OpenViSTAI · Agents · Blockchain · Crypto
Menu
Coding Agents

GRACE Marketplace and CLI

A public TypeScript repository that packages GRACE Agent Skills and an optional CLI for contract-first AI code generation. It is a distribution repository, not an end-user application.

Independent OpenViST project profile, based on linked sources.

GRACE Marketplace and CLI — 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 AI-generated software changes need durable project context, explicit change specifications, planned assertions, and log-driven verification.

Who it is for

  • Developers using AI coding agents
  • Teams seeking contract-driven code-generation workflows
  • Users of Claude Code, Codex CLI, or Kilo Code

Documented uses

  • Bootstrap a .grace project model
  • Create and plan explicit software changes
  • Navigate project knowledge-graph artifacts before code changes
  • Lint contracts, assertions, scopes, and verification artifacts
  • Check generated changes against documented baselines and final conditions
Before you choose

Requirements & limits

The repository is public and open source under the MIT license. The optional CLI requires Bun on PATH.

  • Whether your coding environment is Claude Code, Codex CLI, or Kilo Code
  • Whether your project benefits from a durable .grace XML model
  • Whether you need assertions, scopes, graph navigation, and verification gates
  • Language coverage: TypeScript and JavaScript have bundled semantic analysis; Python and Dart require their runtimes; several other languages receive structural checks only
  • Whether you need the optional CLI in addition to the packaged skills

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

Set up a GRACE 4 project and run initial checks

Create the GRACE project model, prepare a change, and perform the documented pre-execution checks.

Before you start

  • A supported coding environment for the GRACE skills.
  • Bun on PATH if using the optional CLI.
  • A project path for the GRACE 4 artifacts.

Steps

  1. Run $grace-init to create .grace.

  2. Fill the .grace/context artifacts with your agent.

  3. Run $grace-spec for a change, then $grace-plan after spec approval.

  4. Run grace lint --path /path/to/project --assertions current, followed by the documented baseline lint and grace status checks.

Expected outcome

A GRACE 4 project with context, an approved change plan, and documented pre-execution validation.

Guide limitations

  • The evidence documents setup and checks but does not show a complete execution result.
  • Existing GRACE 3 projects should use $grace-migrate and review its report before writing GRACE 4 artifacts.
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
GRACE Marketplace and CLIBootstrap a .grace project modelCLIThe repository is public and open source under the MIT license. The optional CLI requires Bun on PATH.
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

Source record details
Source availability
Active
Sources checked
30 September 2026
Original website title
osovv/grace-marketplace · Official homepage title · retained in its source language