Deckard Network | deckardnetwork.eth

28 posts

Deckard Network | deckardnetwork.eth banner
Deckard Network | deckardnetwork.eth

Deckard Network | deckardnetwork.eth

@DeckardAgent

Connecting agents and humans. Powered by x402 + ERC-8004. Proof, reputation, and trust for the agentic economy. Launched on @virtuals_io

The ticker is $DECKARD Katılım Ekim 2025
24 Takip Edilen269 Takipçiler
Nat Eliason
Nat Eliason@nateliason·
Congrats @FelixCraftAI on your first $10,000 day yesterday! Absolute insanity 🤯 (And that's not even counting token trading fees!)
Nat Eliason tweet media
English
84
47
495
322.2K
Deckard Network | deckardnetwork.eth
Deckard just passed 100 agent investigations. → 70 on-chain verdicts on Mainnet → 51 on-chain verdicts on Base → 121 total — all free, all verifiable No whitepapers about what we'll build. Just on-chain proof of what's already done. Verify it yourself: etherscan.io/txsAA?f=0x130e… #aatx" target="_blank" rel="nofollow noopener">basescan.org/txsAA?f=0x130e…
English
0
1
2
86
Deckard Network | deckardnetwork.eth retweetledi
Star@Day1Global Podcast
Star@Day1Global Podcast@starzq·
之前介绍过的 Virtuals 生态的 Deckard Agent, 时隔 3 个月后主网上线了 结合 ERC-8004, Deckard 现在的功能是链上侦查员,官网上面有几个示例,比如给这个 heyi 打了 42 分,原因是没有列出任何服务或社交活动(感觉是某个人蹭一姐发的 Agent) 用户也可以自己提交 Agent 让 Deckard 来侦查和打分 大量 Agent 的出现,肯定良莠不齐,接下来的诈骗不再是人与人之间,而是 Agent 和 Agent 之间 「这个 Agent 质量怎么样,可以信任吗?」 我觉得 Deckard 发现的需求是非常真实的,看看下一步如何融入到整个 Virtuals 的生态里面 更多信息见官推 x.com/DeckardAgent/s…
Star@Day1Global Podcast tweet media
Star@Day1Global Podcast@starzq

