Coinbase launches Coinbase for Agents

// 1h agoPRODUCT LAUNCH

Coinbase launches Coinbase for Agents

Coinbase for Agents allows developers to connect AI models directly to Coinbase accounts or sub-accounts, enabling them to trade cryptocurrency and execute machine-to-machine payments autonomously. Designed with strict security guardrails and spending limits, the tool utilizes the x402 protocol to facilitate frictionless API and compute resource microtransactions for agentic ecosystems.

// ANALYSIS

While giving AI agents direct control over financial assets offers a fast track to autonomous machine-to-machine economies, it also raises critical security concerns around API credential theft and runaway automated trades.

* Seamless microtransactions: The x402 protocol integration allows agents to pay for API access and on-demand compute without manual subscriptions.

* Security guardrails: Support for sub-accounts and strict spending limits helps mitigate risks associated with autonomous asset control.

* Expansion potential: Although starting with crypto trading, the framework is designed to eventually support equities and prediction markets.

// TAGS

coinbaseagentcryptoweb3fintechdevtool

DISCOVERED

1h ago

2026-06-11

PUBLISHED

1h ago

2026-06-11

RELEVANCE

8/ 10

AUTHOR

brian_armstrong

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

NEWS12m ago

Pieter Levels ports Wolfenstein with Claude Fable 5

Continuing his trend of reviving classic games, developer Pieter Levels (@levelsio) utilized Anthropic's new AI model, Claude Fable 5, to port the 2001 classic "Return to Castle Wolfenstein" to the web. The AI seamlessly handled the porting process, enabling the game to be fully playable in a browser complete with multiplayer capabilities, following his recent successful ports of Quake 1 and Quake 2.

NEWS17m ago

Carmack proposes AI-optimized coding styles for weaker models

A recent thought shared by John Carmack proposes that large language models could be used to optimize coding styles and code structures specifically to make codebases more accessible and manageable for weaker models. By identifying stylistic quirks that uniquely impact transformer-based models, developers could potentially adopt new "AI-friendly" coding standards that allow smaller, more efficient models to successfully perform tasks within a codebase.

UPDATE17m ago

Perplexity integrates Deep Research into Computer harness

Arav Srinivas announced that Deep Research is now a built-in, native skill within Perplexity Computer. Users no longer need to explicitly switch into a standalone mode for Deep Research; it simply works seamlessly as part of the agent harness, marking a significant step forward for state-of-the-art AI automation.