{"id":"eosphoros-ai-db-gpt","name":"DB-GPT","af_score":38.8,"security_score":46.0,"reliability_score":27.5,"what_it_does":"DB-GPT is an open-source agentic AI data assistant that connects to data sources (databases, CSV/Excel, documents/knowledge bases), uses an LLM to generate SQL and Python/code for analysis, executes workflows (including reusable “skills”) and produces reports/charts, with an emphasis on sandboxed execution for code/tools.","best_when":"You want a self-hosted, agentic LLM + data stack that can write/run SQL and code and generate analysis artifacts, and you can manage infrastructure, credentials, and sandboxing appropriately.","avoid_when":"You cannot control or monitor tool/code execution, database write permissions, or secret handling; or you need a strictly API-first product with fully specified machine-readable interfaces (OpenAPI/SDKs) and strong guarantees about error recovery/idempotency.","last_evaluated":"2026-03-29T13:16:20.007882+00:00","has_mcp":false,"has_api":true,"auth_methods":["Interactive setup wizard for selecting LLM provider and entering API key","Environment variables for LLM provider API keys (e.g., OPENAI_API_KEY, MOONSHOT_API_KEY, MINIMAX_API_KEY)"],"has_free_tier":false,"known_gotchas":["Agentic SQL/code generation can have side effects if database permissions allow writes; ensure read-only DB accounts and restrict tool capabilities.","Sandboxed execution is mentioned, but exact isolation guarantees and limits are not specified in the provided excerpt; validate resource/time/network/file controls.","LLM provider selection implies variable reliability and rate limiting behavior depending on upstream APIs; plan retries/backoff outside the system if not documented."],"error_quality":0.0}