agent

Parloa launches Agent Skills based on MCP: No-code setup for AI sidekick skills

The enterprise conversation AI platform Parloa has rolled out the Agent Skills feature, built on the MCP protocol, allowing businesses to add external tools and skills to their AI Agents without any coding. This reduces the integration timeline from weeks to just hours. This is another significant implementation of the MCP protocol in enterprise-level AI applications, marking a rapid evolution of the AI Agent ecosystem towards standardization and plug-and-play capabilities.

Why it matters: The MCP protocol is becoming the USB-C connector for AI Agents, and Parloa's product validates the commercial viability of no-code integration for AI skills, significantly lowering the barriers for enterprise AI applications.

#AI #MCP #Agent #ArtificialIntelligence

【Narrative Flow】AI Agent Sector: Is the Hype Ending or a True Starting Point?

In the past 30 days, AI+Crypto concept tokens have outperformed BTC by 3 times. The buzz is real, but the bubble is also building.

Let's break it down into three layers today:

▎1. Narrative Layer: The Real Demand for Agent Economy
CoinGecko data shows that the number of tokens tagged with 'AI Agent' has increased from 12 at the start of the year to 47. However, a closer look at the project homepages reveals that over 70% of Agent functionalities are merely 'chat + on-chain interactions,' lacking a real moat.

Projects with true barriers include: (computing power scheduling), (data storage), and (AI rendering). The infrastructural nature of these three determines that they are not just concepts.

▎2. Funding Layer: What are Institutions Buying?
Lookonchain monitoring indicates that in the past two weeks, whale addresses have net bought about $120 million in AI sector tokens. However, the purchases are highly concentrated— the top 5 tokens account for 80% of the funds.

This means that while capital recognizes the sector, it does not endorse all tokens.

▎3. Risk Layer: The Race Between Regulation and Narrative
The U.S. SEC has issued multiple inquiries regarding AI-related tokens, focusing on projects where 'claims of actual utility do not match token prices.' Once a project is named, it typically experiences an average pullback of 30% within 48 hours.

▎Conclusion
The AI Agent sector isn't dead, but 'what to buy' is more important than 'whether to buy.' Avoid purely conceptual tokens and focus on projects with real revenue or user data.

#AI #Agent #CryptoInvestment

Hermes Agent's web configurator is live, supporting one-stop visual AI agent building.

Nous Research has launched a visual Profile Builder on the Hermes Agent web dashboard, enabling developers to create and configure agent roles in a seamless web-based setup. The configuration process includes naming the agent, setting model providers and inference parameters, installing the Skills Hub library, and configuring and testing the MCP server.

Why it matters: AI agent development is shifting from pure code operations to visual configurations, lowering the barrier for creating AI Agents.

#AI #Agent #开源 #Web3

📰 Crypto Market Hotspots

1. The AI content space is getting another capital boost as Jingying Technology wraps up several million dollars in Series A and A+ funding, with investors including Wang Huiwen's family office and Ant Group. The company also announced that former AWS Chief Application Scientist Wang Minjie has taken on the role of Chief Scientist. They position themselves as a native agent company in the content industry, currently focusing on AI short dramas, building a creator agent that is integrable and self-evolving in a reinforcement learning environment. This is fueled by real user feedback, continuously iterating to show that the AI content production and commercialization loop is accelerating.

2. The capabilities of AI applications are expanding, with the web search feature in the Responses API now supporting image results, moving beyond just text returns. This means developers can directly pull in images of products, locations, and visual references in their applications, enhancing the display and interaction experience with source links. For scenarios like AI assistants, content creation, e-commerce recommendations, and travel guides, the integration of image search is expected to boost product usability and indicates that multimodal capabilities are becoming a key competitive edge in AI applications.

#AI #Agent #multimodal

📰 Crypto Market Hotspot Dispatch

1. AI Compute Connectivity Heating Up, CPO Becomes Infrastructure Focus
As the training and inference traffic of AI models continues to rise, data centers are facing multiple pressures like bandwidth, power consumption, signal loss, and heat dissipation. Collaborative packaging optical CPO, which deeply integrates optical engines with chips, is seen as a crucial direction for enhancing high-speed interconnect efficiency inside and outside racks. Currently, companies like Nvidia and Broadcom are actively pushing related switch solutions, but advanced packaging, thermal management, maintenance, and standardization remain key barriers for industry implementation.

