realTaki/MAGI

記録された最新のソース活動: 2026年10月29日 04:03

SkillsMP カタログ更新: 2026年11月12日 12:52

収集済み skills: 7

GitHub スター: 5
GitHub フォーク: 7

AI アシスタントでインストール

このプロンプトをコピーして、使用中の AI アシスタントに送ってください。

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/realTaki/MAGI.

リポジトリの README

README の元ファイル：README.md

README の元ファイルを読む

README 全文を表示

# MAGI — Modular Agentic Genesis Intelligences [![License](https://img.shields.io/badge/license-BUSL--1.1-blue.svg)](LICENSE) [![TypeScript](https://img.shields.io/badge/runtime-TypeScript%20%2B%20Node%2024-blue)](https://nodejs.org/) [![Status](https://img.shields.io/badge/status-experimental-orange)](docs/verification.md) [中文](README_zh.md) · [Get started](docs/running.md) · [Architecture](docs/architecture.md) · [Documentation](docs/README.md) > **DSH migration in progress.** `apps/eva` is now a DSH Host plugin, not the previous EVA launcher. The desktop/Shell and revision-switching flows described here and in the linked docs belong to the pre-migration implementation; their integration with the new plugin is not yet complete. Read the [current scope and verification boundaries](DSH-HANDOFF.md) before following those instructions. The current DSH scope has two product bundles and shared components: **MAGI Workbench** supplies desktop navigation and includes **Bot Main Session / Bot Agent Preset** ([@magi/bot-mode](<packages/bot-mode/README.md>)); **EVA Node Manager** manages independent nodes and includes **Bot Direct Messages** ([@magi/dm](<packages/dm/README.md>)) and **Bot Memory** ([@magi/memory](<packages/memory/README.md>)), reusing Bot mode for child nodes. EVA also includes independent [Subconscious](<packages/subconscious/README.md>), paused by default: a bounded, slow sequential reflection conversation, not continuous model traffic or subagent fanout. Source wiring neither enables it nor deploys it to running nodes. Implementations remain independent; package names and data ownership are unchanged. Bundle cards are not runtime instances, and EVA users need not also select standalone Memory. See [plugin layout and update boundaries](<docs/plugin-layout.md>). Use the [DSH pack helper](<scripts/pack-dsh.mjs>) with the MAGI-owned runtime (`npm run pack:dsh -- --app eva --out dist`; also supports `magi-shell`, `memory`, `bot-mode`, and `subconscious`). The old Electron Shell and provider module have been deleted. Only these six workspaces are in the supported install graph; other pre-DSH packages are inert archived source, with no supported root legacy build/test gate. The historical architecture and revision-switching discussion below is not a current launch guide. **Fork it. Grow your own MAGI.** MAGI is an experiment in software that agents can reshape for the people using it. It starts as a persistent multi-agent system. Its source is part of its working environment, not an artifact sealed away after installation. Agents can work on that source, test changes and request a switch to a new runtime revision. The point is not to ship one finished assistant that everyone uses in the same way. It is to give you a starting point for software that becomes yours. Your MAGI should eventually look different from mine. The name is a tribute to *Neon Genesis Evangelion*. ## Software to grow, not just configure Most settings let you choose among behaviors someone else has already built. MAGI explores a different relationship: describe what you need, then let your agent work on the software itself. That might mean changing a tool, building a personal interface, adapting a workflow or learning from another agent project's implementation. Start from a concrete need, make the change and judge it by what it actually does. This is a personal, noncommercial project in intent, not a roadmap toward a uniform hosted product. It does not promise backward compatibility. You are expected to keep your own fork and work with an agent to maintain it, adapt changes and handle migrations. Upstream is a source of ideas and code, not an authority that your version must keep matching. ## What makes that possible? ### A team that stays An **EVA** is an individual agent node. Each has its own process, workspace, model-provider configuration, memory and contacts. The desktop starts the built-in **Shell EVA**, your entry point to that system. From chat, you can ask Shell to create another local EVA or connect to a remote EVA. Nodes exchange messages directly and keep their own histories. There is no central ASP registry or relay. A team is not just a list of temporary model calls; its nodes and workspaces can persist beyond a single task. ### A BUS that separates the parts Inside each EVA, workers coordinate through **BUS Books and durable Jobs** instead of calling one another's implementations. The BUS carries shared data and contracts; workers provide capabilities. The manager handles worker lifecycle and configuration. This separation is meant to make individual capabilities easier to replace and evolve without rewriting the whole system. Keep the collaboration boundary stable so the modules can keep changing. See [how the pieces fit](docs/architecture.md). ### The interface is software, too “Everything is an agent” is the direction: not only the assistants in a chat, but the interfaces, tools and personal systems around them should be able to participate in their own maintenance. Today, MAGI provides editable source and a verified revision-switching mechanism; Shell revisions can include the built UI. The next direction is more self-management and less manual configuration. Eventually, I would like even the settings page to disappear. ## Start with your own version 1. **Fork this repository.** Give your MAGI a home for changes that serve you. You do not need to turn every local adaptation into an upstream contribution. 2. **Run a prepared source checkout or a suitable desktop build.** Follow [Running MAGI](docs/running.md); source preparation and the bundled Node 24 toolchain are in [Contributing](CONTRIBUTING.md). 3. **Configure the intended EVA's model provider.** Use that local EVA's profile, not a key pasted into chat. Wait for its verification result. 4. **Start small.** Ask for one useful, bounded change, check the result and keep the evidence. Saving code, testing it, activating it and publishing it are different actions. For a first self-edit, choose something you can see and test, such as a small interface behavior. Keep the scope and expected result explicit. A successful build is not a substitute for trying the resulting behavior. ## Current boundaries MAGI is experimental. The direction is ambitious; the current boundaries are concrete: - **Private, trusted networks only.** Direct peer messaging is not an authenticated public-internet service. Do not expose peer endpoints to untrusted networks. Native tools are not an OS sandbox. - **Self-editing exists; sustained self-improvement remains to be demonstrated.** Not every component has its own agent. Settings and provider forms still exist. - **Changes still need validation.** Shared-contract changes require coordination, outer Electron updates differ from node replacement, and process rollback does not undo database changes or external actions. - **Protocol compatibility is explicit.** The MAGI peer subset is inspired by A2A 1.0; it is not a standards-compliant A2A implementation. See [Security](SECURITY.md), [Verification](docs/verification.md) and [unfinished work](docs/future.md) for details. ## Explore or contribute - [Documentation map](docs/README.md): choose a route for using, modifying or checking MAGI. - [Architecture](docs/architecture.md): processes, BUS, source ownership and activation. - [Contributing](CONTRIBUTING.md): build, test and send a focused upstream change. - [Research goals](docs/future.md): what remains to be demonstrated. Human and agent collaborators are welcome. For a substantial upstream change, start with an Issue to align on scope. For your own fork, the direction is yours. Report vulnerabilities through [Security](SECURITY.md), not a public issue. **A thousand people. A thousand MAGIs.** ## License MAGI is source-available under [Business Source License 1.1](LICENSE), with realTaki as the Licensor. Non-production use is permitted; the Additional Use Grant also permits the specified research, educational, evaluation, and personal non-commercial production uses. Commercial production use during a version's first six months requires purchasing a separate written commercial license from realTaki. Contact realTaki through [this repository](https://github.com/realTaki/MAGI) for commercial licensing. Each version changes to [MIT](https://opensource.org/license/mit) six months after its first public distribution by the Licensor. Redistributing or modifying that version does not restart its clock. Before the Change Date, copies and derivative works remain subject to BSL; this is not an OSI-approved open-source license or a promise of GPL-style source disclosure. After the Change Date, MIT permits commercial use and closed-source derivatives while requiring preservation of the applicable copyright and permission notices. Third-party and contributor notices remain applicable. This update does not revoke rights already granted for previously published versions. See [LICENSE](LICENSE) for the governing terms.

