Star us ❤️ →
Give it a direction and it ships the work: features, vulnerability disclosures, live apps, deep research - and new skills for itself.
No approval loops. No babysitting. Configure once, forget forever.
▶ Start in your browser: www.aeon.fun/connect - sign in with GitHub, connect a model, pick skills. No clone, no terminal.
🤖 Using a coding agent? Point it here: read https://www.aeon.fun/skills/aeon.md and follow the instructions to set up your Aeon agent.
In your browser (recommended): Aeon Connect. Sign in with GitHub at www.aeon.fun/connect and click Create your aeon: it makes your own repo (public = a fork of aeonfun/aeon, free Actions minutes; private = a copy, on your own minutes) and turns GitHub Actions on. Install the Aeon Connect GitHub App on that one repo (GitHub's page opens with it pre-selected), then connect a model (a Claude subscription token from claude setup-token, an API key, a ChatGPT login, or OpenRouter in one click), pick skills, and press Run. Keys go straight into your repo's encrypted secrets; Aeon Connect only hosts the dashboard, and every run happens on your own GitHub Actions.
Using a coding agent? Paste this into Claude Code, Codex, Hermes or OpenClaw: read https://www.aeon.fun/skills/aeon.md and follow the instructions to set up your aeon agent.
Prefer the terminal?
You need Node.js 20+ and the GitHub CLI (gh). Then:
git clone https://github.com/aeonfun/aeon && cd aeon
./aeon init./aeon init does the rest and tells you what it did at each step: signs you in to GitHub, creates your own repo from the template (public by default - Actions minutes are free; --private if you prefer), points this folder and gh at it, turns on GitHub Actions, stores your GitHub token for runs, connects a model (any of nine harnesses: a Claude subscription, an API key, or one OpenRouter key) and, if you want, links Telegram. It is safe to re-run: every step checks first and skips what is already done. Then ./aeon opens the same dashboard locally at localhost:5555 to pick skills and Run. bin/onboard re-checks the whole setup any time (read-only).
Prefer to do it by hand?
-
Click Use this template on the repo page (keep it public; Actions minutes are free). A template copy starts with GitHub Actions on. If you fork by hand instead, open the fork's Actions tab and enable workflows first: a fork starts with Actions off and its schedules never fire until you do. (Aeon Connect forks public instances and turns Actions on for you.)
-
Clone it and point
ghat it - without this, secrets you set land onaeonfun/aeoninstead of your repo:gh auth login --web -s workflow git clone https://github.com/<you>/aeon && cd aeon gh repo set-default <you>/aeon ./aeon
-
In the dashboard: Connect a model -> add a channel -> pick skills -> Run.
Everything is also an ./aeon command (CLI) or a /aeon chat command (setup skill, installable as a Claude Code or Codex plugin). For skills that reach other repos, add a classic PAT with repo + workflow as GH_GLOBAL (details).
No admin rights / can't install gh?
You don't need either: Aeon Connect sets everything up from the browser. For the terminal path, grab the gh_*_macOS_arm64.zip (or your platform's binary) from github.com/cli/cli/releases and drop it on your PATH (e.g. ~/.local/bin). Then gh auth login.
A skill is a Markdown file: some frontmatter, then a prompt. Here's a real one, trimmed:
# skills/digest/SKILL.md
---
name: digest
description: Generate and send a digest on a configurable topic
metadata:
title: Digest
mode: write
category: basics # which pack it belongs to
var: "" # per-run input - "solana", "rust", "AI agents"…
requires:
- XAI_API_KEY? # ? = optional key, bare = required
---The prompt is the skill. You schedule it, hand it a var, chain it into others, and a cheap model rates every run (Haiku on Claude). How packs work: docs/skill-packs.md.
Full catalog - all 85 skills by pack →
The same SKILL.md runs on any of nine agent CLIs - Claude, Grok, Codex, Pi, Vibe, Kimi, fx, Cursor, Hermes - behind one run-harness contract (same result, usage, and session shape). Swap the harness; nothing else changes. How the contract works: docs/harnesses.md. GLM Coding Plan is a Claude AI Gateway hop (GLM_API_KEY), not a harness.
Most agent tools keep you in the loop - approve this call, review this diff. Aeon is built for the work you want done while you're away, and it's the only framework that does all four unattended: runs on a schedule, remembers across runs, reacts to conditions, and repairs its own broken skills. The most autonomous agent is the one that never asks.
Full comparison vs Claude Code, Hermes, and OpenClaw: SHOWCASE.md.
Live at aeon.fun: 4.7M GitHub stars secured - real vulnerabilities found, patched, and responsibly disclosed across 100+ open-source repos (Alibaba, Tencent, Vercel, and more), many rated High or Critical. 70+ products built on top of Aeon.
Every disclosure → · ecosystem · community packs
feature ships code to your repos, deploy-prototype ships live apps to Vercel, vuln-scanner finds and privately discloses real vulnerabilities, create-skill writes new skills from a sentence. How each works: CORE.md.
A model scores every run 1–5; heartbeat → skill-health → skill-repair → self-improve detect and fix broken skills without you, and aeon-doctor lints the config itself. How the loop closes: CORE.md.
spawn-instance forks Aeon into a new specialized instance (var: "crypto-tracker: monitor DeFi protocols"), picks relevant skills, and registers it - no secrets propagated, billing isolated. fleet-control health-checks and dispatches across the fleet.
Read-only skills can't touch the repo, irreversible actions fail closed, an optional Fleet Watcher gates every run, and secrets stay off the command line. Details: Configuration.
Muse, Grok, and Hermes Cloud run around the clock too, but on their own servers, and they train on your chats unless you opt out (Muse, Grok, Hermes Cloud). Aeon runs on your own GitHub Actions: memory is files in your repo, keys are your repo's encrypted secrets, there is no Aeon server in the loop, and nothing is sent anywhere unless you point tracing at your own collector. Keep it fully private with a private instance (two-repo strategy) and your own model key - your model provider's terms still apply.
Everything lives in aeon.yml - schedules (standard UTC cron), the per-skill var input, model, auth, notification channels, and API keys:
skills:
digest:
enabled: true
schedule: "0 14 * * *" # daily 2pm UTC
var: "solana" # per-run inputFull reference - scheduling, var, models, authentication, notification channels, API keys, guardrails: Configuration.
GitHub permissions: the built-in GITHUB_TOKEN covers same-repo work; add one classic PAT as GH_GLOBAL with repo + workflow scopes to drive every cross-repo, private, disclosure, and workflow-editing skill. No read:org / admin:org. See Cross-repo access. Set up with Aeon Connect? The dashboard reaches your repo through the Aeon Connect GitHub App, so no PAT is needed to get going; GH_GLOBAL is only for the cross-repo skills above.
An Aeon instance is just a GitHub repo + Actions, so GitHub's API is Aeon's API - one GitHub App drives your users' instances (dispatch skills, edit config, write sealed secrets) with no PATs or LLM billing on your side.
Full walkthrough - App setup, tenant isolation, driving skills, shipping your own pack: ADK - Aeon Developer Kit.
The deep reference lives in docs/ - jump in:
|
|
|
We're excited to meet you.
Every bug fix, new skill, or doc tweak makes Aeon better. Big PRs and small ones, both welcome.
📝 Contributing guide · 💬 Say hi on X
MIT · Support the project: 0xbf8e8f0e8866a7052f948c16508644347c57aba3 ⭐
Built by Aaron Elijah Mars, founder of Aeon and MiroShark · @aaronjmars