AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
Apache Magpie는 오픈소스 유지관리자를 위한 AI 기반 어시스턴트로 트리아지·멘토링·초안·페어프로그래밍·자동 병합을 지원
AI-powered assistant for open-source maintainers. Triage, mentor, draft, pair, and auto-merge under Apache Software Foundation governance.
개발 도구Python · ShellGitHub @apache온라인운영자 미확인
써 보셨어요? 한 번만 눌러 주세요. 로그인은 필요 없어요.
개인 계정의 공개 저장소 소유자는 GitHub로 로그인해 운영자를 확인하고 소개를 직접 관리할 수 있습니다. 관리자 승인은 필요하지 않습니다.
로그인한 뒤 확인 파일을 만들어 이 저장소의 기본 브랜치에 30분 안에 커밋해 주세요. 다른 브랜치나 포크의 파일은 인정하지 않습니다. 파일을 올린 뒤 아래에서 확인하면 관리자 승인 없이 관리할 수 있습니다. 자격을 유지하려면 파일을 남겨 두세요.
로그인이 필요하면 로그인 화면으로 이동합니다. 로그인 후 이곳으로 돌아와 원하는 확인 버튼을 다시 눌러 주세요.
프로젝트 폴더에서 /nomorevibe verify를 실행하면 소유권을 확인하고 소개를 직접 관리할 수 있습니다.
1분 만에 확인하기Agent-assisted maintainership and development framework for Apache projects — Triage, Mentoring, Drafting (agent-authored fixes with human review), and Pairing (developer-side dev-cycle) skills shipping; Agentic Autonomous (auto-merge) on the roadmap.
저장소 README에서 가져옴
README 전체를 불러오는 중입니다. 아래는 저장된 발췌입니다.
Adopt a Magpie. Magpie is a curated set of skills for the AI agent you
already use — Claude Code, Codex, Gemini CLI, Copilot and others — that take
on the repetitive parts of running an open-source project: triaging issues and
pull requests, reviewing code, mentoring contributors, drafting fixes, and
handling security reports end to end.
Three things make it different from a folder of prompts:README 전문 보기 ↗Table of Contents generated with DocToc
Adopt a Magpie. Magpie is a curated set of skills for the AI agent you already use — Claude Code, Codex, Antigravity, Copilot and others — that take on the repetitive parts of running an open-source project: triaging issues and pull requests, reviewing code, mentoring contributors, drafting fixes, and handling security reports end to end.
Three things make it different from a folder of prompts:
Magpie is currently in development for ASF projects + Python Core team friendlies. Testers welcome!
One security report, start to finish — installed from the marketplace, the agent sandboxed and guarded, then the report imported, triaged against the project's history, fixed, and published as a CVE:
Illustrative — a written transcript, rendered deterministically, not a recording. The interactive version on the project site steps through the same story with the full output of each command.
[!IMPORTANT] The motivation, scope, and design commitments behind this work live in
MISSION.md— the founding mission of the Apache Magpie Top-Level Project, originally filed as its establishment proposal. Read that for the why; this README is the how once you've decided to install.
Start here → Quick start — a handful of commands, in the agent you already use. Nothing is written to your repository.
/plugin marketplace add apache/magpie # Claude Code
/plugin install magpie-setup@apache-magpie # install this one first
/plugin install magpie-vetted-ops@apache-magpie # always: the skills run on it
/plugin install magpie-agent-guard@apache-magpie # the baseline:
/plugin install magpie-utilities@apache-magpie # take all four
/plugin install magpie-pr-management@apache-magpie # + the families you need
Those first four are the baseline — and the same set a project commits as its floor when it adopts Magpie, so taking them is taking what a project would recommend to every contributor. After that, install one plugin per family you actually want: every installed skill costs context on every turn, used or not (~0.2–2.0k tokens a family), so there is deliberately no install-everything plugin.
Once magpie-setup is in, you never type these again — ask in plain language
("install the Magpie families for PR review") and the setup skill runs the
installs for you.
Codex, VS Code / Copilot, Antigravity, Pi and Goose are short too — the quick start has each of them, plus what to run next to put the agent in its sandbox. Nothing is committed to your repository.
Fallback — the pinned snapshot install. Use it when a marketplace is not an option or not enough: your agent has no plugin mechanism, you need the signed ASF source release rather than a git clone, or the project wants every contributor and CI job pinned to one committed version with drift detection.
docs/setup/install-recipes.md/magpie-setup:setup installThe two are complementary, not exclusive.
Magpie is used by interacting with your AI agents. You'll use plain-language prompts like
review PR #5193
or
triage the latest security reports
or skill calls starting with a slash, like
/magpie-repo-health:dependency-audit
(the family-plugin form, assuming the recommended marketplace install above — see Skill names differ by install method if you're on the pinned-snapshot fallback instead).
Marketplace install (the recommended path above):
/plugin marketplace update apache-magpie then
/plugin update <plugin>@apache-magpie — refresh the marketplace
metadata, then bump the installed plugin(s) to its latest.
Auto-update does the same in the background once enabled./magpie-setup:setup reconcile.
See Reconciliation when a skill first runs after an upgrade./magpie-setup:isolated-setup-update after an upgrade that changed its files, and weekly otherwise.
Run it directly to check now.
