<2-3 sentences summarising what the project addresses and solves, the target audience, and the benefit.> TeaQL Agent Kit provides a framework for deterministic AI-driven code generation by constraining AI agents with semantic models, typed query languages, and generated domain APIs. It targets AI coding agents and developers seeking to improve consistency and reliability in AI-assisted software development, offering a structured approach to building applications.

How It Works

TeaQL enforces "Semantic Guardrails for AI Coding" by shifting from free-form requirements to a domain-modeling-first approach. AI agents work with a semantic model (KSML), a typed query language, and generated domain APIs. This constrains generated code by domain metadata, typed expressions, and tested runtime behavior, ensuring consistency and reducing AI-induced errors.

Quick Start & Requirements

• Java: Requires TeaQL Maven plugin version 0.1.10 or newer from https://nexus.teaql.io/repository/maven-releases/. Use fully qualified coordinates (e.g., mvn io.teaql:teaql-maven-plugin:0.1.10:gen-lib).
• Rust: Requires cargo-teaql version 2.0.0 or newer from crates.io. Install with cargo install cargo-teaql, then run cargo-teaql install-links.
• AI Agents: Agents should follow instructions in AGENTS.md and use provided prompts for modeling and code generation.
• Documentation: Links to specific playbooks and guides are provided within the README for detailed workflows.

Highlighted Details

• Enables deterministic execution for non-deterministic AI coding agents.
• Supports both Java (Spring Boot) and Rust code generation from a single semantic model.
• Provides generated typed APIs for querying, filtering, and multi-level data loading.
• Facilitates Domain-Driven Design (DDD) with typed behavior methods and chainable updates.

Maintenance & Community

The README describes TeaQL as a family of repositories, with teaql-agent-kit serving as the public entry point. It outlines a structured workflow for AI agents and developers but does not detail specific community channels, active contributors, or sponsorship information.

Licensing & Compatibility

The provided README does not explicitly state the software license. This requires clarification for adoption decisions, especially concerning commercial use or integration with closed-source projects.

Limitations & Caveats

The project is presented as an "entry point" for the TeaQL ecosystem, with workflows described as "evolving." The "playground mode" is intended for demos and evaluations, and schema creation/migration are explicit deployment decisions outside this mode. The lack of explicit licensing information is a significant caveat.