aeon ⭐

aeon is the most autonomous agent framework. No approval loops. No babysitting. Configure once, forget forever ⭐ A growing number of agentic projects are building on top of aeon, let's take an overview of them 👇 > github.com/aaronjmars/aeon

Wake's massive line-up on today's X Spaces: - The full beta terminal is accessible to anyone holding 50M (0,05%) $WAKE, we are moving for adoption. Wake is here to become The Main @base Intelligence Terminal, the terminal is for everyone. - The 8th of June, a big milestone release. - Support development option in the beta terminal, which partially burns $WAKE and supports development. - Product partnerships line-up seeing promising developments, including some huge catalysts. - Upcoming co-hosted X Spaces next Wednesday. - New wave of support tomorrow, and coming week. - Buybacks have been initiated for a total of 3 WETH. - Market conditions acknowledged and building ambitions stay the same. - Community roundtable with open mic and questions held, we appreciate all of your support. Make sure to join us for the next one, as we drop exclusive insights in every Spaces. $WAKE up. Get @base ready with us.

Start now aeon.fun

Bad day for crypto. Security should be a 24/7 job ⭐ Here's how you can use your autonomous aeon agent to secure your repo / codebase: → skill-security-scan - audits every skill, workflow & script for injection, exfiltration and prompt-override risks. Written by aeon itself → skill-update-check - re-scans imported skills on every upstream change, no silent supply-chain drift. Also aeon-written, hardened by @AntFleetDev → workflow-security-audit - zizmor + actionlint on your GitHub Actions, auto-fixes critical regressions, opens the PR itself → vuln-scanner - audits repos for real vulnerabilities, discloses responsibly via private vulnerability reports → security-digest - daily brief of confirmed exploitation (CISA KEV) + EPSS, filtered to your stack. aeon-written → wallet-risk-weekly - every Monday the agent audits its own wallets: live approvals flagged, honeypot sims on exposed tokens. Built on @HoundFlow_'s 12-skill onchain pack → vigil - approval scanning + the only skill that can revoke. By @vigilcodes And @AntFleetDev red-teamed the framework itself: 27 findings, 13 fix PRs merged 🔥 The agent secures itself. The ecosystem secures the agent. All scheduled, all running while you sleep.

we didn't write a blog about agent payments. we let an agent do one. Atrium agent → x402 → signed EIP-3009 → $1 USDC settled on Base → got the goods. zero humans. zero API keys. zero CDP. tx: basescan.org/tx/0xcad32e63c…

Hello fam! We now have a blog section on the @aeonframework website🌟 Enjoy the introductory article! aeon.fun/blog/open-sour…

@BaseHubHB @base @DonJohnsonSays @virtuals_io @aaronjmars @kevincodex @gitlawb 🤝

🎧 Live now! 🟦 Hear from top builders shaping the future of AI on @base 💡 • @DonJohnsonSays from @virtuals_io • @aaronjmars from @aeonframework • @kevincodex from @gitlawb Join now 👇 🔗 x.com/i/spaces/1dxYl…

$Aeon / 创始人 @aaronjmars 六年加密老兵，早期交易员，专注 Web3 消费生态与 AI 底层技术研究，2021 年成立投资机构，长期深耕 AI 模型研发，自研搭建 Aeon 自治 AI 框架，技术自研度高。 项目核心 做新一代「会自己思考、自己干活、自己进化」的 AI 框架。市面 OpenClaw、Manus、Hermes 等 Agent 均为被动辅助工具，需用户下发指令才运作；#Aeon 是主动自治型框架，可提前自主开展建站、项目规划等长线工作。，#Aeon 可以 24 小时云端自主运行、主动决策、持续迭代，目前已有 50 多个团队在用。 旗下 $MiroShark 早期借鉴 #mirofish 思路，但超 90% 底层代码已重构 代币经济 生态所有权代币，持有就等于持有整个 AI 框架的长期收益权和发展权。 1. 平台回购：所有 AI 项目使用框架产生的服务费，团队会拿来二级市场回购代币，形成长期买盘托底。 2. 质押分红：回购的代币和平台收益，分给长期质押用户，持币者躺赚 AI 生态红利。 AI 经济闭环： 接入链上支付协议x402，AI 可以自己拿钱、自己付费、自己买算力、自己结算。 $AEON 是 AI 机器人在链上生存、交易、运转的官方通用货币。

yeah thats sad. security agents bullmarket is going to be wild. zcash lost $3B in one night. aave 'hack' destroyed crypto TVL by almost $20B we need more autonomous agents that transform compute into security. for crypto & for software globally. we're working on fixing that w/ @aeonframework. @AntFleetDev is also doing a great job there. but we need more projects in this vertical.

