash\ngit clone https://github.com/Ontheia/ontheia.git\ncd ontheia\ncp .env.example .env\n# Edit .env — set FLYWAY_PASSWORD, ONTHEIA_APP_PASSWORD, SESSION_SECRET, ADMIN_EMAIL\ndocker compose up -d\n```\n\n**Open Ontheia**\n\nVisit [http://localhost:5173](http://localhost:5173) in your browser.\n\nFull installation guide: [docs.ontheia.ai/en/getting-started/02_installation](https://docs.ontheia.ai/en/getting-started/02_installation)\n\n---\n\n## Documentation\n\nFull documentation at **[docs.ontheia.ai](https://docs.ontheia.ai)**\n\n| Topic | EN | DE |\n|---|---|---|\n| Introduction | [EN](https://docs.ontheia.ai/en/getting-started/01_introduction) | [DE](https://docs.ontheia.ai/de/getting-started/01_introduction) |\n| Installation | [EN](https://docs.ontheia.ai/en/getting-started/02_installation) | [DE](https://docs.ontheia.ai/de/getting-started/02_installation) |\n| Environment variables | [EN](https://docs.ontheia.ai/en/configuration/01_environment_variables) | [DE](https://docs.ontheia.ai/de/configuration/01_environment_variables) |\n| Agents | [EN](https://docs.ontheia.ai/en/admin/agents/01_concept) | [DE](https://docs.ontheia.ai/de/admin/agents/01_concept) |\n| Agent Skills | [EN](https://docs.ontheia.ai/en/admin/skills/01_concept) | [DE](https://docs.ontheia.ai/de/admin/skills/01_concept) |\n| Chain Engine | [EN](https://docs.ontheia.ai/en/admin/chains/01_concept) | [DE](https://docs.ontheia.ai/de/admin/chains/01_concept) |\n| Memory / RAG | [EN](https://docs.ontheia.ai/en/admin/memory_audit/01_architecture) | [DE](https://docs.ontheia.ai/de/admin/memory_audit/01_architecture) |\n| Security | [EN](https://docs.ontheia.ai/en/security/01_security_concept) | [DE](https://docs.ontheia.ai/de/security/01_security_concept) |\n| Automation | [EN](https://docs.ontheia.ai/en/automation/01_overview) | [DE](https://docs.ontheia.ai/de/automation/01_overview) |\n| API Reference | [EN](https://docs.ontheia.ai/en/api/01_api-ref) | [DE](https://docs.ontheia.ai/de/api/01_api-ref) |\n\n---\n\n## Stack\n\n- **Backend:** Node.js / TypeScript (Fastify)\n- **Frontend:** React, shadcn/ui, Tailwind CSS\n- **Database:** PostgreSQL with pgvector extension\n- **Containerization:** Docker, Docker Compose (rootless)\n- **AI Protocols:** Anthropic Messages API, OpenAI-compatible API, MCP (Model Context Protocol)\n\n---\n\n## Roadmap\n\nSee [ROADMAP.md](./ROADMAP.md) for planned features across all horizons.\n\nCommunity input is welcome — open an [issue](https://github.com/Ontheia/ontheia/issues) or start a [discussion](https://github.com/Ontheia/ontheia/discussions).\n\n---\n\n## Contributing\n\nContributions are welcome.\n\n1. Fork the repository\n2. Create a feature branch\n3. Submit a pull request\n\nPlease read [CONTRIBUTING.md](./CONTRIBUTING.md) before opening a pull request.\n\nIf Ontheia resonates with you, a ⭐ helps others find it — and helps us build a community around sovereign AI.\n\n---\n\n## License\n\nOntheia is dual-licensed:\n\n1. **Open Source:** [GNU Affero General Public License v3.0](./LICENSE) — free for personal use, self-hosted deployments, and open-source projects.\n2. **Commercial:** [Commercial License](./LICENSE-COMMERCIAL.md) — for organizations that need to use Ontheia without AGPL obligations (e.g. as part of a proprietary product or managed service). Contact us via [ontheia.ai](https://ontheia.ai) for inquiries.\n\n---\n\n## Contact\n\n- Website: [ontheia.ai](https://ontheia.ai)\n- GitHub Discussions: [github.com/Ontheia/ontheia/discussions](https://github.com/Ontheia/ontheia/discussions)\n\n---\n\n© 2026 Ontheia · Open source under AGPL-3.0.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOntheia%2Fontheia","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FOntheia%2Fontheia","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOntheia%2Fontheia/lists"}