X-Agent

X-Agent

2026-09-21 07:59:32

X-Agent white paper lays out push from AI content generation to execution and trading

X-Agent, an onchain operating system for AI agents, released a new white paper on Sept. 21 outlining its product architecture, MCP ecosystem, business model, and the planned use cases for $XAGT. The document says the next phase of AI is not limited to generating text, images, or code. Instead, it focuses on enabling agents to understand user intent, call tools, execute tasks, and complete transactions. The project said users can create AI agents through natural language prompts without writing code. Those agents are designed to support context, memory, skills, API access, and wallet connectivity. X-Agent also described a commercial framework that links agent creation, MCP capability integration, distribution, payments, and monetization. Developers, according to the white paper, can package APIs, data, and professional services as MCP capabilities and earn revenue through per-call fees, subscriptions, or trading commissions. X-Agent said $XAGT is planned for secure runtime computing costs, LLM and API calls, agent trade settlement, MCP service payments, Premium Agent template purchases, and developer deployment. The project also disclosed that it has more than 1 million registered users, has completed more than 1.1 million autonomous tasks, and has consumed more than 84 billion LLM tokens.

400

X-Agent

2026-09-09 06:34:26

X-Agent outlines a shift for AI agents from generation to real-world task execution

X-Agent’s latest Medium post argues that the next contest in AI agents will be less about generating apps with natural language and more about completing real-world tasks across platforms and services. Using the example of booking a trip to Tokyo, the article describes an execution model in which a user states a request once and the agent handles search, comparison, confirmation, and follow-through across flights, hotels, and payments. Even so, the user remains in control of destination, budget, terms, and final approval. X-Agent says the gap between recommendation and dependable execution is still large, with infrastructure issues such as price changes, login verification, order timeouts, and partially completed bookings still unresolved. To address that, it proposes separating conversational, task, execution, and event capabilities while testing several routes including WebMCP, APIs, MCP tools, browser automation, and Computer Use. The company adds that this is still an exploratory product direction, not a live general booking capability.

830

X-Agent

2026-09-09 02:47:31

X-Agent joins Tokyo AI community pitch event, eyes deeper Japan expansion

X-Agent, a platform that lets users build runnable AI applications through natural language, took part in the AI Foundation Community Lightning Pitch held at WeWork in Tokyo, according to ChainCatcher. The event brought together entrepreneurs, developers, investors, and AI application practitioners for in-person exchanges. Discussions on site focused on AI Agents, real-world AI App deployment, and ecosystem collaboration. Participants also got a closer look at X-Agent’s product experience, which is designed to help users create runnable AI applications with natural-language inputs. X-Agent said it plans to keep expanding both its product presence and community footprint in Japan, while also exploring collaboration opportunities with local developers, project teams, and partners.

840

X-Agent

2026-09-04 02:39:20

X-Agent says the next step for OPCs is not building more products, but making capabilities callable by agents

X-Agent argues that AI coding tools and the rise of "Vibe Coding" are rapidly lowering the barrier to software development, allowing a single developer to deliver work that once required a small product and engineering team. In its latest article, however, the firm says that for one-person companies, or OPCs, productivity is no longer the main constraint. The scarcer resources are demand, trust and distribution. The article says a fast-built demo does not automatically enter real workflows used by customers or other agents. Instead of starting with a full SaaS stack that includes a website, login system, backend, subscriptions and customer support, developers can begin with one clear, practical and callable capability. X-Agent suggests packaging data analysis, market research, automation processes or AI tools as MCP services so that agents can understand what the service does, when to call it, what inputs it needs and what results it will return. That idea also sits at the center of the X-Agent AI MCP Hackathon. According to X-Agent, the goal is not to reward the most complex MCP Server, but to help developers turn real APIs, tools or services into agent-native services with clear capability boundaries, stable interfaces, verifiable deployment and long-term product potential.