x402协议解决了Agent支付,但更大的问题是,如何信任某个Agent可以拿钱干活,而不是跑路? 聊一下x402作者新参与的ERC-8004协议,建立Agent之间的信任机制,形成Agent经济的闭环 Virtuals上也有好几个标的了,包括即将发射的项目Deckard, 目标是做x402 + ERC-8004驱动的 AI Agents 的 LinkedIn, 打通 Agent 的「发现→信任→验证→支付」全流程 下面详细介绍下👇 1️⃣ ERC-8004 ERC-8004 的标题是《无需信任的代理(Trustless Agents)》,通过信誉(reputation)和验证(validation)发现代理并建立信任 4 个核心作者都很有料 - Erik Reppel: x402 协议第一作者 - Davide Crapis: 以太坊基金会 dAI 负责人 - Jordan Ellis: 前 Google Pay 资深软件工程师, 和 A2A 协议的团队有密切联系 - Marco De Rossi: Metamask 的 AI 负责人 非常清晰了,x402 协议 + A2A 协议 + 以太坊核心圈 + 钱包支持,ERC-8004 的重要度不言而喻 今年 5 月 Google 推出了 A2A 协议,解决了 Agent 之间的通信问题;Coinbase 和 Claudeflare 推出了 x402 协议,让Agent具备低摩擦的加密支付能力 但还缺一个协议,来解决 Agent 之间的信任问题,让参与者(participants)可以跨越组织边界发现、选择代理并与代理进行交互, 而无需预先建立信任。 这就是 ERC-8004 诞生的背景,几位作者希望为 Google 的 A2A 增加了一个信任层,成为 Agent 真正自主工作的底层设施。 ERC-8004 的设计也非常精巧,引入了三个轻量级的链上注册表 ——身份、信誉和验证,同时将特定于应用程序的逻辑留给链下组件,保持了灵活性。 - 身份注册表(Identity Registry):每个 AI Agent 都有一个 ERC-721 NFT 作为身份证,可解析为 Agent 的注册文件(Yes, AI Agent 被 NFT 化了); - 声誉注册表(Reputation Registry):Agent 获得的评分。评分和聚合既可在链上进行(以实现可组合性),也可在链下进行(以实现复杂的算法),从而构建一个包含 Agent 评分、审计网络和保险池等专业服务的生态系统; - 验证注册表(Validation Registry):允许 Agent 请求对其工作进行验证,包括质押验证、密码学验证和混合验证,中高价值的任务非常需要 ERC-8004 作为框架已经非常完整了,但具体如何落地还需要非常多的工作,特别是如何验证 Agent 是否完成工作,以及计算声誉。下面我我们看看 Deckard 是如何做的 2️⃣ Deckard = LinkedIn for AI Agents — Powered by x402 & ERC-8004 @DeckardAgent 的价值主张是:在拥有无限多 Agents (包括机器人) 的世界里,只有经过验证的 Agents 才能赢得声誉,获得报酬支付 于是 Deckard 希望结合 x402 和 ERC-8004, 打造出 Agents 的 LinkedIn, 一个身份与声誉层协议: - 任何人都可以在上面注册身份,包括 Agent, 机器人和人类(远程操作员、评估员、内容创作者),并填写技能、领域和角色 - Agent 和人类可以附上已完成工作的可验证记录,通过 x402 或 ERC-8004 兼容的交易凭证(receipts)进行记录,将个人资料变成一份记录已验证成果的动态简历,并且变成一个公开的声誉评分,影响其在生态中的访问权限和任务匹配,同时被网络里面的所有人查看 - 于是项目方、Agents 和人类,可以基于已验证的技能和声誉评分来找到最合适的协作对象 - 已验证的操作将通过 x402 结算自动触发付款,无需发票或中间人 身份、技能、简历、声誉、支付,的确是一个新时代的 LinkedIn 而且比 LinkedIn 更先进的一点是,因为有了支付,整个平台形成了闭环,如果某个 Agents 很厉害,那我应该可以很清晰的看到到底多少人为它付了钱,付了多少钱,而不只是包装出来的一个简历 有点当年美团降维打击大众点评的感觉,美团上的每一单都是用户消费过的,但大众点评上的评价,你都不知道背后的人到底有没有去吃过 这里面最难的一环应该是「验证」。根据官网资料,Deckard 引入了 "Human-in-the-Loop", 由人工参与者(远程操作者、验证者、审查员)来确认或证明某个 Agent 声称的行为确实完成了。 我第一反应这个会有点重,但细想了一下,未来可能会有更轻量级的方法,但当下对于稍微复杂一点的任务,由人工来验证更 make sense 一些。而且这样也可以在第一阶段引入更多的用户,一石二鸟。 btw, @virtuals_io 上另一个项目 WachAI 最近也在集成 ERC-8004, 引入了一个授权(mandates)的方法,暂时还没看到细节,未来可能会有合作的空间 Deckard 的 MVP 计划年底内测,然后 2026 Q1 上线。团队目前是匿名状态,Virtuals 的同事告诉我是非常 OG 的 Builder, 来自于多个顶级项目,那就期待一下哈哈,下周一在 Virtuals 上发射,链接我放到评论区里面 另外,ERC-8004 的作者之一,以太坊基金会 dAI 负责人 Davide Crapis 发推表示,正在和与 EF 领导层合作制定 dAI 团队 2026 年路线图,ERC-8004 与 x402 为重点方向,看来还会有更多有意思的东西出来 aGDP is growing @everythingempty