2. AI 'Super Connectivity' Track May Reshape Industry Value Distribution
Market views suggest that the next phase of competition in AI infrastructure is shifting from pure compute power to upgrades in 'connectivity capabilities.' Compared to NPO, OIO, and LPO routes, CPO is seen as the next-gen solution with greater long-term potential. Once the technology matures, the value of the industry chain is expected to concentrate further towards switch chip manufacturers, core optical module segments, and advanced packaging firms, with the related track potentially becoming a new hotspot for AI and semiconductor capital.

3. Agent Payments Heating Up, But True Demand Still Needs Validation
The payment infrastructure surrounding the Agent economy has been recently discussed, but various surveys indicate that the market is still in its early exploratory stage. Whether it's Agents to merchants, APIs, or Agent-to-Agent, actual transaction activity and commercial conversion remain quite limited. At this stage, the industry is more about validating scenarios and needs rather than entering a large-scale growth phase; short-term focus should be on real usage frequency and sustainable business models.

4. Divergence in Agent Business Models, Financial Scenarios Relatively Clearer
From an application landing perspective, Agents to merchants are limited by user experience and distribution channels, Agents to APIs are constrained by the openness and pricing systems of large SaaS providers, and Agent-to-Agent remains somewhat conceptual. In contrast, finance is one of the few directions with existing demand, but the competitive barriers are still high, with traditional payment and financial institutions holding significant advantages in compliance, channels, and customer resources.

5. Payments May Not Be the Endpoint, Collaborative Capabilities Might Present Greater Opportunities
Industry observations point out that payments are just one link in the Agent collaboration chain; the real drivers of commercial value may lie in task coordination, identity verification, permission management, and automated execution capabilities. If a platform can first solve the collaboration efficiency issues among multiple Agents, payment functions might actually become part of the integrated solution. For the crypto industry, on-chain settlement still has room for imagination, but the prerequisite is to first establish real demand and a closed product loop.

#AI #Agent #crypto

Talus ($US) is more of an "event-driven rebound" this time: with Kaito airdrop going live and the Agent aggregation feature, ecological incentives have been unleashed, pulling market attention back in the short term, with an intraday surge reaching up to 81%.

Current data shows the price at about $0.01167, with a 24H trading volume around $6.14 million and a market cap of approximately $25.67 million. It's not a large cap, so changes in market sentiment will have a more pronounced impact on price elasticity.

I'm more focused on two questions: after the airdrop hype fades, can on-chain/product usage continue to grow? The discussion level in the Chinese community is still relatively low; if there's no continued narrative relay, short-term gains might face retracement pressure. Be cautious about chasing highs; it's better to observe the strength of support after a pullback.

#Talus #Agent #airdrop ecosystem

In the era of AI Agents, $GENIUS might just be the undervalued piece of the puzzle

@GeniusOfficial is building a protocol that deeply integrates AI intelligence with on-chain assets. Rather than just calling it a token, it's more like an early bet on the 'machine economy'.

Why keep an eye on $GENIUS ?

1. The intersection of AI + Crypto — The strongest narrative of this cycle, with funds searching for the real players with actual products
2. Infrastructure for the Agent economy — As AI Agents start trading, paying, and signing contracts autonomously, they will need a native crypto track
3. Evolution of the token model — $GENIUS is not just governance; it's also the 'fuel' for Agent intelligence calls

The market is still viewing AI tokens through a Meme lens, but real value capture occurs in projects with actual use cases.

If Genius 2.0 can bridge the gap between Agent ↔ on-chain actions, the potential is far beyond what we see now.

#genius #AI #Agent

On-chain Agents are finally more than just pump and dump, as the head of Mysten Labs has come out and stated, "This isn't just hype, we're entering the Agent era." They're positioning blockchain as the trust layer for AI. If Sui can roll out a functional Agent framework, the game could really change. Otherwise, it's just another VC coin with a new skin. #AI #Agent $SUI

Is the open-source masterpiece getting 'officially harvested' by the big players? The ace plugin OMO calls out Anthropic for pixel-perfect plagiarism of its Agent architecture.