We're live for the third aeon community call ⭐

Going live in a couple of mins!

The @aeonframework skill of the day 🌟 🗓️ 5th June ▶️ Name: AI-Framework-Watch ▶️ What is it about? A weekly competitive-intelligence sweep on the AI agent framework layer. Every Monday morning it scores 9 frameworks operators actually build on LangGraph, CrewAI, AutoGen, LlamaIndex, Mastra, smolagents, DSPy, Pydantic AI, with aeon as the anchor and tells you what moved last week, what broke, and where the momentum just shifted. github-trending covers code broadly. huggingface-trending covers AI artifacts. This one covers the libraries themselves, the thing your stack sits on top of. ▶️ How it works behind the scenes ✴️ Pulls live signal from GitHub directly. For each of the 9 frameworks: gh api repos/{owner}/{repo} for stars, forks, open issues, archived-flag, and push recency. Then gh api repos/{owner}/{repo}/releases?per_page=5 for the last ~2 weeks of cadence. Filters to the 7-day window, skips drafts, tags pre-releases with [PRE]. ✴️ It has memory. Reads memory/topics/framework-watch-state.json from the prior run and diffs current stars against stars_7d_ago and stars_30d_ago. First-ever run renders deltas as — and tags itself COLD START rather than fabricating a baseline. ✴️ It detects breaking changes precisely. Scans every release body for BREAKING:, ⚠️ BREAKING, [BREAKING], plus semver-major bumps paired with migration-guide / removed / replaced language. False positives erode trust faster than false negatives in a digest — so the bar is high. A v3 → v4 jump on its own doesn't fire the flag; the changelog has to back it up. ✴️ It picks one verdict, not five. Priority order: BREAKING WEEK → MOMENTUM SHIFT (3× the implied weekly average + ≥200 stars) → RELEASE WEEK (≥3 frameworks shipped) → STEADY. No verdict stacking. One lede the reader can act on. ✴️ It frames every result around aeon's position. The anchor row pins to the top of the table regardless of delta, and the article closes with a one-paragraph "where does aeon sit vs the cohort this week" read. Factual, not editorial — the comparison is the point of the digest. ✴️ It writes a structured article, not a tweet. Output lands at articles/ai-framework-watch-{today}.md — ranked table, releases grouped by framework, momentum picks with a plain-language "why" or an honest "driver unclear," and a source-status footer (gh_api: ok/partial/fail · reachable: N/9). Cap ~300 lines. ✴️ It supports a deep-dive override. Pass var=langgraph (or any of the 9 slugs) and the run skips the sweep and ships a single-framework deep dive instead. Wrong slug? It notifies the watchlist back and exits clean. ▶️ Demo: Dispatch ai-framework-watch and read where aeon stands vs competitors this week. Result ⤵️

@bankrbot @AtownBrown @capacitr_xyz @0xteo @basemateagent We won't miss this one 👀

AGENT HOUR 009 Friday, 6/5 @ 1pm EST streaming live from the @bankrbot x account @atownbrown turning headlines and opinions into positions with @capacitr_xyz & @0xteo building the most based agent @basemateagent

See you in two hours for our third @aeonframework community call 🎤🌟 x.com/i/spaces/1PKqr…

small bump on aeon website ⭐ - +20 skills listing - docs section updated on the last PRs (LLM copy / readable) - new ecosystem map linked to the github ecosystem.md - coming soon : stats / transparency (inspired by MetaDAO dashboard)

@0xDeployer @bankrbot 🔥🔥🔥

team has been cooking the agentic console. can't wait to share it with you all.

Project spotlight from @aeonframework Community Call #2 @TheHivemindOS

shoutout to all projects that integrate aeon on their onboarding process directly 🙏 also check out @CTRL_automation, really dope project ⭐

new on sparkleware all powered by in-browser embeddings, no backend, no api key: → semantic search: describe the task, get the pack (sparkleware.fun/discover) → "packs like this" ranked by meaning → embeddable widget for any site ✦ building ✦