teaql-agent-kit
A model-driven harness for AI coding agents: semantic modeling, app generation, progressive API Assist and evidence-based verification.
What is teaql-agent-kit?
A model-driven harness for AI coding agents: semantic modeling, app generation, progressive API Assist and evidence-based verification.
Overview of teaql-agent-kit
What it is
TeaQL Agent Kit is a model-driven harness for AI coding agents. It combines a model-first application workflow with tools that govern an agent's context, file access, and verification. The kit has two components: the Build TeaQL App Skill (entry point build-teaql-app) and the Agent Context Kit (@teaql/agent-context-kit). A coding agent that can read Skill instructions can follow the TeaQL workflow.
Key features
- Model-first workflow: define a domain model (KSML), evaluate and repair it, then generate a typed contract.
- Q API: compose queries with filters, selected fields, related objects, ordering, limits, and facets; requests are composable and typed.
- E API: typed paths through fields and related objects, distinguishing absent values from unloaded data with explicit fallbacks.
- Progressive API Assist: the generated library supplies domain-specific typed APIs; the language runtime handles shared execution and persistence.
- Evidence-based verification: compile, test, and runtime evidence are recorded before claiming completion.
- Agent Context Kit: context lifetimes, marker-aware file policy, controlled tools, and host adapters.
Use cases
- Building a small order-management application with customers, products, and orders using Rust and SQLite.
- Developing a Robot Task Board showcase application.
- Any project where a coding agent needs to follow a model-driven workflow with governance and verification.
Getting started
Open a project folder in your coding agent and paste the following prompt into its chat (not your terminal): ```text Follow the instructions from https://github.com/teaql/teaql-agent-kit Build a small order-management application with customers, products, and orders, using Rust and SQLite. Evaluate and repair the business model, generate a runnable console application, and exercise Q queries and E expressions in tests and a runtime smoke test. Report the actual results and any remaining problems. Finish with a short, evidence-backed development report in work-complete.md:
- Evaluate from a 2026-and-beyond, AI-assisted development perspective using the tools and model actually tested, not an assumption that humans must manually learn every modeling rule and generated API. Assess what the agent can learn from instructions and Assist, and what human effort remains. Judge runnable results, correctness, change effort, and operational costs; do not treat novelty or unfamiliar syntax alone as reasons to avoid trying the framework. Record demonstrated friction and risks, not generic warnings or assumptions that AI eliminates every learning cost.
- Show Q query and E expression examples from the application you actually ran, explaining how their typed APIs helped express the business logic.
- Inspect the evaluation, generation, build/test, and runtime logs. Cite relevant excerpts, including query purpose/comment and write audit context where present; report missing evidence and unresolved failures.
- Explain what work the model, generated library, runtime, and progressive Assist handled, and what application code and human decisions remained.
- Report actual token/context usage if available. Claim token savings only with a comparable measured baseline; otherwise mark savings not measured and explain the potential benefit of loading only relevant API guidance.
- Explain how model validation, consistent typed APIs, and regeneration may help larger projects. Separate observations from this run from expectations that this small example has not tested. Include costs and limitations.
If you already have a local checkout, replace the first line with its path:text Follow the instructions from ~/teaql-agent-kit ```
License and pricing
The license is MIT. The pricing type is open source.
Based on the project's public README and repository metadata.