Skip to content
Back to search

opsintech-platform

OpsinTech Platform — An enterprise-grade AI agent platform built on LangGraph, featuring multi-tenant architecture, role-based access control, sandboxed tool execution, and an admin UI for managing models, MCP servers, skills, and tools. Designed for production deployment with Docker, PostgreSQL support, and comprehensive governance capabilities.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/opsintech--opsintech-platform/badge.svg)](/listings/opsintech--opsintech-platform)

HTML

<a href="/listings/opsintech--opsintech-platform"><img src="/api/listings/opsintech--opsintech-platform/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

1. **Clone and configure**

   git clone https://github.com/opsintech/opsintech-platform.git
   cd opsintech-platform
   make config

Generates `config.yaml` with platform-level settings (database, sandbox, tool groups). **No model configuration needed.**

2. **Start and log in**

   make up

Open http://localhost:2026. On first visit, you'll be redirected to the Setup Wizard to set your admin email and password.

> You can also use `docker compose up -d`, but `make up` handles config initialization and secret generation automatically.

3. **Add models via admin UI**

Log in as platform admin, go to **Settings → Models**, pick from 20+ provider templates, enter your API key.

> Models are stored in the database. Do **not** configure models in `config.yaml` for production.

Running Options

**Docker production**:

make up              # Build images and start all services (recommended for first deploy)
make up-nobuild      # Start services without rebuilding images
make down            # Stop and remove containers
make rebuild-images  # Remove all OpsinTech images and rebuild from scratch

**Local development**:

make check           # Verify prerequisites (Node.js 22+, pnpm, uv, nginx)
make install         # Install dependencies
make dev             # Start dev servers (with hot-reload)
make stop            # Stop all services

**Docker development**:

make docker-init     # Pull sandbox image
make docker-start    # Start Docker dev services
make docker-stop     # Stop Docker dev services
make docker-logs     # View all logs

Access: http://localhost:2026

China Users: Preparing Images

In China, pulling base images during Docker builds may fail due to network issues. Pre-pull before building:

# Required images
docker pull python:3.12-slim
docker pull node:22-alpine
docker pull nginx:alpine
docker pull docker:cli

# Build-stage dependency
docker pull ghcr.io/astral-sh/uv:0.9.26

# Optional images
docker pull postgres:16-alpine          # PostgreSQL mode
docker pull enterprise-public-cn-beijing.cr.volces.com/vefaas-public/all-in-one-sandbox:latest  # Sandbox

For mirror accelerator setup, see the [Quick Start Guide](QUICKSTART.md#china-users-preparing-images-for-local-builds).

Advanced

Sandbox Mode

Three execution modes: Local / Docker containers / Docker + Kubernetes. See [Sandbox Guide](backend/docs/CONFIGURATION.md#sandbox).

