OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Infrastructure

AI Devkit

AI Devkit is a local-first control plane for configuring, supervising and coordinating multiple AI coding agents. It combines shared project configuration, a live terminal session console, cross-agent messaging, local SQLite memory retrieval and composable engineering skills.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

AI Devkit — OpenViST project profile in Agent Infrastructure.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use AI Devkit when coding-agent work has expanded beyond one isolated assistant and requires a shared operating model, session visibility, local project memory or coordination between agents.

Who it is for

  • Developers coordinating multiple AI coding agents in one project.
  • Teams that need shared agent configuration and project-local workflow files.
  • Engineers managing long-running sessions, review loops or handoffs between agents.

Documented uses

  • Reconcile agent configuration, skills and MCP setup from one project-level configuration file.
  • List and supervise running agent sessions through a terminal dashboard.
  • Send prompts, logs or test output to active agents and agent groups.
  • Store and retrieve project decisions, conventions and fixes locally.
  • Apply reusable requirements, planning, testing, review and verification workflows.
Before you choose

Requirements & limits

The repository is public, identifies Apache-2.0 licensing and provides the documented `npx ai-devkit@latest init` entry point.

  • The project is infrastructure for supported coding agents rather than a standalone coding assistant.
  • The configuration model is project-local and can be reviewed and committed with repository files.
  • Memory is stored in local SQLite and retrieved through CLI and MCP integration.
  • The live console and messaging commands are useful when agents run across multiple sessions or providers.
  • The lifecycle skills extend beyond orchestration into planning, implementation, testing, review and verification.

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

Initialize AI Devkit in a project

Create project-local configuration, selected agent integrations, memory wiring and lifecycle documentation areas.

Before you start

  • A project in which to run the initialization command.
  • Node.js package execution capable of running npx.
  • One or more supported coding-agent tools selected during initialization.

Steps

  1. Run the command below.

    Documented command
    npx ai-devkit@latest init

  2. Use the initialization wizard to select the agents and control-plane components for the project.

  3. Review the generated .ai-devkit.json, agent directories, skills, settings and docs/ai/ folders.

  4. Commit the project-local files if they match the team’s workflow.

Expected outcome

The project receives a shared configuration source, selected agent-specific setup, composable skills, MCP settings including the local memory integration, and lifecycle documentation folders.

Guide limitations

  • The supplied instructions document initialization and generated files, but do not establish successful execution of a particular agent or workflow.
  • Generated agent directories depend on the tools selected in the wizard.
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
AI DevkitReconcile agent configuration, skills and MCP setup from one project-level configuration file.CLI, Desktop, Self-hostedThe repository is public, identifies Apache-2.0 licensing and provides the documented `npx ai-devkit@latest init` entry point.
NasikoDetect supported coding-agent CLIs and inspect their versions and configuration locations.CLIThe documented discovery command requires no account. Reporting and routing require an active control plane and valid login. The Docker Compose path requires Docker Engine with Compose V2; the CLI requires Rust 1.85 or later.
ParitokRoute coding-agent requests through a local proxy.Self-hosted, ServerThe project is public and licensed under Apache-2.0. The documented self-hosted quick start uses Python 3.11 or later and Ollama.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
3 October 2026
Original website title
codeaholicguy/ai-devkit · Official homepage title · retained in its source language
How we review sourcesSuggest a correction