Savvina AI
savvina.ai
What it is
Savvina AI turns plain-English questions into SQL and returns database results within the customer’s own environment. It supports follow-up queries, validates SQL as read-only, and adds LIMIT clauses automatically. Results can appear in eight chart types, from bar and line charts to gauges and numeric displays. The product lists 22 data sources, including PostgreSQL, BigQuery, Snowflake, MongoDB, Amazon S3, and Google Cloud Storage. Customers bring their own LLM provider; listed choices include Anthropic, OpenAI, Google, Ollama, OpenRouter, and vLLM. Plans run on customer infrastructure through Docker. Savvina says the LLM receives schema details rather than query results; users can exclude schemas, tables, or columns from prompts, and sensitive values are masked in results. Database passwords and API keys are encrypted at rest. The free Community plan is limited to one user and PostgreSQL and MySQL. Paid plans start at €39/mo, with no free trial. Enterprise pricing is custom and includes multiple deployments and air-gapped licenses.
Spec sheet
- Purpose
- Savvina AI turns plain-English questions into SQL and returns database results within the customer’s own environment.Read 7 Oct 2026 · savvina.ai
- Intended users
- The maker describes use by operations, data, engineering, finance, healthcare, HR, and other teams that need analytics while keeping data in-house.Read 7 Oct 2026 · savvina.ai
- Deployment
- All plans run on the customer’s own infrastructure via Docker, and the pricing page says Savvina does not touch customer data.Read 7 Oct 2026 · savvina.ai
- Security
- Savvina says query results are never sent to external models and that the LLM receives schema information rather than query results.Read 7 Oct 2026 · savvina.ai
- Support
- Support ranges from GitHub community support on Community to dedicated support on Enterprise.Read 7 Oct 2026 · savvina.ai
- Air-gapped use
- Enterprise includes air-gapped deployment with offline-signed licenses; the Community Edition makes no external calls except to the configured LLM provider API.Read 7 Oct 2026 · savvina.ai
- Credentials
- Database passwords and API keys are Fernet-encrypted at rest, with plaintext decrypted into memory when a query is dispatched.Read 7 Oct 2026 · savvina.ai
- Data sources
- The product lists 22 data sources, including PostgreSQL, BigQuery, Snowflake, MongoDB, Amazon S3, and Google Cloud Storage.Read 7 Oct 2026 · savvina.ai
- License limit
- The pricing FAQ says one license can be used for one deployment; multiple deployments are covered by Enterprise.Read 7 Oct 2026 · savvina.ai
- LLM providers
- Customers bring their own LLM, with listed providers including Anthropic, OpenAI, Google, Ollama, OpenRouter, and vLLM.Read 7 Oct 2026 · savvina.ai
- Privacy controls
- Users can exclude schemas, tables, and columns from LLM prompts, and sensitive values are masked in returned results.Read 7 Oct 2026 · savvina.ai
- Querying
- It supports multi-turn natural-language querying with read-only SQL validation and automatically injected LIMIT clauses.Read 7 Oct 2026 · savvina.ai
- Trial and evaluation
- The pricing page says paid plans have no free trial, while production evaluations are arranged with Savvina and use an evaluation license.Read 7 Oct 2026 · savvina.ai
- Visualizations
- Results can be shown in eight chart types, including bar, line, area, pie, scatter, combo, number, and gauge.Read 7 Oct 2026 · savvina.ai
Plans and prices
Strong points and limits
Strong points
- Runs on customer infrastructure via Docker.
- Supports 22 data source types across paid tiers.
- Read-only SQL validation and automatic LIMIT clauses.
- Users can exclude schema details from LLM prompts.
Limits
- Paid plans have no free trial.
- Customers must bring their own LLM provider.
- Community is limited to one user and two database types.
- One license covers one deployment.
Who it suits
Savvina AI suits teams that need analytics while keeping data in-house, including operations, data, engineering, finance, healthcare, and HR teams. It may fit organizations that can provide their own LLM and run the software on their infrastructure.
Verdict
Savvina AI combines conversational querying, charts, and controls intended to keep database results within the customer environment. Check the Community limits, provider requirements, deployment licensing, and paid-plan costs before selecting a tier.
Where Specifiction places it
- AI SQL Generators#6 of 198.0