Anthropic Tests "Lobster" Conway: Supports Independent UI, Webhook Activation, and Custom Extension Standards

marsbitPublicado em 2026-04-02Última atualização em 2026-04-02

Resumo

Anthropic is actively developing "Conway," a persistent agent solution designed to provide Claude with an always-on, independently running intelligent environment. It features a standalone UI instance, operating as a traditional chat interface and more of a dedicated workspace. Conway can directly control browsers, connect to external services, and integrate Claude Code for deeper code execution and task handling. It supports Webhook-based invocation, enabling external services or events to trigger automated workflows. Additionally, Conway will support for extensions through the upcoming CNW ZIP standard, allowing developers to build custom tools, UI tabs, and context handlers, similar to an app store ecosystem. This enhancement aims to transform Claude from a reactive conversational tool into a proactive, multi-step task assistant, positioning it as a strong competitor in the AI agent space and advancing the trend toward always-on AI capabilities.

Anthropic is actively developing a persistent agent solution named Conway, aimed at creating an always-on, independently running intelligent environment for Claude.

According to related information, Conway will feature an independent UI instance, moving beyond the traditional chat interface to operate as a standalone agent workspace. It will be capable of directly controlling browsers, connecting external connectors, and integrating Claude Code functionality (potentially involving Epitax-related features), enabling deeper code execution and task handling. Simultaneously, Conway supports invocation via Webhooks, allowing external services or events to trigger agent workflows, thereby boosting automated response capabilities.

Additionally, Conway will support an extension system. Anthropic is set to launch the CNW ZIP standard, which developers can use to easily build custom tools, UI tabs, and context handlers, forming an ecosystem expansion capability similar to an "app store." This will significantly enhance Claude's flexibility and scalability in handling complex tasks.

The emergence of Conway is seen as a key strategic move by Anthropic in the AI agent domain, aiming to transform Claude from a passive conversational tool into a persistent assistant capable of continuous operation and autonomous execution of multi-step tasks. It not only supports browser automation and event triggering but also strengthens code generation, execution, and problem-solving capabilities through native integration of Claude Code.

Industry observers believe that Conway has the potential to become a strong competitor to rivals like OpenClaw, driving the advancement of AI agents toward an "always-on" direction. The era where Claude can truly "show its prowess" may be just around the corner.

Perguntas relacionadas

QWhat is the name of the persistent agent solution being developed by Anthropic for Claude?

AThe persistent agent solution being developed by Anthropic for Claude is named Conway.

QHow does Conway differ from a traditional chat interface?

AConway differs by being an independent UI instance that operates as a standalone agent workspace, capable of directly controlling the browser, connecting to external connectors, and integrating Claude Code functionality.

QWhat method does Conway support to allow external services or events to trigger its work?

AConway supports being invoked via Webhook, which allows external services or events to trigger the agent's work and enhance automated response capabilities.

QWhat is the name of the extension standard that will allow developers to build custom tools for Conway?

AThe extension standard that developers can use to build custom tools, UI tabs, and context handlers for Conway is called the CNW ZIP standard.

QHow is Conway expected to transform the role of Claude according to the article?

AConway is expected to transform Claude from a passive conversational tool into a persistent assistant that can run continuously and autonomously execute multi-step tasks, moving towards an 'always-on' AI agent direction.

Leituras Relacionadas

Amidst Capital's Encirclement, Decentralization is the Sole Defense for Public Blockchains

In a landscape dominated by power and profit motives, the author argues that decentralization is not merely one desirable feature among many in blockchain design—it is the singular, non-negotiable defense against corporate and capital capture. The article adopts a Machiavellian, realist perspective on human institutions, positing that businesses will inevitably attempt to co-opt any valuable network to protect their profits and dominance. While external attacks like 51% forks are often discussed, the greater existential risk is internal capture—the gradual erosion of a protocol’s neutrality by vested interests, as seen historically with platforms like Visa and Google. The piece critiques permissioned chains, highly centralized “permissionless” layer-1s, and layer-2s without sufficient decentralization (e.g., single sequencers) as inherently vulnerable. These compromised systems, promoted by established financial players, are framed as delaying tactics to stifle truly open networks that threaten existing high-fee, inefficient business models. Real-world examples, such as closed enterprise consortiums that exclude competitors, illustrate how such systems cement oligopolies rather than foster innovation. The author concludes that while decentralized protocols like Ethereum are imperfect and costly to operate, they represent the only viable long-term equilibrium. In a market where value naturally flows to the most secure and neutral settlement layer, only maximally decentralized public blockchains can resist being subsumed by capital and powerful incumbents.

