Why "most autonomous agent framework"?

Most agent tools put you in the driver's seat — approve this tool call, review this diff, confirm this action. That's useful for interactive work. But there's a whole class of tasks where you just want the work done while you're not there: morning briefs, market monitoring, PR reviews, research digests, security scans.

Aeon is built for that. Here's how it compares:

| | Aeon | Claude Code | Hermes | OpenClaw | |--|------|------------|--------|---------| | Runs unattended on a schedule | Yes | No | Yes | No | | Self-heals when skills fail | Yes | No | No | No | | Monitors its own output quality | Yes | No | No | No | | Persistent memory across runs | Yes | No | Limited | No | | Reactive triggers (auto-responds to conditions) | Yes | No | No | No | | Fixes its own broken skills | Yes | No | No | No | | Zero infrastructure | Yes (GitHub Actions) | Local | Self-hosted | Self-hosted | | Reasons about tasks | Yes | Yes | Yes | Yes |

The key difference: other agents are interactive tools you use. Aeon is an autonomous system you configure and walk away from. It decides when to run, what to check, and when to bother you. It scores its own output, detects degradation, and patches failing skills without intervention.

This isn't better for everything — you still want Claude Code for writing code interactively. But for the 90% of recurring tasks that don't need you in the loop, the most autonomous agent is the one that never asks.

For a comparison against the broader agent ecosystem (AutoGen, CrewAI, n8n, LangGraph) and a list of active forks running in production, see SHOWCASE.md.

Autonomy spectrum

Quick start

git clone https://github.com/aaronjmars/aeon
cd aeon && ./aeon

aeon

Why "most autonomous agent framework"?

Quick start

Related Skills

Skills

Instance Fleet

Authentication

Bankr Gateway (optional)

Soul (optional)

Quality scoring & self-healing

Self-healing loop

Reactive triggers

Cost tracking