Automation & Ops github-actionscron-schedulingself-healingskill-packsmulti-harnessvulnerability-disclosuremcp-serverfleet-orchestration

AEON Autonomous Agent Framework

The autonomous AI agent framework that runs unattended on GitHub Actions: configure once, forget forever, with self-healing skills and no approval loops.

FollowAgents review · FARS-2.1
Not recommended
56/ 100 5-point scale 2.8 / 5
1 2 3 4 5 6
1Trust14 / 29 · 2.4/5

Evidence shows substantial hardening (default-deny egress to link-local/metadata, bubblewrap read-only sandbox, SHA-pinned actions, fail-closed opt-in Fleet Watcher preflight), but the workflow grants broad permissions (contents:write, id-token:write, pull-requests:write, issues:write) and runs unattended — deducted. 'No approval loops' is explicit; only an optional gate exists. Data flows (chain context files, Issues state backend, audit log) are well documented (2); secrets are never echoed and the audit log has adversarial multi-encoding redaction tests, but GH_SECRETS_PAT persists rotated OAuth tokens back to repo secrets (2); dependencies are pinned ([email protected], SHA-pinned actions, offline cache) (2); external effects — unattended pushes to main, PRs, notifications — deducted to 1; rollback is limited to rebase/reset retries and PR snapshots (1); attribution is solid: MIT, OIDC-signed attestations, fixed git identity (2).

2Reliability9 / 14 · 3.2/5

Comments record a live-observed concurrency bug (8/10 runs silently cancelled), its fix, and the remaining unfixed gap — high self-consistency with known gaps (2); dependency availability is supported by npm cache + --prefer-offline, apt lock timeouts, step timeouts (2); failure messages use ::error::/::warning:: with specifics and distinguish invalid-dispatch from real failures (2).

3Adaptability10 / 18 · 2.8/5

Nine harnesses and opt-in state backends with fork backward-compatibility (2); capability boundaries are asserted in marketing ('most autonomous', 'self-healing') with only comment-level acknowledgment of limits (1); trigger precision via skill-name regex validation, ai-build label gating, and choice inputs preventing HTTP 422 (2); environment fit handles the ubuntu-24.04 AppArmor userns restriction with measured evidence (2).

4Convention10 / 18 · 2.8/5

Clear repo structure (apps/, skills/, scripts/, memory/) (2); a bootstrap script exists but no README/install docs appear in evidence (1); naming stable (2); examples exist only as tests, no user docs/FAQ (1); known-limitations documentation is exceptional, with measured dates, observed incidents, and unfixed gaps (3); MIT license complete (3); root version 0.0.0, no changelog evidence, deliberately divergent per-app toolchains (1); no maintainer/CONTRIBUTING evidence beyond a fixed git identity (1).

5Effectiveness9 / 13 · 3.5/5

Outputs land as consumable files (output/.chains, memory/cron-state., skill-health JSON) (2); multi-harness orchestration plus supply-chain hardening and attestations is distinctive (2); cost discipline via max_dispatches budget, step/job timeouts, fail-closed preflight (2).

6Verifiability4 / 8 · 2.5/5

Comments carry concrete dates, observed incidents (2026-08-19 hangs, 8/10 cancellations), and checkable mechanisms (attestations, audit log, state files) (2); tests cover only a few scripts, so most claims rest on self-attestation (1); facts and inference are separated in comments, but top-level marketing claims are unverifiable (1).

Evidence confidence: Low Reviewed Sep 07, 2026 Reviewed revision f96beb9ac971
Before you use it
  • Unattended runs with contents:write/id-token:write mean any skill-level prompt injection could push to main or open PRs directly; the Fleet gate is opt-in — enable it or add your own approval step.
  • GH_SECRETS_PAT lets scripts persist rotated OAuth tokens back into repo secrets — a sensitive-credential persistence path; scope that PAT minimally.
  • The bubblewrap sandbox works by disabling kernel.apparmor_restrict_unprivileged_userns, which itself weakens the runner's isolation baseline.
  • This is a static review with no executed runs; the 'most autonomous' / 'self-healing' marketing claims are not supported by the reviewed evidence — do not rely on them for capability assessment.
Review evidence [1][2][3][4][5][6][7]
See the full review method →

What does this agent do, and when should you use it?

AEON is an open-source (MIT) autonomous agent framework whose execution boundary is a GitHub repository plus GitHub Actions, running scheduled jobs unattended on UTC cron. Its core abstraction is the skill: a single SKILL.md file made of frontmatter plus a plain-language prompt, with all 78 skills organized into six packs (Core, Evolution, Basics, Dev & Code, Crypto & Markets, Productivity). The same SKILL.md runs on any of nine agent CLIs — Claude, Grok, Codex, Pi, Vibe, Kimi, fx, Cursor, Hermes — behind one unified run-harness contract. All configuration lives in aeon.yml, covering schedules, per-skill var inputs, models, authentication, notification channels, and API keys. Unlike agent tools that keep a human in the approval loop, AEON is built around four unattended capabilities — running on a schedule, remembering across runs, reacting to conditions, and repairing its own broken skills — closed by a heartbeat-driven health and repair loop.

AEON reads schedules and configuration from aeon.yml, triggers SKILL.md skills on cron via GitHub Actions, and dispatches them through the run-harness contract to one of nine agent CLIs. Concrete outputs: the feature skill ships PRs to your repos; deploy-prototype deploys live apps to Vercel; vuln-scanner finds real vulnerabilities and privately discloses them; create-skill writes new skills from a single sentence. After each run, a model scores it 1–5, and the heartbeat → skill-health → skill-repair → self-improve chain detects and fixes broken skills automatically, while aeon-doctor lints the config itself. spawn-instance forks one Aeon into specialized instances (e.g. a DeFi tracker) with no secrets propagated and isolated billing, and fleet-control health-checks and dispatches across the fleet. Results are reported back to Telegram, Discord, or email channels, and every skill is also exposed as an aeon MCP tool inside Claude.

