{"id":51168132,"url":"https://github.com/alibaba/UnifiedModel","last_synced_at":"2026-07-02T20:00:40.956Z","repository":{"id":359019285,"uuid":"1230664565","full_name":"alibaba/UnifiedModel","owner":"alibaba","description":"The semantic layer that makes enterprise data understandable to AI agents — model entities and relations once, query through SPL/MCP/REST, and connect telemetry, services, and business objects in one object graph.","archived":false,"fork":false,"pushed_at":"2026-06-23T06:17:20.000Z","size":3164,"stargazers_count":188,"open_issues_count":19,"forks_count":36,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-06-23T07:18:17.016Z","etag":null,"topics":["ai-agent","aiops","cmdb","data-modeling","knowledge-graph","mcp","object-graph","observability","opentelemetry","semantic-layer"],"latest_commit_sha":null,"homepage":"https://alibaba.github.io/UnifiedModel/","language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/alibaba.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":"SUPPORT.md","governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":"NOTICE","maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-05-06T07:51:44.000Z","updated_at":"2026-06-23T06:09:59.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/alibaba/UnifiedModel","commit_stats":null,"previous_names":["alibaba/unifiedmodel"],"tags_count":4,"template":false,"template_full_name":null,"purl":"pkg:github/alibaba/UnifiedModel","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alibaba%2FUnifiedModel","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alibaba%2FUnifiedModel/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alibaba%2FUnifiedModel/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alibaba%2FUnifiedModel/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alibaba","download_url":"https://codeload.github.com/alibaba/UnifiedModel/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alibaba%2FUnifiedModel/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35060913,"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":"2026-07-02T02:00:06.368Z","response_time":173,"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":["ai-agent","aiops","cmdb","data-modeling","knowledge-graph","mcp","object-graph","observability","opentelemetry","semantic-layer"],"created_at":"2026-06-26T22:00:19.665Z","updated_at":"2026-07-02T20:00:40.951Z","avatar_url":"https://github.com/alibaba.png","language":"Go","funding_links":[],"categories":["AIOps Platforms \u0026 Frameworks","AI for *Ops"],"sub_categories":["Full-Stack AIOps Platforms","AIOps Platforms \u0026 Frameworks"],"readme":"# UModel\n\n[![CI](https://github.com/alibaba/UnifiedModel/actions/workflows/ci.yml/badge.svg)](https://github.com/alibaba/UnifiedModel/actions/workflows/ci.yml)\n![Go 1.22+](https://img.shields.io/badge/Go-1.22%2B-00ADD8)\n![Node 22+](https://img.shields.io/badge/Node.js-22%2B-339933)\n![License](https://img.shields.io/badge/License-Apache--2.0-blue)\n\n中文版本：[README_CN.md](README_CN.md)\n\nUModel (Unified Model) is a vendor-neutral semantic runtime for enterprise AI, data governance, and operational intelligence. It turns fragmented schemas, entities, business objects, telemetry links, and topology relations into workspace-scoped graph context that humans, systems, and AI agents can understand and use through one local service.\n\nWith UModel, you can:\n\n- Author and import model packs that define enterprise objects, operational objects, datasets, links, storage, and topology semantics.\n- Query models, entities, and topology through one SPL surface: `.umodel`, `.entity`, and `.topo`.\n- Explore the workspace through a local Web UI.\n- Connect agent clients through AgentGateway and MCP.\n- Use public REST, CLI, and SDK contracts without depending on server internals.\n\n## Demo\n\n\u003cvideo src=\"https://github.com/user-attachments/assets/3cdc72de-2f78-495c-baf9-7066c1d9792f\" controls\u003e\u003c/video\u003e\n\nAn AI agent reads across the object graph in the `quickstart-multidomain` workspace (90 seconds): it discovers services, walks cross-domain topology, and pulls metrics and logs through model-scoped query plans, without hand-writing a single query.\n\n## Why UModel\n\n- Accelerate enterprise AI at scale. A unified semantic standard helps AI models understand data meaning across platforms, departments, tools, and domains, improving the path to intelligent operations, customer service, analytics, prediction, and agent workflows.\n- Reduce data governance cost. A shared language for multi-source enterprise data frees data teams from repetitive metric alignment, field translation, and context reconstruction, so more effort goes into extracting value from data.\n- Preserve vendor neutrality and choice. UModel is independent of any single platform, data tool, observability stack, or AI vendor, helping organizations avoid semantic lock-in while building digital infrastructure.\n- Build an enterprise semantic operating system. UModel moves beyond a passive data dictionary toward a live, programmable semantic runtime that AI agents can query, reason over, and use as shared context for future multi-agent collaboration.\n\n## Project Scope\n\nThis repository includes the local UModel service, `umctl` CLI, MCP server, OpenAPI contract, React Web UI, generated SDK assets, example packs, Docker/Compose assets, and test suites.\n\nThe open-source core focuses on local operation, public contracts, semantic modeling, agent integration, and contributor-friendly extension points. Cloud-hosted control planes, multi-tenant authorization, Aliyun internal frontend packages, and domain-specific read APIs outside Query Service are outside the public core.\n\n## Five-Minute Quick Start\n\nRequirements:\n\n- Go 1.22 or newer.\n- Make.\n- Node.js 22 or newer for the Web UI.