940

X-Agent

2026-09-01 04:09:23

X-Agent AI MCP Hackathon 2026 to open Sept. 2 with two tracks and prizes in USDT and X-Points

X-Agent said its X-Agent AI MCP Hackathon 2026 will officially begin on Sept. 2, inviting developers and teams worldwide to submit Agent and MCP applications with practical use cases and verifiable functionality. The online global event is supported by OlaXBT and includes two separate competition tracks. The open innovation track calls for practical API-driven Agent or MCP capabilities built around AI, crypto assets, data, automation, and Agent infrastructure. A second track, the OlaXBT × X-Agent Trading Challenge, gives participating teams access to OlaXBT Nexus MCP tools for strategy development, backtesting, performance analysis, and market data, allowing them to validate trading strategies and build related Agent or MCP applications. Prize pools include USDT and X-Points. The first-place team in each track will receive 500 USDT, while the top five teams in each track will share X-Points. According to the announcement, X-Points can be used to take part in the redemption for X-Agent airdrop token $XAGT. Registration and development run from Sept. 2 to Sept. 19, judging is scheduled for Sept. 20 through Oct. 1, and winners are expected to be announced between Oct. 2 and Oct. 4.

980

X-Agent

2026-08-14 03:34:57

X-Agent opens AI MCP Hackathon 2026, with winning projects eligible for OKX.AI marketplace listing

Web3 AI network X-Agent has launched its online "X-Agent AI MCP Hackathon 2026: Build, Verify, MCPize, Monetize," opening the event to developers worldwide and to Web3 AI teams. The hackathon is designed to move projects beyond the demo stage by focusing on AI APIs and on-chain capabilities that can be called in real use, verified, and turned into sustainable revenue-generating tools. The event runs for nearly four weeks, including a five-day warm-up period and a 14-day build phase. Participants do not need to set up a complex MCP, or Model Context Protocol, framework on their own. Instead, they are asked to build core AI or crypto functions on top of APIs and submit source code. Projects that pass technical verification and security review will be standardized by X-Agent into MCP tools that fit agent architecture requirements. As a central incentive, selected winning projects may be recommended by X-Agent for listing on the OKX.AI Agent Marketplace. X-Agent said monetization can be handled through the A2MCP and x402 protocols, combined with the gas-free USDC settlement channel on OKX X Layer, allowing developers to receive pay-per-call revenue when other AI agents or users invoke their tools.

2060

X-Agent

2026-07-28 07:28:09

X-Agent open-sources xpense, an AI payment control plane tied into the OKX ecosystem

Web3 AI network X-Agent has announced the open-source release of xagentAI/xpense after completing a deep integration with OKX Agentic Wallet and launching a paid MCP tool on the OKX marketplace. The project is positioned as a payment control plane for AI agents, aimed at filling a missing control layer in autonomous spending, budget risk management, and delivery verification. According to the announcement, existing standards and tools including HTTP 402, x402, MPP, MCP, and OKX Agentic Wallet already support signing and micropayment rails, but they do not fully address the upper-layer controls required when machines spend funds on their own. X-Agent said xpense is designed to answer practical questions such as who sets spending limits for an agent, how repeated charges can be prevented, and how a system can verify that a paid service was actually delivered. The project lays out a seven-step deterministic flow covering Intent, Policy, Route, Pay, Deliver, Verify, and Account. It also adopts a dual-state-machine model that separates payment settlement from service delivery. X-Agent said the system also relies on policy-engine controls, a payment-aware router, and OKX infrastructure including TEE-based key isolation and x402 gas-free USDC settlement.

1920

X-Agent

2026-07-22 02:25:48

X-Agent joins OKX Agent Marketplace, launches three risk-analysis MCP tools

X-Agent, a no-code AI Agent operating platform built on a Web3 social network, said it has officially become a merchant on the OKX Agent Marketplace and rolled out three production-grade risk analysis tools based on MCP, or Model Context Protocol. The first batch includes Token Security Scan, priced at 0.03 USDT per call, Wallet Reputation at 0.01 USDT per call, and Portfolio Health at 0.01 USDT per call. According to the announcement, these services package X-Agent’s validated risk assessment capabilities into standardized MCP tools that other agents in the ecosystem can automatically discover and invoke. X-Agent also said it has integrated with OKX Onchain OS and OKX Agentic Wallet. The setup includes x402 native machine settlement, a no-gas USDC settlement flow based on EIP-3009 and the Coinbase x402 protocol on OKX X Layer, enabling micropayments as low as 0.01 USDT per use without pre-funding or manual approval. The company added that private keys are stored in OKX TEE, while X-Agent only receives short-session signing authorization. It also introduced Pre-Broadcast protection and an idempotent state machine to reduce repeated charges and state conflicts in autonomous on-chain tasks.

2130