  1. Open-source maintainer: let vuln-scanner scan your repos on a schedule and privately disclose high-severity findings instead of exposing them publicly.
  2. Solo developer: use the feature skill to ship PRs to your own repos on a schedule, working through backlog unattended.
  3. Prototype team: use deploy-prototype to push apps live to Vercel on cron, getting a working deployed version automatically.
  4. Security researcher: replicate the pipeline behind the project's documented disclosures across 69 open-source repos (Alibaba, Tencent, Vercel and more).
  5. Agent enthusiast: fork one instance into specialized crypto, security, or research nodes via spawn-instance and manage them with fleet-control.
  6. Platform builder: use the ADK (Aeon Developer Kit) to drive your users' Aeon instances through a GitHub App API and ship your own product on top.

What are this agent's strengths and limitations?

Pros
  • Genuinely unattended: scheduled runs, memory across runs, condition-triggered reactions, and self-repair together — no approval loops — which is the framework's core differentiator over most agent tools.
  • One SKILL.md runs across nine agent CLIs (Claude, Grok, Codex, Pi, Vibe, Kimi, fx, Cursor, Hermes); the unified run-harness contract means swapping engines requires no skill changes.
  • Self-healing is a concrete mechanism, not a slogan: a model scores every run 1–5 and the heartbeat → skill-health → skill-repair → self-improve loop detects and fixes broken skills on its own.
  • Verifiable track record: the official site documents real vulnerabilities found, patched, and responsibly disclosed across 69 open-source repos (many High or Critical), plus 68 products built on Aeon.
  • Guardrails ship by default: 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.
Limitations
  • Strong GitHub-ecosystem dependence: the runtime boundary is a repo plus Actions, and cross-repo, private, disclosure, and workflow-editing skills all require a classic PAT with repo and workflow scopes (GH_GLOBAL).
  • Unattended operation raises trust costs: with no human approval step, adoption requires careful configuration of capability tiers and the Fleet Watcher gate to contain mistakes.
  • Ongoing cost in GitHub Actions minutes plus the underlying model's API fees (Haiku scores every run); the repo provides no usage benchmarks for estimating long-term spend.
  • Operationally bound to a supported agent CLI as the execution engine (e.g. Claude requires its own account/keys); GLM Coding Plan is only a gateway hop, not a harness, and behavior may vary when swapping engines.
  • Skill quality equals prompt quality: since the prompt is the skill, writing and debugging weak SKILL.md files demands prompt-engineering experience from the user.

How do you install or deploy this agent?

Prerequisites: Node.js 20+ and an authenticated GitHub CLI (run gh auth login). Installation is via your own fork: click Use this template on the repo page (keep it public so Actions minutes are free), or run gh repo fork aeonfun/aeon --clone. Then:

git clone https://github.com/<you>/aeon
cd aeon && ./aeon

Open http://localhost:5555 and follow the dashboard: Authenticate (any of nine harnesses) → add a channel → pick skills → Run. For cross-repo skills, add one classic PAT as the GH_GLOBAL secret with repo and workflow scopes.

How do you use this agent?

All configuration lives in aeon.yml, for example:

skills:
digest:

enabled: true
schedule: "0 14 * * *"   # daily 2pm UTC
var: "solana"            # per-run input

Once saved, Aeon runs unattended on GitHub Actions and pushes results to your configured Telegram, Discord, or email channel. Every dashboard action is also an ./aeon CLI command or a /aeon chat command (installable as a Claude Code or Codex plugin). Skills are files: write frontmatter and a prompt in skills/<name>/SKILL.md, declare required API keys with requires (a ? suffix means optional), accept per-run input via var, and chain into other skills.

How does this agent compare with similar options?

The README compares Aeon against Claude Code, Hermes, and OpenClaw (see docs/SHOWCASE.md): most agent tools keep you in the loop — approve each call, review each diff — whereas Aeon targets work done while you're away and claims to be the only framework that does all four unattended: scheduled runs, cross-run memory, condition-triggered reactions, and self-repair. If your workflow needs human confirmation at every step, a Claude Code-style tool fits better; if you want a configure-and-forget fleet of scheduled jobs, Aeon is the better match.

FAQ

What does running it cost?
Three components: GitHub Actions minutes (free on public repos), the underlying agent CLI's model API fees, and the small cost of Haiku scoring every run. The repo gives no usage benchmarks, so start with a few skills enabled and scale gradually.
What permissions and keys are required?
The built-in GITHUB_TOKEN covers same-repo work; cross-repo, private, disclosure, and workflow-editing skills need one classic PAT stored as GH_GLOBAL with only repo and workflow scopes — no read:org or admin:org. Per-skill API keys are declared in each SKILL.md's requires field.
What happens when a skill breaks?
A built-in self-repair loop handles it: every run is scored 1–5 by a model, and heartbeat → skill-health → skill-repair → self-improve automatically detect and fix broken skills, while aeon-doctor lints the config file itself.
There's no approval step — how is risk controlled?
Four guardrails, on by default or one flag away: read-only skills cannot touch the repo, irreversible actions fail closed, an optional Fleet Watcher auth gate approves every run, and secrets never appear on the command line.
Can I build a product on top of it?
Yes. An Aeon instance is just a GitHub repo plus Actions, so GitHub's API is Aeon's API — one GitHub App can dispatch skills, edit config, and write sealed secrets to drive your users' instances with no PATs or LLM billing on your side. See the ADK (Aeon Developer Kit) docs.

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.

Related agents