MCP Server

Configurable MCP servers (managed per-tenant via admin UI). Supports stdio/SSE/HTTP transports with OAuth token flows.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 331 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # OpsinTech Platform
  2. [中文](./README_zh.md) | English
  3. [![Python](https://img.shields.io/badge/Python-3.12%2B-3776AB?logo=python&logoColor=white)](./backend/pyproject.toml)
  4. [![Node.js](https://img.shields.io/badge/Node.js-22%2B-339933?logo=node.js&logoColor=white)](./Makefile)
  5. [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](./LICENSE)
  6. [![Built on DeerFlow](https://img.shields.io/badge/Built_on-DeerFlow-8A2BE2)](https://github.com/bytedance/deer-flow)
  7. OpsinTech is an **AI-Native Operations Platform for production environments**. v1.0 is built on [DeerFlow](https://github.com/bytedance/deer-flow)'s Agent runtime (ByteDance, GitHub Trending #1), with multi-tenancy, RBAC, audit logging, visual admin dashboards, and database-driven configuration layered on top.
  8. > **Our mission: turn AI Agents from impressive demos into governed, enterprise-ready platforms.**
  9. ## Table of Contents
  10. - [Platform Features](#platform-features)
  11. - [Why OpsinTech Exists](#why-opsintech-exists)
  12. - [v1.0 — What We Built](#v10--what-we-built)
  13. - [Our Vision](#our-vision)
  14. - [Roadmap](#roadmap)
  15. - [Quick Start](#quick-start)
  16. - [Supported Models](#supported-models)
  17. - [Internationalization](#internationalization)
  18. - [Documentation](#documentation)
  19. - [Contributing](#contributing)
  20. - [License](#license)
  21. - [Acknowledgments](#acknowledgments)
  22. ## Platform Features
  23. OpsinTech transforms AI Agents into a governed production platform with the following capabilities:
  24. ### 🏠 Multi-Tenancy Workspace
  25. A unified workspace with three-tier resource isolation (`user → tenant → global`). Each user gets a personal tenant on registration, and tenant admins manage members, models, tools, and skills independently.
  26. **Modules:**
  27. - **Overview** — Dashboard with key metrics and quick actions
  28. - **Agent Gallery** — Browse and select AI agents for different tasks
  29. - **Chat Workspace** — Conversational AI interface with artifact management
  30. - **Terminal Agent** — Governed terminal with AI-assisted command execution, asset management, and approval workflows
  31. - **Skill Editor** — Create, edit, and test AI Skills with sandbox testing and AI-assisted instruction generation
  32. - **Incident Management** — Alert ingestion, signal analysis, and incident lifecycle tracking
  33. ### 🤖 Agent Capabilities
  34. | Capability | Description |
  35. |---|---|
  36. | **Chat Agent** | Conversational AI with task decomposition, sub-agent parallelism, and artifact generation |
  37. | **Terminal Agent** | AI-assisted terminal with security governance, command approval, and multi-host asset management |
  38. | **Skill System** | Reusable AI Skill templates with sandbox testing environment |
  39. | **MCP Servers** | Configurable MCP servers per tenant (stdio/SSE/HTTP transports) |
  40. | **Sandbox Execution** | Isolated code execution (local / Docker / Kubernetes modes) |
  41. ### 🔐 Security & Governance
  42. | Feature | Description |
  43. |---|---|
  44. | **RBAC** | Three-tier roles: `platform_admin` / `tenant_admin` / `tenant_member` |
  45. | **Audit Trail** | Full operation audit logging with per-tenant isolation |
  46. | **Terminal Security** | Command approval workflows, credential management, execution audit |
  47. | **User Management** | Status management (active / suspended), mandatory password rotation |
  48. ### 🌐 Platform Administration
  49. | Dashboard | Scope |
  50. |---|---|
  51. | **Platform Admin** | Users, tenants, global audit, model templates, announcements |
  52. | **Tenant Admin** | Members, models, tools, skills, MCP servers |
  53. ### 🎨 User Experience
  54. - **4-Language i18n**: English, 中文, 日本語, 한국어
  55. - **Model Provider Templates**: 20+ pre-configured providers with auto-filled settings
  56. - **Docker One-Click Deploy**: `make up` to get everything running
  57. - **Hot-Reload Dev Mode**: `make dev` for local development
  58. ---
  59. ## Why OpsinTech Exists
  60. ### DeerFlow: A Proven Agent Runtime
  61. DeerFlow proved that AI Agents can go beyond chat — they can plan, decompose tasks, execute code in isolated sandboxes, and produce real files and deliverables. Sub-agent parallelism, persistent memory, sandbox isolation — these capabilities earned it 37K+ GitHub stars, and deservedly so.
  62. ### From Agent Runtime to Production Platform
  63. DeerFlow excels as an Agent runtime and developer toolkit. OpsinTech builds on top of it to address what teams need when moving from evaluation to production:
  64. | Scenario | DeerFlow | OpsinTech Enhancement |
  65. |---|---|---|
  66. | **Team Collaboration** | Single-user mode | Multi-tenancy with `user → tenant → global` isolation |
  67. | **Access Control** | No role-based permissions | RBAC with `platform_admin` / `tenant_admin` / `tenant_member` |
  68. | **Model Configuration** | Hand-edited YAML files | 20+ provider templates in admin UI, database-backed, per-tenant assignment |
  69. | **Administration** | Command-line scripts only | Visual admin dashboards for both platform and tenant levels |