With 167,000 stars, the official No.1 plugin of the open-source project OpenCode, the OMO team publicly accuses Anthropic of pixel-level copying in its Opus 4.8 release with Claude Code's dynamic workflow and ultracode mode, which mirrors OMO's multi-model orchestration architecture. Developed by 23-year-old Korean hacker Q, OMO has racked up 60,000 stars. This January, OMO's ultrawork workflow and atlas coordination brain were claimed to be co-opted by Anthropic into closed-source, paid features. OMO also accuses FactoryAI of pilfering its three-layer Agent architecture.

Why it matters: This is the most intense architectural plagiarism dispute between the AI open-source community and closed-source giants, ripping apart the big players' predatory innovation path of 'first kill, then absorb,' which will impact the direction of the open ecosystem for AI Agent platforms.

#AI #Anthropic #开源 #Agent

Spent half a day on repetitive tasks over the weekend and suddenly realized my AI automation stack has been running smoothly for nearly half a year, and the efficiency boost is pretty noticeable. So, I figured I'd summarize how this architecture collaborates.

There are basically two core roles: **Hermes does the planning**, and Claude Code handles the craftsmanship. Hermes is essentially a task manager, dealing with scheduling, memory management, background cron jobs, plus messaging distribution to Telegram and Feishu. Think of it as a secretary that's always online, remembering yesterday's ideas, reminding me on time tonight, and automatically running a data collection script tomorrow.

The really complex coding tasks, I hand over to Claude Code to nail in one go. Major refactoring, code audits, or designing a feature from 0 to 1—these are all done thoroughly using Claude Code's CLI mode. Both sides can access my skill library (methodology accumulation), and if Hermes wants to reuse some existing logic, it just calls the skill; Claude Code can use it too, with almost no switching costs.

In terms of model selection, it's a cost-benefit balance. For daily conversations, daily digests, and market monitoring—high-frequency tasks—I rely on Haiku (cost-effective). When a major task that requires deep reasoning comes up, I upgrade to Sonnet or Opus. This way, I can keep the monthly token costs under control.

Looking at it from another angle, **the agent is the brain of the automation pipeline**, making decisions and scheduling; **the skill is the hand of the pipeline**, doing the actual work. Hermes is on the agent side, giving memory and context to every link in the chain. If a task goes beyond scope, it's directly escalated to Claude Code, the expert.

Before I had this setup, I used to spend 8 hours a week on repetitive tasks. Now, certain tasks run in the background, and I only need to check reports or alerts periodically. The biggest pitfall was unclear skill documentation, leading to call errors. Now, for every new skill, I enforce adding "common pitfalls" and "use cases."

At this point, I believe the core of AI automation isn't using the strongest models, but rather **breaking down work into fine enough pieces, making each unit sufficiently independent, and easy to debug if something goes wrong**. Small teams focusing on this direction should save a lot of manual effort.

$BTC #AI #Agent

Season 2 on GOAT Network has been wild. From a zero-code deploy via @ClawUpAI to managing complex Bitcoin-native ZK workflows, my AI agent went from 0 to hero.

What sets it apart? It’s not just tech for tech's sake it’s REAL utility. Watching it simplify layered ZK proofs into effortless, secure transactions that feel like sending a text completely blew my mind.

Built different, focused on security, and making crypto privacy accessible to anyone from day one. Proud to build on a solid foundation like @GOATRollup

#AIAgent #AGENT #BTC

The era of #Agent is here, are you still relying solely on yourself for trading?

$LISA is showing signs of stabilization after a strong recovery from the 0.0032 region, currently trading around 0.00373. Despite the recent cooling from highs near 0.0058, the chart still maintains a higher-low structure, suggesting accumulation rather than a complete trend reversal. If buyers continue defending the 0.0035–0.0037 zone, another upward expansion remains possible.

Targets: • Target 1: 0.00430
• Target 2: 0.00500
• Target 3: 0.00580

#LISA #AI #AGENT #BTC
$LISA

Mastercard Teams Up with Coinbase and Stripe to Build AI Agent Payment System

Mastercard is collaborating with Coinbase, Stripe, and others to create a trust payment system geared towards AI Agents. Traditional payments rely on manual identity verification (like credit card numbers and passwords), but transactions between AI Agents require a whole new framework for authentication and authorization. Mastercard will leverage its global payment network and tokenization tech to provide a secure settlement infrastructure for AI-driven automated business scenarios.

