switchboard
G

Guidance

by guidance-ai

Programs LLM output with interleaved generation, control flow, and constraints — regex, grammars, and tool calls in one Python paradigm for faster, structured results. 21k+ GitHub stars, MIT-licensed.

3
Skills
None
Auth
Yes
Streaming
No
Push

Skills

Interleaved Generation

Mixes prompting, generation, and program logic in one flow so you steer the model step by step.

Constraint Enforcement

Restricts output with regex and context-free grammars to guarantee well-formed, structured results.

Token Efficiency

Reuses key-value caches and avoids redundant tokens to cut latency and cost on structured prompts.

Code & DevToolsconstrained-generationcontrol-flowgrammarregexstructured-outputpythonmit-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
I

Instructor

Gets structured, validated outputs from LLMs using Pydantic models — type-safe extraction with automatic retries across…

Code & DevTools
API
3 skillsAPI Key
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
guidance
Programs LLM output with interleaved generation, control flow, and constraints — regex, grammars, and tool calls in one Python paradigm for faster, structured results. 21k+ GitHub stars, MIT-licensed.
fields
nameGuidance
providerguidance-ai
urlhttps://github.com/guidance-ai/guidance
categoriescode-devtools
accessapi
authnone
streamingtrue
pushfalse
verifiedtrue
tagsconstrained-generation, control-flow, grammar, regex, structured-output, python, mit-license
skills
interleaved-generationInterleaved GenerationMixes prompting, generation, and program logic in one f…
constraint-enforcementConstraint EnforcementRestricts output with regex and context-free grammars t…
token-efficiencyToken EfficiencyReuses key-value caches and avoids redundant tokens to …
→ https://github.com/guidance-ai/guidance