Embedded libSQL/SQLite databases with optional Turso Cloud edge replication
Turso documents libSQL—an open-source SQLite fork—and the Turso CLI (`tursodb`) at docs.turso.tech for embedded, local-first SQLite databases with optional Turso Cloud hosting for multi-region replication. Official guides cover installing the CLI (`curl -sSL tur.so/install | sh`), opening `.db` files or `:memory:` databases, schema migrations, and vector search extensions described in the Turso documentation index. Turso Cloud adds managed groups, database tokens, and HTTP/libSQL remote URLs provisioned through the Turso dashboard and `turso` CLI commands (`turso db create`, `turso db tokens create`) per quickstart pages.
Use cases
- Shipping offline-capable agents that persist state in embedded SQLite files
- Replicating lightweight app databases to Turso Cloud regions for low-latency reads
- Prototyping RAG or catalog features with local vector tables before scaling hosted replicas
- Teaching teams libSQL migrations without standing up full Postgres clusters
- Pairing Turso MCP with coding agents for schema-aware SQL iteration
Key features
- Local-first SQLite-compatible storage via `tursodb` and libSQL per Turso CLI documentation
- Optional Turso Cloud replication with database URLs and auth tokens managed in the dashboard/CLI
- Built-in MCP server mode (`tursodb path/to.db --mcp`) documented for agent database tooling
- Vector search and schema tooling described in Turso docs for AI-adjacent app stacks
- Git-friendly single-file databases suitable for edge and mobile deployments
Who Is It For?
- Developers building edge or mobile apps with SQLite ergonomics
- Platform engineers evaluating lightweight state stores for agent workflows
- Teams migrating from file-based SQLite to managed Turso Cloud groups
Frequently Asked Questions
- Is Turso only a hosted cloud database?
- No—Turso documents open-source embedded libSQL via the CLI plus optional Turso Cloud hosting; many workflows start with local `.db` files.
- How do agents connect to Turso databases?
- Turso documents a built-in MCP mode on `tursodb --mcp` and Turso Cloud URLs/tokens for remote libSQL clients—see docs.turso.tech agent/MCP sections.
- Where are pricing details?
- Turso publishes Turso Cloud plan tiers at turso.tech/pricing; embedded libSQL usage is open source without cloud fees.
Related
Related
3 Indexed items
Baseten
Baseten documents a training and inference platform at docs.baseten.co where teams deploy models via the open-source Truss framework or call hosted Model APIs without standing up infrastructure. Config-only Truss deployments point at Hugging Face checkpoints, select GPU resources, and engines such as TensorRT-LLM; `truss push` builds optimized containers and exposes OpenAI-compatible sync endpoints like `https://model-{model_id}.api.baseten.co/environments/production/sync/v1`. Custom architectures use a Truss `Model` class with `load` and `predict` in `model.py`. Model APIs provide immediate OpenAI-SDK-style access to catalog models (DeepSeek, Qwen, GLM, and others listed in docs) using `BASETEN_API_KEY`.
AssemblyAI
AssemblyAI documents Voice AI APIs at assemblyai.com/docs where developers transcribe and analyze audio via REST at `https://api.assemblyai.com` and real-time WebSockets at `wss://streaming.assemblyai.com` (EU pre-recorded host `api.eu.assemblyai.com` per cloud residency docs). Pre-recorded transcription requires an explicit `speech_models` array on every `POST /v2/transcript` request—docs recommend `universal-3-pro` with `universal-2` fallback for 99-language coverage. The platform also publishes a Voice Agent API for speech-to-speech agents, Speech Understanding features (diarization, sentiment, summarization), Guardrails, and an LLM Gateway to run frontier models on transcripts.
Fireworks AI
Fireworks AI documents a REST platform at docs.fireworks.ai where developers call language, image, and embedding models with Bearer API keys from the dashboard or `firectl api-key create`. Models use globally unique IDs such as `accounts/<account>/models/<model-id>` and can be served via serverless inference for popular open weights (for example Llama 3.1 70B listed on fireworks.ai/models) or private dedicated GPU deployments for custom base models and LoRA addons. Official docs distinguish serverless per-token billing with best-effort uptime from dedicated deployments billed per GPU-second with private capacity, and state that prompts and generated outputs are not logged except for documented exceptions such as the FireFunction model or opt-in advanced features.