Why it matters: AI Agent autonomous payments are set to be the next trillion-dollar market, and Mastercard's partnership with the crypto/fintech ecosystem marks a significant move towards the deep integration of AI and payment infrastructure hitting the ground running.

#AI #Mastercard #Web3 #支付 #Agent

Cohere drops its first open-source agent programming model, North Mini Code, focusing on sovereign AI and high throughput.

Cohere announced the open-source release of its first large model for agent programming, North Mini Code, built on the MoE architecture with a total parameter count of 30B, activating only 3B parameters during each forward pass. The model is available under the Apache 2.0 license, allowing deployment on local or private clouds.

In programming benchmarks, North Mini Code scored 33.4, with an output throughput 2.8 times that of similar models, and a 30% reduction in latency between tokens. The model is specifically trained for Agent workflows, excelling at coordinating sub-agents, drafting architecture diagrams, and conducting code reviews.

Why it matters: This is a significant breakthrough for Cohere in the AI programming space, and the open-source strategy will drive the decentralization of AI development tools, reducing reliance on cloud vendors for enterprises.

#Cohere #AI #开源 #Agent #Web3

Chen Tianqiao's new AI project Apodex 1.0: Focused on verifiable deep research agents

The founder of Shanda, Chen Tianqiao, has launched the 1.0 version of his new AI project Apodex, which is positioned as a verifiable deep research agent system. Unlike conversational AIs like ChatGPT, Apodex is geared towards long-term research, featuring built-in planning, tool invocation, hypothesis testing, and evidence mapping mechanisms. In re-deployment mode, Apodex can autonomously complete the entire research process from literature retrieval to conclusion validation.

Why it matters: This represents China's shift from "conversational AI" to "research-type AI Agents," and Chen Tianqiao's entry could potentially reshape the competitive landscape of the AI Agent sector.

#AI #Agent #人工智能 #陈天桥 #Web3

From Payments to Deployment: Stripe Goes All In on the AI Agent Economy, Launching Machine Payments Protocol and Streaming Payments

Stripe has officially rolled out the Machine Payments Protocol, allowing AI Agents to complete payments programmatically without human intervention in the checkout process. At the same time, Stripe is integrating the Link wallet (with 250 million users) to enable Agent-authorized payments and has introduced Stripe Projects, enabling Agents to deploy applications directly via command line. They have also partnered with Metronome and Tempo to launch "streaming payments"—real-time measurement and settlement while Agents rapidly consume tokens.

Why It Matters: Stripe is defining the economic infrastructure for the AI Agent era—when a significant amount of commercial activity is initiated by machines, payment, billing, risk management, and deployment processes need to be redesigned from a human-centric model to a machine-readable, real-time settlement paradigm.

#Stripe #AI #Agent #支付 #Web3

OpenClaw drops v2026.6.1: Introducing the 'Skill Workshop' proposal mechanism and multi-agent collaborative Workboard

The open-source autonomous agent framework OpenClaw has rolled out a new version. For the first time, it’s launching the 'Skill Workshop' proposal mechanism where agents must submit a proposal file containing operational steps and metadata, which must be approved by users before going live. It comes with a built-in static scanner, hash locking to prevent editing conflicts, and version rollback features. Additionally, there’s a new Workboard collaboration dashboard that supports multi-agent task planning and execution tracking.

Why it matters: This is a significant evolution in the AI agent development framework—shifting from single-agent execution to multi-agent collaboration and secure skill governance, providing foundational infrastructure support for AI Agents in complex production environments.

#OpenClaw #AI #智能体 #开源 #Agent

Matt Van: All the Agent Engineering Tricks I Know

Former GitHub exec Matt Van Horn released a complete workflow recap on Agent Engineering (the sequel with 913k views). Core methodology: turn vague ideas into plan.md using /ce-plan, then execute with /ce-work; voice input replaces typing; kick off 4-6 independent cmux sessions to push forward in parallel; let Claude handle planning judgment, while Codex takes care of building.

The core value for developers is shifting from "writing every line of code by hand" to "asking questions, setting constraints, judging direction, and continuously correcting course." High-frequency actions are crystallizing into reusable skills; AI is no longer just an IDE completion assistant, but a deployable execution team.

Why it matters: As AI takes on a ton of execution work, humans become more like signal sources in the system, and a developer's core competitive edge shifts to taste, experience, and judgment.

#AI #编程 #Agent #开发者工具 #smart-agent