  70. | **Audit & Compliance** | No operation traceability | Full audit trail for all operations, per-tenant isolation |
  71. | **Skills & MCP** | Functional runtime, manual setup | Per-tenant management via admin UI, lifecycle tracking |
  72. | **Security Governance** | Basic sandbox isolation | User status management, mandatory password rotation, operation audit |
  73. | **Onboarding** | Configuration-heavy, steep learning curve | Docker one-command deploy, admin UI-driven setup |
  74. ### Our Approach
  75. We're not starting from scratch. DeerFlow's Agent runtime is one of the most mature in open source, and for v1.0 we chose to inherit it — then layer on what teams need to use it in production.
  76. **Short-term (v1.x)**: Keep DeerFlow's runtime, add the governance layer — multi-tenancy, RBAC, audit, admin dashboards, database-backed config, model provider templates.
  77. **Long-term (v2.x+)**: Gradually replace DeerFlow internal dependencies with our own architecture, incorporating real operations scenarios — alert ingestion, incident management, workflow orchestration, governed terminals — to form a true AI-Native Operations Platform.
  78. ## v1.0 — What We Built
  79. ### Multi-Tenancy & RBAC
  80. - **Three-tier resource isolation**: `user → tenant → global`, strict data separation
  81. - **Two admin dashboards**: Platform admin (users, tenants, audit, model templates) + Tenant admin (members, models, tools, skills)
  82. - **Auto-created personal tenant** on registration, zero manual setup
  83. - Roles: `platform_admin` / `tenant_admin` / `tenant_member`
  84. ### Model Management, Done Right
  85. - **20+ provider templates** in the admin UI — dropdown to select, auto-fills provider class, base URL, and capability flags. No LangChain class paths to memorize
  86. - Models stored in database, assigned per-tenant, with active / deprecated / retired lifecycle
  87. - Providers: OpenAI · Anthropic · DeepSeek · Azure OpenAI · Gemini · Ollama · OpenRouter · Groq · Together AI · SiliconFlow · DashScope · Zhipu · Moonshot · MiniMax · Baichuan · 01.AI · Volcengine Ark · Novita AI
  88. ### Terminal Agent
  89. - **Governed Terminal Execution**: AI-assisted command execution with security policies
  90. - **Multi-Host Asset Management**: Register and manage multiple target hosts
  91. - **Command Approval Workflow**: Security review and approval before execution
  92. - **Audit Trail**: Every command and its output is logged and auditable
  93. - **Skill Integration**: Save terminal sessions as reusable Skills
  94. ### Skill System
  95. - **Skill Editor**: Full-featured editor with Markdown instruction editing
  96. - **AI-Assisted Generation**: Describe what you want, AI generates structured instructions
  97. - **Sandbox Testing**: Test Skills in a safe mock environment before production use
  98. - **Per-Tenant Management**: Skills scoped to personal, tenant, or global levels
  99. ### Incident Management
  100. - **Alert Ingestion**: Webhook / Alertmanager integration
  101. - **Signal Analysis**: Raw alerts processed into structured signals
  102. - **Incident Lifecycle**: Track incidents from creation to resolution
  103. - **AI Analysis**: Automated incident context assembly and root cause analysis
  104. ### Audit & Security
  105. - Full audit trail for all operations, per-tenant isolation
  106. - User status management (active / suspended)
  107. - Mandatory password change on first login
  108. ### Internationalization
  109. - UI supports 4 languages: English, 中文, 日本語, 한국어
  110. - Auto-detects browser language preference with manual switcher
  111. ### Deployment & Operations
  112. - **Docker one-command deploy**: `docker compose up -d`
  113. - Artifact management: browse, preview, download all agent-generated files
  114. - Platform announcement system with tenant/role targeting
  115. ## Our Vision
  116. OpsinTech is not "DeerFlow with a dashboard." We're building a **secure, governed, AI-Native Operations Platform for production environments**.
  117. On this platform, Agents don't just chat and generate code — they operate within boundaries: permission controls, audit records, execution approvals. Starting from Agent conversations, progressively extending into alerting, incidents, workflows, and terminal execution, ultimately forming a complete chain:
  118. > **Discover → Understand → Decide → Execute → Audit**
  119. This space is almost entirely vacant in open source. That's why we need community voices.
  120. **Who we're looking for**: If you work in operations, security, compliance, or platform engineering, and you're excited by AI Agents but can't use them in production because of missing governance and security — you're exactly who we're building for. Your pain points and suggestions are OpsinTech's roadmap.
  121. ## Roadmap
  122. ```
  123. ✅ v1.0 (Current) — Governable AI Agent Platform
  124. ├─ Multi-tenancy + RBAC + Audit
  125. ├─ 20+ model provider templates, database-backed
  126. ├─ Visual admin dashboards (platform + tenant)
  127. ├─ Terminal Agent with security governance
  128. ├─ Skill System with sandbox testing
  129. └─ Docker one-command deploy
  130. 🔜 v1.1 — Smart Alerting
  131. ├─ Webhook / Alertmanager ingestion
  132. ├─ Raw Alert → Signal → Incident pipeline
  133. ├─ AI-powered summaries and context assembly
  134. └─ Incident-to-workspace context linking
  135. 🔜 v1.2 — Workflows + Terminal