See Automatic reminders from the pre-flight.Pinned-snapshot install (the fallback):
/magpie-setup upgrade — refresh the snapshot to a newer
framework version + reconcile any overrides against the new
framework structure./magpie-setup verify — read-only health check (snapshot
intact, symlinks live, .gitignore correct, etc.)./magpie-setup:setup override <framework-skill> — open or
scaffold an override file for a framework skill.The following skill families ship in the framework, all at experimental or
stable, and each skill declares its family in a family: frontmatter
key. On the recommended marketplace install, you choose families by which
per-family plugin(s) you install (see Install above) — install
or uninstall a plugin at any time to add or drop a family. On the
pinned-snapshot fallback, /magpie-setup offers the opt-in families —
and the optional MCP servers (ponymail, apache-projects,
gmail-plaintext) — in a single install choice, and symlinks for the picked
families land in the skill directory. Either way, the two always-on
families (setup, utilities) are wired unconditionally and never prompted
for.
The Modes column maps each family to the MISSION agent-assistance
taxonomy — see docs/modes.md for what each mode
means and which modes are still proposed vs. shipping today.
| Family | Type | Modes | Purpose | Detail |
|---|---|---|---|---|
| setup | always-on | (infra) | Isolated agent setup, framework install + maintenance, shared-config sync. The prerequisite — at minimum the setup skill itself runs out of this family. | 12 skills, docs/setup/ |
| utilities | always-on | (meta) | Framework meta-skills: author skills (write-skill), restructure them (optimize-skill), reconcile skill state (skill-reconciler), report framework issues (report-framework-issue), and print a live index (list-skills). | 5 skills |
| security | opt-in | Triage, Drafting | 16-step security-issue handling lifecycle — from security@ import through CVE publication, including state sync — plus producing, verifying, and maintaining the project's own security model. Maintainer-only. | 16 skills, docs/security/ |
| pr-management | opt-in | Triage | Maintainer-facing PR-queue management — triage, stats, deep code review, stack review, express-lane merge, stale-sweep, reviewer routing, and pre-first-PR checks. | 9 skills, docs/pr-management/ |
| issue |
Skill families or individual skills can be pulled
from a trusted external source — a repo other than apache/magpie that
ships Magpie-shaped skills (with their evals and tests). Where a skill
directory would sit, a skills/<name>/source.md redirect names a
pinned, verified source the adopter has vouched for; /magpie-setup fetches
it into the gitignored snapshot and wires it in exactly like a framework
skill. Nothing is fetched unless the adopter commits the pin — see
docs/skill-sources/,
PRINCIPLES.md §14,
and RFC-AI-0006.
Apache Magpie was first developed and proven inside Apache Airflow, and was
maintained for a time as the apache/airflow-steward repository under the
Airflow PMC before being renamed and established as its own project. It also
incorporates early skill work contributed by way of the Apache Groovy
community. All of that code carries the same rightsholder — Copyright The Apache
Software Foundation, under the Apache License 2.0 — so it is not a third-party
inclusion; the required attribution lines from the originating projects' NOTICE
files are reproduced in NOTICE.
MISSION.md — founding mission of the established TLP: motivation, scope, design commitments, initial PMC composition target.docs/setup/agentic-overrides.md — the contract between adopters who write overrides and framework skills that read them.docs/prerequisites.md — what a maintainer needs installed before invoking any framework skill (Claude Code, Gmail MCP, GitHub auth, browser, uv, etc.).docs/source-release-contents.md — what ships in the signed apache-magpie-<version>-source.zip (and what is excluded), with the rationale for the repository-root metadata/config files it keeps.docs/release-management/manual-release-process.md — the concrete, as-executed runbook for cutting a Magpie release by hand on the current hybrid SVN-dist + ATR-vote backend (with the abstract per-backend runbooks and the 14-step lifecycle alongside it in docs/release-management/).AGENTS.md — agent instructions, placeholder convention, framework conventions.CONTRIBUTING.md — for framework contributors.| opt-in |
| Triage, Drafting |
| General-issue lifecycle: triage, reproduction, fix drafting, reassess, stale-sweep, deduplication, and backlog reporting. |
8 skills, docs/issue-management/ |
| release-management | opt-in | Triage, Drafting | 14-step ASF release lifecycle, planning issue, RC cut + sign, [VOTE] thread, tally, promote, [ANNOUNCE], archive, audit log. Agent never holds the RM's signing key and never publishes the release. Experimental, all 10 skills shipped. | 10 skills, docs/release-management/ |
| repo-health | opt-in | Triage | Read-only repository-health audits: obsolete runner labels, Actions workflow security, dependency vulnerabilities, dependency licence review, license/NOTICE compliance, flaky-test patterns, workflow runner-usage optimization, plus audit-finding fixes. | 8 skills, docs/repo-health/ |
| pairing | opt-in | Pairing | Pair a change with a structured self-review or a multi-agent adversarial review before it lands. | 2 skills, docs/pairing/ |
| mentoring | opt-in | Mentoring | Newcomer-facing mentoring — first-contact welcome, newcomer-issue explanations, and good-first-issue authoring + backlog curation. Experimental. | 4 skills, docs/mentoring/ |
| contributor-growth | opt-in | Triage, Mentoring | The path-to-committer track: activity sweeps, nomination briefs, contributor-sentiment signals, readiness tracking, threshold calibration, candidate screening, committer / post-vote onboarding, and contributor identity mapping across Slack, Discord, and social media. | 9 skills, docs/contributor-growth/ |