# Guidance Guidance is an MIT-licensed language for controlling large language model generation with regular expressions, context-free grammars, control flow, tool use, and efficient interleaving of generation and application logic. Canonical URL: https://aiidelist.com/ide/guidance Language: en Updated: 2026-08-14 ## Overview - Category: Developer Workflow Tools - A constrained-generation library for developers who need an LLM to follow exact syntax or grammar while retaining programmable control over generation and tools. - Editor base: Python library - Platforms: Python, Local models, Hosted model APIs - Open source: Yes - Local model support: Yes - Bring your own API key: Yes ## Quick verdict Guidance is most useful when exact output syntax, token-level control, or grammars are central requirements and a developer is comfortable defining generation programs directly. ## Best for - Grammar-constrained LLM output - Reliable JSON or domain-specific formats - Local-model applications - Tool-using generation programs - Research and advanced agent control ## Strengths - Grammar constraints can guarantee syntax that post-hoc parsing cannot - Interleaving code and generation gives precise application control - Works with local and hosted model backends - MIT licensing and source access support experimentation and production adoption ## Limitations - No-code agent building - Teams needing a complete hosted runtime - Simple extraction already solved by a typed parser - Use cases where backend models cannot support efficient constraints - Constrained decoding support differs by model backend - Grammar design can become complex for large formats - Syntactic correctness does not guarantee factual correctness - The project is a developer library rather than a hosted end-user agent platform # Guidance Review Guidance is an MIT-licensed language for controlling large language model generation with regular expressions, context-free grammars, control flow, tool use, and efficient interleaving of generation and application logic. ## What Guidance Is A constrained-generation library for developers who need an LLM to follow exact syntax or grammar while retaining programmable control over generation and tools. ## Core Capabilities ### Constrained generation - Enforce regular-expression patterns - Generate against context-free grammars - Build structured responses token by token instead of repairing them afterward ### Programmable control - Interleave Python control flow and model generation - Capture generated spans and reuse variables - Compose tool calls and multi-step generation programs ### Model flexibility - Use supported local models - Connect compatible hosted APIs - Apply the same generation program across model backends where capabilities allow ## Best Use Cases - Grammar-constrained LLM output - Reliable JSON or domain-specific formats - Local-model applications - Tool-using generation programs - Research and advanced agent control ## Pricing - **Open Source:** $0 — Guidance is available under the MIT license. - **Model usage:** Provider or infrastructure cost — Costs depend on the selected hosted API or local inference stack. - **Operations:** Self-managed — Deployment, evaluation, observability, and scaling are handled by the application team. Pricing and availability can change. These details were checked against official sources on 2026-08-14. ## Advantages - Grammar constraints can guarantee syntax that post-hoc parsing cannot - Interleaving code and generation gives precise application control - Works with local and hosted model backends - MIT licensing and source access support experimentation and production adoption ## Limitations - Constrained decoding support differs by model backend - Grammar design can become complex for large formats - Syntactic correctness does not guarantee factual correctness - The project is a developer library rather than a hosted end-user agent platform ## Privacy and Operational Notes Guidance runs in the application process, but data privacy depends on the configured model backend. Local models can keep prompts on controlled infrastructure; hosted providers receive whatever context the application sends. ## Guidance Alternatives The most relevant comparison set is Instructor, DSPy, Pydantic AI. Compare products by execution model, integration surface, security controls, deployment model, maintenance burden, and total usage cost. ## Verdict Guidance is most useful when exact output syntax, token-level control, or grammars are central requirements and a developer is comfortable defining generation programs directly. ## Official Sources - [Official repository](https://github.com/guidance-ai/guidance) - [Documentation](https://guidance.readthedocs.io/) - [License](https://github.com/guidance-ai/guidance/blob/main/LICENSE) ## Features ### Constrained generation - Enforce regular-expression patterns - Generate against context-free grammars - Build structured responses token by token instead of repairing them afterward ### Programmable control - Interleave Python control flow and model generation - Capture generated spans and reuse variables - Compose tool calls and multi-step generation programs ### Model flexibility - Use supported local models - Connect compatible hosted APIs - Apply the same generation program across model backends where capabilities allow ## Pricing open-source - Open Source: $0 — Guidance is available under the MIT license. - Model usage: Provider or infrastructure cost — Costs depend on the selected hosted API or local inference stack. - Operations: Self-managed — Deployment, evaluation, observability, and scaling are handled by the application team. Pricing checked: 2026-08-14 ## Privacy and data handling Guidance runs in the application process, but data privacy depends on the configured model backend. Local models can keep prompts on controlled infrastructure; hosted providers receive whatever context the application sends. ## Alternatives - Instructor - DSPy - Pydantic AI ## Sources - [Official website](https://github.com/guidance-ai/guidance) - [Official repository](https://github.com/guidance-ai/guidance) - [Documentation](https://guidance.readthedocs.io/) - [License](https://github.com/guidance-ai/guidance/blob/main/LICENSE) Last checked: 2026-08-14 ## Update history - 2026-08-14: Added as an active constrained-generation library for structured and tool-using LLM applications.