BootAgent

Name: BootAgent
Author: MaimoryLab

Pending

BootAgent is a local management tool of AI agents. It turns a fresh machine into a usable, repeatable setup without asking you to edit several tool-specific config files by hand.

84stars

5forks

Installation

# Add to your Claude Code skills
git clone https://github.com/MaimoryLab/BootAgent

Getting Started

Guides for using ai agents skills like BootAgent.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

README.md

Frequently Asked Questions

What is BootAgent?

BootAgent is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by MaimoryLab. BootAgent is a local management tool of AI agents. It turns a fresh machine into a usable, repeatable setup without asking you to edit several tool-specific config files by hand. It has 84 GitHub stars.

Is BootAgent safe to use?

BootAgent's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.

How do I install BootAgent?

Clone the repository with "git clone https://github.com/MaimoryLab/BootAgent" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is BootAgent written in?

BootAgent is primarily written in Go. It is open-source under MaimoryLab on GitHub, so you can review or fork the full source.

Are there alternatives to BootAgent?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh BootAgent against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

ECC

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

239,787

prompt-refine-skill OneAgent

BootAgent is a local desktop workspace for AI coding Agents. It turns a fresh machine into a usable, repeatable setup without asking you to edit several tool-specific config files by hand.

What it does

Detects, installs, updates, and launches supported CLI and desktop Agents.
Migrates existing Codex and ChatGPT Desktop conversations into BootAgent's bootagent provider bucket from their Agent rows. This operation intentionally creates no history backup.
Connects Agents to built-in or custom Providers, with model selection and protocol-aware connection checks.
Saves reusable Profiles and applies the right configuration to each Agent.
Bootstraps required runtimes such as Node.js, uv, and Aider's managed Python when needed.
Keeps long-running installs visible and cancellable in the Task Center.
Imports and exports Providers, Profiles, and selected MCP servers. API keys and MCP secrets are excluded by default; password-encrypted or explicitly confirmed plaintext export is also available.
Discovers MCP servers from initialized Claude Code, Codex, OpenCode, Kilo CLI, and Hermes installations, and applies selected servers across them from the MCP Registry. Scanning runs in the background; edits are explicit and local.
Creates backups, writes atomically, and keeps credentials in private local storage. The latest three historical versions are kept per Profile, Provider, MCP, Agent configuration target, and Skill; backups live under ~/.bootagent/backup and the per-target count can be changed in Settings.
Checks for BootAgent updates and installs release artifacts through the built-in updater.

Supported Agents

CLI Agents	Desktop Agents
Codex · Claude Code	ChatGPT Desktop（macOS/Windows）
Kilo CLI · Aider· OpenCode	WorkBuddy（macOS/Windows）
Hermes Agent · OpenClaw
Kimi Code

JieKou.AI, PPIO, Novita, DeepSeek and Moonshot are built in, listed in that order. Any OpenAI-compatible or Anthropic-compatible Provider can be added from the Provider page. BootAgent probes the protocol an Agent actually uses; an endpoint that only exposes a different API is rejected before configuration is written.

The MCP Registry is user-level only and stored locally. It supports stdio, HTTP, and SSE servers for Claude Code, Codex, OpenCode, Kilo CLI, and Hermes. Select sync targets explicitly and apply changes when ready; clearing all targets removes the server from Agent configs but keeps it in the Registry. Deleting a server removes it from Agent configs first and from the Registry only after the application succeeds. MCP exports are selected per server and carry no Agent bindings, so they can be imported on another machine before choosing local targets.

Download

Download the latest macOS, Windows, or Linux package from GitHub Releases. Linux releases provide deb, rpm, AppImage, and OTA zip packages for amd64 and arm64. Release artifacts include SHA-256 checksums. The current channel is technical-preview-unsigned while Wails remains in Alpha; platform signing and notarization are not yet provided.

BootAgent does not redistribute Agent packages and does not bundle Node.js, Git, WebView, or API keys. Missing prerequisites are reported with a link to the official installation instructions.

Build from source

Requirements: Go, Node.js, pnpm 11.21.0, and the target platform's WebView dependencies. Linux builds use GTK4 and WebKitGTK 6.0; GTK3 is not supported.

git clone https://github.com/MaimoryLab/BootAgent.git
cd BootAgent
cd frontend && pnpm install --frozen-lockfile && pnpm run build && cd ..
go run -tags wails ./cmd/bootagent-desktop

For the usual development loop, install Task and run task dev. Useful checks:

go test ./...
go test -race ./...
go vet ./...
cd frontend && pnpm run test && pnpm run build

Project links

AI Agent Kit: set up an Agent environment step by step
Documentation: specifications and architecture decisions
Public site repository
Issues and feature requests