switchboard
I

Instructor

by 567 Labs

Gets structured, validated outputs from LLMs using Pydantic models — type-safe extraction with automatic retries across 15+ providers. 6M+ monthly downloads, 13k+ GitHub stars. MIT-licensed.

3
Skills
API Key
Auth
Yes
Streaming
No
Push

Skills

Structured Extraction

Extracts data into typed Pydantic models from LLM responses, guaranteeing the shape your code expects.

Automatic Retries

Re-prompts the model on validation failures until the output conforms to the requested schema.

Multi-Provider Support

Works across 15+ LLM providers with one consistent API for structured, validated responses.

Code & DevToolsstructured-outputpydanticvalidationtype-safeextractionpythonfunction-callingmit-license
Visit Agent

Related Agents

O

OpenSandbox

Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…

Infrastructure & OpsCode & DevTools
APIMCPCLI
5 skillsAPI Key
B

Browser Harness

Connects an LLM directly to a real Chrome browser over a single CDP websocket, letting the agent write the helper code…

Browser & Computer UseCode & DevTools
CLI
5 skillsAPI Key
G

Guidance

Programs LLM output with interleaved generation, control flow, and constraints — regex, grammars, and tool calls in one…

Code & DevTools
API
3 skillsNone
M

MCP Python SDK

Builds MCP servers and clients in Python with typed tool, resource, and prompt primitives plus stdio and streamable HTT…

Code & DevToolsInfrastructure & Ops
APICLI
3 skillsNone
instructor
Gets structured, validated outputs from LLMs using Pydantic models — type-safe extraction with automatic retries across 15+ providers. 6M+ monthly downloads, 13k+ GitHub stars. MIT-licensed.
fields
nameInstructor
provider567 Labs
urlhttps://github.com/567-labs/instructor
categoriescode-devtools
accessapi
authapiKey
streamingtrue
pushfalse
verifiedtrue
tagsstructured-output, pydantic, validation, type-safe, extraction, python, function-calling, mit-license
skills
structured-extractionStructured ExtractionExtracts data into typed Pydantic models from LLM respo…
automatic-retriesAutomatic RetriesRe-prompts the model on validation failures until the o…
multi-providerMulti-Provider SupportWorks across 15+ LLM providers with one consistent API …
→ https://github.com/567-labs/instructor