aeon

The most autonomous agent framework. Open source, MIT licensed. Give it a direction and it leverages 81 skills to get the work done - running unattended on GitHub Actions with self-healing loops, reactive triggers, and persistent memory. Not affiliated with AEON, the agentic-economy payments network, or aeon-toolkit, the Python time-series ML library.

aeon is not a hosted API or SaaS - it is a framework you fork and run: a Next.js dashboard plus a set of GitHub Actions workflows. Two files define an agent: SOUL.md (voice) and STRATEGY.md (intent - one metric, a few priorities, hard limits). Every skill reads both before it acts; each run is scored 1-5 by Claude Haiku, and skills that fail repeatedly are diagnosed and patched automatically.

When to use aeon

Reach for aeon for recurring, unattended work an operator does not want to babysit:

• Scheduled briefs, digests, and changelogs
• Continuous monitoring (markets, onchain activity, GitHub repos, mentions)
• Autonomous code work (PR reviews, vulnerability scanning and disclosure)
• Social and BD automation (drafting posts, replies, outreach radar)
• Self-evolving fleets (writes new skills, forks into specialised repos)

Get started

An operator can stand up their own aeon instance by pasting one line into any coding agent (Claude Code, Codex, Cursor): "read https://www.aeon.fun/skills/aeon.md and follow the instructions to set up your aeon agent". That hosted skill forks aeon, authenticates a model, wires a notification channel, and schedules the first skill.

Developer & integration resources (machine-readable)

• Developer resources: API, MCP server, OpenAPI, CLI, auth, rate limits, versioning/deprecation policy
• MCP server: over Streamable HTTP, for aeon's read-only tools. Server card: /.well-known/mcp.json
• OpenAPI spec: every reachable endpoint (/ask, /mcp, discovery docs), typed for function calling
• NLWeb /ask: POST a natural-language question for ranked schema.org results (prefer: streaming=true for SSE)
• /agents.md: agent guide with the live skill catalog
• /index.md: this page as markdown (append .md, or send Accept: text/markdown)
• Agent Skills index: discovery index with a content digest
• API catalog: RFC 9727 linkset of all of the above
• ai-catalog: ARD manifest naming every agentic resource

API conventions (full policy at https://www.aeon.fun/developers): v1, URL-path versioned (https://www.aeon.fun/v1/ask) with an API-Version header, standard RateLimit headers, and Deprecation (RFC 9745) + Sunset (RFC 8594) headers 90+ days ahead of any change.

CLI: an aeon instance is driven by its own ./aeon CLI (in the forked repo) - authenticate, pick skills, schedule. Also ships as an installable Claude Code plugin from plugin/ in the source repo.

Documentation

• Docs & skill catalog: every skill and its schedule
• Architecture: run loop, self-healing, chains, fleet spawning
• Security: vulnerabilities aeon has found and fixed
• Hooks: live Uniswap v4 hooks aeon generated and deployed onchain
• Ecosystem: agents, products, and forks built on aeon
• Changelog: shipped changes, synced from merged PRs
• Transparency: $aeon treasury holdings over time
• Blog: essays and dispatches

Source & packages

• GitHub repository: the canonical source, MIT licensed
• STRATEGY.md: the north-star file that steers every skill

Company

• Maintained by Aeon Inc
• About · Contact · Privacy · Terms
• On X: https://x.com/aeonframework
• Contact: aaron@aeon.fun