{"data":{"slug":"eosphoros-ai-db-gpt","name":"DB-GPT","tagline":"open-source agentic AI data assistant for the next generation of AI + Data products","github_url":"https://github.com/eosphoros-ai/DB-GPT","owner":"eosphoros-ai","repo":"DB-GPT","owner_avatar_url":"https://avatars.githubusercontent.com/u/140580304?v=4","primary_language":"Python","stars":19740,"forks":2882,"topics":["agents","bgi","database","deepseek","gpt","gpt-4","hacktoberfest","llm","private","rag","security","vicuna"],"archived":false,"github_pushed_at":"2026-08-17T12:25:25+00:00","maintenance_label":"Very active","stars_delta_30d":239,"url":"https://www.graphcanon.com/tools/eosphoros-ai-db-gpt","markdown_url":"https://www.graphcanon.com/tools/eosphoros-ai-db-gpt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/eosphoros-ai-db-gpt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=eosphoros-ai-db-gpt","description":"open-source agentic AI data assistant for the next generation of AI + Data products.","homepage_url":"http://docs.dbgpt.cn","license":"MIT","open_issues":428,"watchers":143,"ai_summary":"DB-GPT is an open-source framework that leverages AI and LLMs to handle tasks involving reasoning, task planning, SQL writing/execution, and more. It integrates with various LLM services like OpenAI, Moonshot API (Kimi), and MiniMax.","readme_excerpt":"### Plan and execute\nLet AI reason through the task, write SQL and code, and execute step by step.\n\n---\n\n## Quick Start\n\nGet DB-GPT running in minutes with the one-line installer (macOS & Linux):\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh | bash\n```\n\nOr specify a profile and API key directly:\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh \\\n  | OPENAI_API_KEY=sk-xxx bash -s -- --profile openai\n```\n\nFor Kimi 2.5 via Moonshot API:\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh \\\n  | MOONSHOT_API_KEY=sk-xxx bash -s -- --profile kimi\n```\n\nFor MiniMax via the OpenAI-compatible API:\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh \\\n  | MINIMAX_API_KEY=sk-xxx bash -s -- --profile minimax\n```\n\nAlready have a local DB-GPT checkout? Reuse it instead of cloning `~/.dbgpt/DB-GPT`:\n\n```bash\nOPENAI_API_KEY=sk-xxx \\\n  bash scripts/install/install.sh --profile openai --repo-dir \"$(pwd)\" --yes\n```\n\nOr reuse your local repo with Kimi 2.5:\n\n```bash\nMOONSHOT_API_KEY=sk-xxx \\\n  bash scripts/install/install.sh --profile kimi --repo-dir \"$(pwd)\" --yes\n```\n\nOr reuse your local repo with MiniMax:\n\n```bash\nMINIMAX_API_KEY=sk-xxx \\\n  bash scripts/install/install.sh --profile minimax --repo-dir \"$(pwd)\" --yes\n```\n\nAfter installation, start the server with the generated profile config:\n\n```bash\ncd ~/.dbgpt/DB-GPT && uv run dbgpt start webserver --profile <profile>\n```\n\nThen open [http://localhost:5670](http://localhost:5670).\n\n> **Prefer to review the script first?**\n> ```bash\n> curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh -o install.sh\n> less install.sh\n> bash install.sh --profile openai\n> ```\n\n---\n\n### Install via PyPI\n\nInstall DB-GPT from PyPI and start it with a single command — no source checkout required.\n\n> **Prerequisites:** Python **3.10+** and [uv](https://docs.astral.sh/uv/getting-started/installation/) (recommended) or pip.\n\n**1. Install**\n\n```bash\n\n---\n\n### Advanced Installation\n\n\n\n\n\n\nFor Docker, local GPU models (vLLM, llama.cpp), or manual source-code setup, see the full docs:\n\n- [**Install**](http://docs.dbgpt.cn/docs/installation)\n  - [Docker](http://docs.dbgpt.cn/docs/installation/docker)\n  - [Source Code](http://docs.dbgpt.cn/docs/installation/sourcecode)\n- [**Quickstart**](http://docs.dbgpt.cn/docs/quickstart)\n- [**Application**](http://docs.dbgpt.cn/docs/operation_manual)\n  - [Development Guide](http://docs.dbgpt.cn/docs/cookbook/app/data_analysis_app_develop)\n  - [App Usage](http://docs.dbgpt.cn/docs/application/app_usage)\n  - [AWEL Flow Usage](http://docs.dbgpt.cn/docs/application/awel_flow_usage)\n- [**Debugging**](http://docs.dbgpt.cn/docs/operation_manual/advanced_tutorial/debugging)\n- [**Advanced Usage**](http://docs.dbgpt.cn/docs/application/advanced_tutorial/cli)\n  - [SMMF](http://docs.dbgpt.cn/docs/application/advanced_tutorial/smmf)\n  - [Finetune](http://docs.dbgpt.cn/docs/application/fine_tuning_manual/dbgpt_hub)\n  - [AWEL](http://docs.dbgpt.cn/docs/awel/tutorial)","github_created_at":"2023-04-13T14:52:43+00:00","created_at":"2026-07-07T17:36:33.473396+00:00","updated_at":"2026-08-18T06:01:55.05463+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"agents","name":"agents"},{"slug":"bgi","name":"bgi"},{"slug":"database","name":"database"},{"slug":"deepseek","name":"deepseek"},{"slug":"gpt","name":"gpt"},{"slug":"llm","name":"llm"}],"trust":{"provenance":{"is_fork":false,"github_id":627480054,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-18T06:01:54.310Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":1,"days_since_push":0,"last_release_at":"2026-06-18T05:24:35Z","stars_delta_30d":239,"open_issues_delta_30d":-5},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:07:42.338Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-18T06:01:54.754Z"},"deploy":{"source":"dockerfile:docker-compose.yml","self_host":true,"observed_at":"2026-08-18T06:01:54.754Z","managed_saas":false},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-18T06:01:54.754Z"},"has_docker":{"value":true,"source":"dockerfile:docker-compose.yml","observed_at":"2026-08-18T06:01:54.754Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-18T06:01:54.754Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["- You need a tool that can handle complex data processing and task automation using AI.","- Your project requires integration with multiple LLM service providers like OpenAI, Moonshot API (Kimi), or MiniMax.","- The focus of your application is on rapid development cycles for the next generation of AI + Data products, benefiting from pre-built components that DB-GPT provides."],"when_not_to_use":["- You are looking for a heavily community-customized or fine-tuned experience as,DB-GPT's flexibility might be limited compared to more customizable systems.","- Your use case strictly requires proprietary services and you seek a tool without dependency on third-party LLM services which DB-GPT inherently relies upon.","- Deployment contexts that strictly adhere to closed-source frameworks or environments where open-source software is restricted might not align well with DB-GPT’s licensing model."],"source":"enrich:decision_facts","observed_at":"2026-07-11T14:22:57.565Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"DB-GPT is an open-source framework that integrates with various LLM services, streamlining tasks from reasoning to SQL execution and planning."}]}}