# Choosing an SDK

Source: https://docs.littlebigbrain.com/sdks/overview/

Every client below speaks the **same HTTP API** and authenticates with the same
[stack API key](https://docs.littlebigbrain.com/start/authentication/). You can load data with one client and
query with another, on the same graph.

The first-party SDKs (`@littlebigbrain/client`, `lbb`) are generated from one
API contract. Their shapes match across languages.

## Comparison

| SDK / surface | Package | Runtime | Use it when… |
| --- | --- | --- | --- |
| [TypeScript client](https://docs.littlebigbrain.com/sdks/typescript/) | `@littlebigbrain/client` | Node 18+, browsers, edge workers | You're building a JS/TS app, API route, or edge function |
| [Python client](https://docs.littlebigbrain.com/sdks/python/) | `littlebigbrain` (imports as `lbb`) | Python 3.10+ (`httpx` + `pydantic`) | Scripts, notebooks, data pipelines |
| [MCP server](https://docs.littlebigbrain.com/sdks/mcp/) | `@littlebigbrain/mcp` | Node (stdio) or hosted HTTP | You want an AI agent (Claude, Cursor, Codex) to search, query and write the graph |
| [HTTP API](https://docs.littlebigbrain.com/sdks/http-api/) | n/a | Any language | No SDK for your language, or you want the native SPARQL Protocol |

## The same flow everywhere

Whatever you pick, the flow is the same:

1. Declare your types and links. See [Load your data](https://docs.littlebigbrain.com/start/load-data/).
2. Write records as JSON.
3. Turn on search for a type.
4. Search by meaning, then follow links with SPARQL.

The [quickstart](https://docs.littlebigbrain.com/start/quickstart/) shows the flow in TypeScript, Python and
cURL. If your data is RDF already, [load it as it is](https://docs.littlebigbrain.com/guides/load-rdf/).

Standard SPARQL tools need no SDK. Each stack serves the SPARQL 1.1 Protocol at
`/sparql`. YASGUI, Protégé and RDFLib's `SPARQLWrapper` connect with the
endpoint URL and a bearer token.

## Local development and legacy tools

Run `lbb-server` locally and connect the same HTTP clients to its local URL.
For exact local queries, `lbb-testctl query sparql` also reads RDF with
SPARQL. Class-declared embeddings use `/v1/embeddings*` and `/v1/search`,
as shown in [Search by meaning](https://docs.littlebigbrain.com/guides/search-by-meaning/).

The older `lbb-testctl graph search`, `multi-search`, `full-text` and
record-index `embeddings` commands, and Python's `LbbLocalClient` search
methods, are deprecated for new integrations. Their existing execution and
arguments remain unchanged; no removal version is set. Their BM25, fusion
and explicit record-vector contracts are different from class embedding
search and have no automatic conversion.

## Pick one

- [TypeScript](https://docs.littlebigbrain.com/sdks/typescript/): Dependency-free fetch wrapper; typed request/response shapes.
- [Python — lbb](https://docs.littlebigbrain.com/sdks/python/): Sync + async, dict or typed Pydantic models.
- [MCP server — @littlebigbrain/mcp](https://docs.littlebigbrain.com/sdks/mcp/): Task-shaped tools for agents; local stdio or hosted OAuth.
- [HTTP API & SPARQL](https://docs.littlebigbrain.com/sdks/http-api/): REST plus the native SPARQL 1.1 Protocol endpoint.