OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Coding Agents

Teaql Agent Kit

Teaql Agent Kit is a Python developer harness that guides an existing AI coding agent through TeaQL business-domain modeling, model evaluation and repair, application generation, and evidence-based verification.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Teaql Agent Kit — OpenViST project profile in Coding Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you have a project folder and an agent capable of reading files and running terminal commands, and want that agent to follow TeaQL's modeling-to-verification workflow.

Who it is for

  • Developers who already use a coding agent and want it to follow a model-first TeaQL application workflow.
  • Teams evaluating whether an agent can generate and verify an application from business requirements.

Documented uses

  • Guide an agent to turn a business-domain description into a semantic model and generated application.
  • Ask the agent to evaluate and repair the model before generation.
  • Have the agent exercise application behavior and report results with relevant logs and unresolved problems.
Before you choose

Requirements & limits

The repository is public and lists an MIT license. The default workflow requires network access and sends model content to the configured service.

  • The kit guides existing coding agents; it is not itself a replacement coding agent.
  • The README names Claude Code, OpenAI Codex, Cursor, GitHub Copilot and Gemini CLI and requires an agent mode that can read project files and run terminal commands; these mentions are not agent-specific compatibility test
  • Evaluation, generation and API guidance may involve TeaQL services, while a local checkout only changes where the agent reads instructions.
  • The example workflow uses Rust and SQLite, but it is presented as a prompt example rather than a guarantee of successful output.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Start a TeaQL workflow from a project prompt

Ask an existing coding agent to model a business domain, generate an application and report evidence from its work.

Before you start

  • A project folder open in an agent mode that can read project files and run terminal commands.
  • Permission for the agent to work in the project folder and run development commands.
  • Network access for the default evaluation, generation and API-guidance workflow.

Steps

  1. In the agent's chat, ask it to follow the instructions at https://github.com/teaql/teaql-agent-kit.

  2. Replace the README's sample order-management requirement with the application requirement you want to build.

  3. Request model evaluation and repair, application generation, relevant tests or runtime checks, and an evidence-backed report of actual results and remaining problems.

Expected outcome

The agent is instructed to follow TeaQL's model-first workflow and report what it actually completed, including evidence and unresolved issues.

Guide limitations

  • The workflow may require installing or updating TeaQL clients and language build tools and downloading dependencies.
  • A prompt does not guarantee success or eliminate setup and follow-up questions.
  • Model content is sent to the configured service; assess data-sharing requirements before using private business requirements.
  • Using a local checkout for instructions does not make evaluation and generation offline.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Teaql Agent KitGuide an agent to turn a business-domain description into a semantic model and generated application.CLIThe repository is public and lists an MIT license. The default workflow requires network access and sends model content to the configured service.
SpectraClarify requirements and compare approaches before proposing a change.CLI, DesktopThe README lists a macOS and Windows desktop app, and a Homebrew installation for macOS. The CLI is published through npm and requires Node.js 22.14 or newer.
Skills — michaelshimelesInstall reusable task-specific skills into a coding-agent setup.CLIThe repository README provides an npx installation command for most coding agents and describes automatic or explicit skill invocation in Claude Code.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
teaql/teaql-agent-kit · Official homepage title · retained in its source language
How we review sourcesSuggest a correction