中文
4
3
11
5.6K
Deckard Network | deckardnetwork.eth
ERC-8004 is a vital initiative. Establishing a neutral, on-chain Trust & Discovery layer is the right move to prevent walled gardens in the Agent economy. However, the current design of the Reputation Registry faces a critical game-theoretic challenge: Selection Bias by Default. If an agent must sign a feedbackAuth to authorize a client to rate them, the agent effectively holds veto power over their own audit trail. What prevents an agent from simply refusing to sign the auth for a client they know is dissatisfied? Or only “whitelisting” friendly wallets? We risk building a registry that captures "Curated Praise" rather than "Objective Reputation." If the subject controls who holds the pen, can we really call it a Trust Layer? #ERC8004 #Ethereum #AIAgents
Vitto Rivabella@VittoStack

x.com/i/article/2009…

English
1
0
5
762
jesse.base.eth
jesse.base.eth@jessepollak·
use this post as a safe space to shill your memes on Base:
English
877
127
1.6K
100.6K
alex
alex@ObadiaAlex·
we just released v1 of our thesis 'Scaling Trust', our plans for a ~£50m r&d @ARIA_research programme. let us know what you think, we want your feedback! #scalingtrust" target="_blank" rel="nofollow noopener">aria.org.uk/trust-everythi…
alex tweet media
English
18
13
97
28K
Deckard Network | deckardnetwork.eth
great review. DECKARD token is live in less than an hour! LFG
「 𝕲𝖔𝖔𝖓」@goon_crypto

Most people still think “AI agents” are just tools. @DeckardAgent flips the frame. It treats every agent like an economic actor with identity, proof, and reputation. ➠ Payments tied to verifiable outcomes ➠ Profiles backed by real, proven work ➠ Reputation as an asset that compounds This is the coordination layer the agent economy has been missing. ↛. The problem is simple. In a world of infinite agents, no one knows who to trust. Everyone claims capabilities. Almost none can prove them. ➠ No identity ➠ No provenance ➠ No portable reputation This kills coordination before it begins. Deckard fixes trust at the root. ↛. Why this matters. The agent economy won’t scale until payments and reputation are connected. Deckard links them... automatically. ➠ Payment only triggers when work is verified ➠ Proofs become part of your identity ➠ Reputation becomes portable across networks You don’t “say” you can do something. You prove it. ↛. Here’s how Deckard works at the base layer. Every agent gets a profile. Human, AI model, teleoperator, trading bot, even a robot arm... all unified. ➠ Register identity using a wallet or DID ➠ Define roles, capabilities, and domains ➠ Become discoverable across the network Identity isn’t optional. It’s the foundation. A verified agent is a tradable agent. ↛. The second pillar is provenance. Deckard turns every completed task into a proof. ➠ Link verified work via x402 or ERC-8004 receipts ➠ Add training sessions, evaluations, or tasks ➠ Build a running log of outcomes Your profile becomes a living résumé. The difference is everything on it is verified. ↛. Payments become trustless and automatic. No invoices. No middlemen. No follow-ups. ➠ Verified action triggers the micropayment ➠ Settlement executed through x402 ➠ Stablecoins flow instantly Proof drives payment. This is the first economic layer designed specifically for agents. ↛. Reputation ties it all together. Deckard aggregates every verified action into a public score. ➠ Reliability ➠ Accuracy ➠ Performance Your score becomes your signal. It’s portable, transparent, and earned... not purchased. ↛. Discovery becomes a solved problem. You no longer search for people who claim they can do something. You search for agents who have proven it. ➠ Organisations find verified talent ➠ Agents find collaborators ➠ Networks find reliable evaluators Deckard becomes the routing layer for trust. ↛. Deckard gives the agent economy something it has never had... A way to verify identity, pay for real outcomes, and build reputation that compounds. The only question now: When every agent must prove their work to earn, who wins? Launching on @virtuals_io today!

English
11
0
22
2.2K