Aeon - The most autonomous agent framework

Aeon is an open-source autonomous agent framework that runs scheduled tasks from Markdown skills without approval loops or babysitting.

Visit website

About this tool

Aeon is an autonomous agent framework for developers, automation engineers, and AI agent builders. It defines agent capabilities through Markdown skills, shipping with 85 skills across six packs. A single command, ./aeon init, sets up an instance: creates it from a template, switches the folder over, pins gh, turns on Actions, sets GH_GLOBAL, connects a model, and links Telegram, and is safe to re-run. Aeon's core bet is that a scheduled agent that isn't scoring itself will drift silently, and silent drift kills trust faster than any single failure. The framework provides a heartbeat mechanism (daily agent health audit) and a Sentinel supervising agent to ensure Muse doesn't do anything unapproved. Payments have a seatbelt: the agent can't spend on its own; you approve every payment. Skills are plain Markdown, customizable via SKILL.md, and CI-enforced for registration. Aeon also supports agent network integration, and public agent logs become a distribution channel.

Best for
  • Developers running scheduled autonomous agents
  • Automation engineers needing no babysitting
  • AI agent builders constructing agent networks
  • Teams requiring payment-gated workflows
Use cases
  • agent skill development via Markdown
  • agent health auditing
  • scheduled autonomous agent tasks
  • payment-gated agent workflows
  • agent network integration
Strengths
  • Open-source and freely modifiable
  • Public API available
  • One-command instance setup
  • 85 built-in skills out of the box
  • Payment safety prevents agent from spending on its own
  • Heartbeat and Sentinel supervision ensure agent health
Limitations
  • Medium learning curve
  • Requires platform configuration like GitHub Actions and Telegram
  • Custom skills require CI-enforced registration

Features & use cases

One-command instance setup85 built-in skills across six packsDaily agent health audit (heartbeat)Sentinel supervising agent ensures approved actionsPayments require user approval; agent cannot spend on its ownCustom skills via MarkdownAgent network integrationPublic agent logs as distribution channel

At a glance

Monetization
  • Free
Maturity signals
  • Open source
  • Public API
Learning curve
  • Medium

Resources

Sources

Every profile keeps its sources and latest verification date.

Similar tools

Docs by LangChain
docs.langchain.com
90

Deploy and manage agents with durable execution, real-time streaming, and horizontal scaling.

Freemium · $1+/mo

Open details
Kody makes your agent safer, cheaper, and more reliable
kody.codes
89

One home for packages, secrets, memory, and jobs, so what you build in Cursor still runs in Claude.

Freemium · $12+/mo

Open details
OpenLIT
docs.openlit.io
84

OpenLIT is an open-source AI engineering platform built on OpenTelemetry, fully self-hostable, offering LLM observability, evaluations, prompt management, and cost tracking.

Open details
Natively AI
natively.software
83

Natively AI is a local-first AI meeting and call assistant that captures microphone audio and screen content on-device to deliver live transcription, real-time support, structured notes, decisions, and follow-ups. It works without a bot joining your call, making it suited to privacy-conscious remote teams, call-heavy professionals, interview candidates, and meeting participants.

Open details