リポジトリの README を読み込んでいます…

このリポジトリの skills

分類待ち

skill

職業分類

説明

更新

magi-bot-memory

未分類

Remember, reconcile, archive, or remove this Bot's reusable facts and preferences without duplicates or stale writes.

原文の言語: 英語

2026-10-29

magi-eva-nodes

未分類

Create, start, inspect or stop local EVA Bots, distinguish reuse from allocation, and diagnose unavailable nodes safely.

原文の言語: 英語

2026-10-29

magi-local-dm

未分類

Coordinate local MAGI Bots, report back to this Bot's main conversation, or diagnose pending DM delivery.

原文の言語: 英語

2026-10-29

project

未分類

Read and edit this MAGI's source checkout, then ask the desktop app to rebuild this MAGI, the operator UI, or ASP.

原文の言語: 英語

2026-10-12

codebase-search

未分類

Locate modules, functions, and classes in the current workspace and explain what they do.

原文の言語: 英語

2026-09-28

reminder-template

未分類

Create a precise recurring reminder or automated-task prompt with an explicit schedule.

原文の言語: 英語

2026-09-25

web-lookup

未分類

Research current public information when an installed web or MCP search tool is available.

原文の言語: 英語

2026-09-25

収集済み skill 7 件中 7 件を表示しています。