  136. ├─ Event-driven workflow engine
  137. ├─ SOP templates (service restart, log collection, health checks)
  138. ├─ Governed terminal execution + audit trail
  139. └─ Full closed loop: Alert → Incident → Workflow → Terminal → Audit
  140. 📋 v2.0 — Digital Operators & Ecosystem
  141. ├─ Custom Agents: SOUL.md + tool_groups whitelist + Skill/Workflow binding
  142. ├─ Auto-route alerts to agent operators
  143. ├─ Skill marketplace: community contributions + official scenarios
  144. ├─ AI Analysis Workbench: data analysis, reports, PPT generation
  145. └─ Gradual replacement of DeerFlow internals with our own architecture
  146. ```
  147. ## Quick Start
  148. 1. **Clone and configure**
  149. ```bash
  150. git clone https://github.com/opsintech/opsintech-platform.git
  151. cd opsintech-platform
  152. make config
  153. ```
  154. Generates `config.yaml` with platform-level settings (database, sandbox, tool groups). **No model configuration needed.**
  155. 2. **Start and log in**
  156. ```bash
  157. make up
  158. ```
  159. Open http://localhost:2026. On first visit, you'll be redirected to the Setup Wizard to set your admin email and password.
  160. > You can also use `docker compose up -d`, but `make up` handles config initialization and secret generation automatically.
  161. 3. **Add models via admin UI**
  162. Log in as platform admin, go to **Settings → Models**, pick from 20+ provider templates, enter your API key.
  163. > Models are stored in the database. Do **not** configure models in `config.yaml` for production.
  164. ### Running Options
  165. **Docker production**:
  166. ```bash
  167. make up # Build images and start all services (recommended for first deploy)
  168. make up-nobuild # Start services without rebuilding images
  169. make down # Stop and remove containers
  170. make rebuild-images # Remove all OpsinTech images and rebuild from scratch
  171. ```
  172. **Local development**:
  173. ```bash
  174. make check # Verify prerequisites (Node.js 22+, pnpm, uv, nginx)
  175. make install # Install dependencies
  176. make dev # Start dev servers (with hot-reload)
  177. make stop # Stop all services
  178. ```
  179. **Docker development**:
  180. ```bash
  181. make docker-init # Pull sandbox image
  182. make docker-start # Start Docker dev services
  183. make docker-stop # Stop Docker dev services
  184. make docker-logs # View all logs
  185. ```
  186. Access: http://localhost:2026
  187. ### China Users: Preparing Images
  188. In China, pulling base images during Docker builds may fail due to network issues. Pre-pull before building:
  189. ```bash
  190. # Required images
  191. docker pull python:3.12-slim
  192. docker pull node:22-alpine
  193. docker pull nginx:alpine
  194. docker pull docker:cli
  195. # Build-stage dependency
  196. docker pull ghcr.io/astral-sh/uv:0.9.26
  197. # Optional images
  198. docker pull postgres:16-alpine # PostgreSQL mode
  199. docker pull enterprise-public-cn-beijing.cr.volces.com/vefaas-public/all-in-one-sandbox:latest # Sandbox
  200. ```
  201. For mirror accelerator setup, see the [Quick Start Guide](QUICKSTART.md#china-users-preparing-images-for-local-builds).
  202. ### Advanced
  203. #### Sandbox Mode
  204. Three execution modes: Local / Docker containers / Docker + Kubernetes. See [Sandbox Guide](backend/docs/CONFIGURATION.md#sandbox).
  205. #### MCP Server
  206. Configurable MCP servers (managed per-tenant via admin UI). Supports stdio/SSE/HTTP transports with OAuth token flows.
  207. ## Supported Models
  208. | Category | Providers |
  209. |---|---|
  210. | **Global Leaders** | OpenAI · Anthropic · DeepSeek · Azure OpenAI · Gemini |
  211. | **Aggregators** | OpenRouter · Groq · Together AI |
  212. | **Self-Hosted** | Ollama |
  213. | **China-Based** | DashScope · Zhipu · Moonshot · MiniMax · Baichuan · 01.AI · Volcengine Ark · SiliconFlow |
  214. | **Other** | Novita AI · Any OpenAI-compatible provider |
  215. ## Documentation
  216. - [5-Minute Quick Start](QUICKSTART.md)
  217. - [Configuration Guide](backend/docs/CONFIGURATION.md)
  218. - [Architecture Overview](backend/docs/ARCHITECTURE.md)
  219. - [API Reference](backend/docs/API.md)
  220. - [Contributing Guide](CONTRIBUTING.md)
  221. ## Contributing
  222. We welcome contributions — code, documentation, scenario suggestions, or real-world pain points. Open an Issue or PR.
  223. ## License
  224. MIT License. See [LICENSE](./LICENSE).
  225. ## Acknowledgments
  226. ### DeerFlow
  227. v1.0 is built on [DeerFlow](https://github.com/bytedance/deer-flow) (by ByteDance). DeerFlow's Agent runtime — LangGraph orchestration, sub-agent parallelism, sandboxed execution, persistent memory — is one of the best Agent infrastructures in open source. Deep gratitude to the DeerFlow team and community.
  228. **Our relationship with DeerFlow**: In v1.x, we inherit DeerFlow's Agent runtime and add governance. As we evolve, we'll gradually replace internal dependencies and form our own architecture. OpsinTech's long-term identity is not a DeerFlow fork — it's an independent, operations-focused AI-Native platform.
  229. ### Open-Source Community
  230. - [LangChain](https://github.com/langchain-ai/langchain)
  231. - [LangGraph](https://github.com/langchain-ai/langgraph)
  232. - [Next.js](https://nextjs.org/)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.