\n- pnpm 9 or newer is preferred; `corepack` or `npm exec` fallback is supported by the Makefile.\n\nCheck the local toolchain:\n\n```bash\nmake check-env\n```\n\nStart the API and Web UI with a preloaded demo workspace:\n\n```bash\nmake quickstart\n```\n\n`make quickstart` starts a local API, starts the Web UI, preloads the `demo` workspace with `GRAPHSTORE=memory`, and leaves no local demo data behind after the process stops.\n\nNext steps:\n\n- Open `http://localhost:5173`, select `demo`, and inspect the workspace through Explorer, Query, Data Store, and Agent views.\n- Integrate an agent through AgentGateway or MCP. Start with `umctl agent discover demo`, then connect an MCP client through `umodel-mcp`.\n- Query models, entities, and topology through CLI or REST using Query Service.\n\nDetailed flows:\n\n- [Quick Start](docs/en/getting-started/quickstart.md)\n- [Web UI Guide](docs/en/guides/web-ui.md)\n- [Query Service Guide](docs/en/guides/query-service.md)\n- [MCP Reference](docs/en/reference/mcp.md)\n\nStop local services:\n\n```bash\nmake stop-all\n```\n\n## Agent Skills\n\nLoadable skills let a skill-aware agent drive UModel directly — read entities, relations, topology, and the model itself, then run model-guided root-cause analysis over the object graph. In Claude Code, install both skills in one command:\n\n```\n/plugin marketplace add alibaba/UnifiedModel\n/plugin install umodel@unifiedmodel\n```\n\nQoder, Codex, Cursor, and other agents load the same two `SKILL.md` files — copy them into the agent's skills directory (`.qoder/skills/` for Qoder, `.agents/skills/` for Codex, `.claude/skills/` for Claude Code). See [Agent Skills](skills/README.md) for the catalog and [the skills quickstart](skills/QUICKSTART.md) for per-agent install.\n\n## Architecture\n\n![UModel architecture](images/architecture.png)\n\nUModel runs as a local service around one workspace-scoped object graph:\n\n- Model packs define the object vocabulary: EntitySets, datasets, links, storage, and relation semantics.\n- EntityStore writes runtime entities and topology relations that instantiate the model.\n- Query Service is the unified read surface for `.umodel`, `.entity`, and `.topo`.\n- AgentGateway and MCP expose discovery, resources, query examples, and safe tools for agent clients.\n- Web UI, CLI, REST, and SDK clients operate against the same public contracts.\n\nArchitecture details:\n\n- [Architecture Overview](docs/en/architecture/overview.md)\n- [Runtime Flow](docs/en/architecture/runtime-flow.md)\n- [Query And Agent Architecture](docs/en/architecture/query-and-agent.md)\n\n## Documentation\n\nStart with the bilingual documentation index: [docs/README.md](docs/README.md).\n\n| Area | Entry |\n|---|---|\n| Getting started | [Installation](docs/en/getting-started/installation.md), [Quick Start](docs/en/getting-started/quickstart.md) |\n| Concepts | [Concepts Index](docs/en/concepts/index.md), [Object Graph Semantic Layer](docs/en/concepts/object-graph-semantic-layer.md) |\n| Guides | [Model Authoring](docs/en/guides/model-authoring.md), [Entity And Relation Writes](docs/en/guides/entity-relation-writes.md), [Query Service](docs/en/guides/query-service.md), [Web UI](docs/en/guides/web-ui.md), [SDK And Client Guide](docs/en/guides/sdk-clients.md) |\n| Architecture | [Architecture Overview](docs/en/architecture/overview.md), [Runtime Flow](docs/en/architecture/runtime-flow.md), [Query And Agent Architecture](docs/en/architecture/query-and-agent.md) |\n| Reference | [CLI](docs/en/reference/cli.md), [MCP](docs/en/reference/mcp.md), [REST OpenAPI](api/openapi/openapi.yaml), [MCP Tool And Resource Schema](api/mcp/tools.schema.json) |\n| Examples | [Multi-Domain Quickstart Example Pack](examples/quickstart-multidomain/README.md), [Incident Investigation Demo (AI agent)](examples/incident-investigation/README.md), [Service Localization Demo (AI agent)](examples/service-localization/README.md) |\n| Agent Skills | [UModel Agent Skills](skills/README.md) — loadable skills for MCP/CLI agents: read entity/relation/model data and run model-guided root-cause analysis |\n| Deployment | [Docker And Compose](deployments/README.md) |\n\nChinese documentation: [docs/zh/README.md](docs/zh/README.md).\n\n## Development\n\nInstall local dependencies:\n\n```bash\nmake install-env\n```\n\nBuild:\n\n```bash\nmake build\n```\n\nRun focused checks:\n\n```bash\nmake guard\nmake test-service\nmake verify\nmake example-validate\n```\n\nRun the local CI gate:\n\n```bash\nmake ci\n```\n\nGenerated Go and Python model SDKs live under `sdk/`. The Java SDK currently remains under `generated/java/`. The minimal Go service client lives under `sdk/go/service` and wraps public REST contracts.\n\n## GraphStore Providers\n\nRuntime GraphStore providers are selected with `--graphstore`.\n\n| Provider | Typical use |\n|---|---|\n| `memory` | Ephemeral local tests and quickstart demos. Data is lost after process exit. |\n| `file.memory` | JSON persistence under `--data`. Default for `make dev`, Docker, and Compose. |\n| `local.ladybug` | Ladybug-backed environments. Requires `-tags ladybug` and a local Ladybug runtime. |\n\nProvider details: [GraphStore Providers](docs/en/graphstore-providers.md).\n\n## Governance And Support\n\n- License: [Apache-2.0](LICENSE)\n- Contributions: [CONTRIBUTING.md](CONTRIBUTING.md)\n- Security policy: [SECURITY.md](SECURITY.md)\n- Support channels: [SUPPORT.md](SUPPORT.md)\n- Code of conduct: [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md)\n- Changelog: [CHANGELOG.md](CHANGELOG.md)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falibaba%2FUnifiedModel","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falibaba%2FUnifiedModel","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falibaba%2FUnifiedModel/lists"}