Foresight NewsHá 13m

Amidst Capital's Encirclement, Decentralization is the Sole Defense for Public Blockchains

Foresight NewsHá 13m

Who Decides the Rules of Bitcoin? BIP-110 Ignites Governance Debate

Bitcoin's governance is once again at the center of a heated debate, this time ignited by BIP-110, the "Reduced Data Temporary Softfork." This proposal aims to curb non-monetary data (like inscriptions and Runes) by introducing seven new consensus-layer restrictions over a year, such as limiting new output scripts to 34 bytes and restoring the OP_RETURN cap to 83 bytes. The controversy stems from BIP-110's fundamental shift: it moves the battle against "spam" from node relay and miner policies to the consensus layer, rendering currently valid transactions invalid. Supporters, arguing that default policy governance has failed (highlighted by Bitcoin Core v30's relaxation of OP_RETURN limits), see this as necessary to protect node resources and Bitcoin's monetary focus. Opponents, led by figures like Michael Saylor and Adam Back, warn it dangerously centralizes governance. Saylor listed 110 reasons against it, criticizing its low 55% miner activation threshold and potential for chain splits. Back emphasized Bitcoin's "permissionless" ethos, arguing no single group should impose value judgments via consensus rules. Further complicating matters, technical critiques suggest BIP-110 may be technically circumventable, and a "BlockSlop" vulnerability in its upgrade path poses a consensus risk. The debate has drawn in diverse stakeholders: miners (with pools like Ocean signaling support and Foundry polling clients), node operators (like Bitcoin Knots), and new players like corporate treasury holder MicroStrategy (Saylor), whose market influence adds a novel dimension. Ultimately, BIP-110 acts as a governance stress test, exposing the unresolved question: who decides Bitcoin's rules? It pits the authority of miners, node operators, developers, and capital holders against each other, with each side claiming to defend Bitcoin's core principles of neutrality and security.

marsbitHá 30m

Who Decides the Rules of Bitcoin? BIP-110 Ignites Governance Debate

marsbitHá 30m

Who Decides Bitcoin's Rules? BIP-110 Ignites Governance Debate

Title: Who Decides Bitcoin's Rules? BIP-110 Ignites Governance Debate A new technical proposal, BIP-110 (Reduced Data Temporary Softfork), has sparked a fundamental governance debate within the Bitcoin community. It aims to impose new consensus rules for one year to limit non-financial data (like inscriptions and Runes) on-chain, moving beyond simple node and miner policy filters to invalidate currently valid transactions. Supporters argue that default policies have failed due to workarounds, necessitating consensus-layer changes to protect Bitcoin's core monetary function from data spam. Critics, including Michael Saylor and Adam Back, contend this dangerously centralizes judgment, undermines permissionlessness, and sets a risky governance precedent. They advocate for market-based solutions like fees or Layer 2s instead. The debate exposes deeper tensions: miners are divided on activation; node operators assert their sovereignty; Bitcoin Core developers influence defaults without direct accountability; and large corporate holders like MicroStrategy now wield narrative influence. Technically, BIP-110 may not fully block data and carries a disclosed consensus bug risk. Ultimately, BIP-110 acts as a stress test, forcing the community to confront the unresolved question: who legitimately decides what Bitcoin is and how it evolves, amidst competing claims from miners, nodes, developers, and capital holders.

链捕手Há 41m

Who Decides Bitcoin's Rules? BIP-110 Ignites Governance Debate

链捕手Há 41m

Zcash's New Node Zakura Goes Live: Privacy Payments Can Reach 50,000 TPS, Aiming to Rival Visa and Mastercard

Zcash, a privacy-focused cryptocurrency, has launched a new full node software called Zakura version 1.0.0. Developed by Zcash co-founder Sean Bowe and Dev Ojha, with private ZEC donations, its goal is to enable Zcash to process over 50,000 transactions per second (TPS)—matching the scale of Visa and Mastercard—while maintaining full transaction privacy and verifiability. This addresses a key bottleneck, as Zcash currently handles only about 1 private transaction per second. Zakura is a fork of the Zcash Foundation's Zebra node. It features chain pruning and snapshots, reducing disk usage and allowing new nodes to sync in under two minutes. It also offers compatibility with the legacy `zcashd` client interface. The scalability challenge stems from the large data size of privacy proofs. Bowe's Tachyon project aims to use recursive proofs to reduce consensus-layer data needs from ~500 MB/s to ~100 MB/s. For wallet scalability, Valar Group is researching Private Information Retrieval (PIR) tech to allow wallets to fetch their data privately. Zakura supports fast block propagation and the upcoming "Ironwood" network upgrade (NU6.3), scheduled for activation around July 28th. Ironwood was created to contain a critical inflation bug discovered in the Orchard shielded pool in May 2024. The fix uses "turnstiles" to trap any counterfeit ZEC created during the vulnerability period within the shielded pool, preventing it from entering circulation and restoring supply integrity.

marsbitHá 56m

Zcash's New Node Zakura Goes Live: Privacy Payments Can Reach 50,000 TPS, Aiming to Rival Visa and Mastercard

marsbitHá 56m

Trading

Spot
活动图片