Google donates Agent Payments Protocol (AP2) to FIDO Alliance, releases v0.2 with 'Human Not Present' payments

Google has donated the Agent Payments Protocol (AP2) to the FIDO Alliance, an industry association focused on open security standards. Alongside the transfer, Google released AP2 v0.2 on GitHub, which introduces critical updates for autonomous transactions, including support for 'Human Not Present' payments — enabling AI agents to execute payments securely without direct user intervention, based on pre-authorized instructions.
The 'Human Not Present' feature allows agents to autonomously perform time-sensitive transactions, such as purchasing limited-run tickets the moment they go on sale, without requiring the user to be present to approve each step. This is built on pre-authorized user instructions, ensuring the agent acts within defined bounds.
AP2 v0.2 also helps drive the Verifiable Intent standard, co-developed with Mastercard and also being donated to FIDO. Verifiable Intent creates a tamper-proof log of user-authorized agent actions, providing accountability and auditability for autonomous transactions.
By transitioning ownership to FIDO Alliance, Google aims to ensure AP2 remains platform-agnostic and community-led, accelerating adoption of secure agentic payments across the industry. The protocol is designed to serve as open infrastructure for AI shopping and commerce, with support from industry leaders.
📖 Read the full source: HN AI Agents
👀 See Also

Pantheon-Reasoning-27B: A Dense Reasoning RP Model from Gryphe
Gryphe releases Pantheon-Reasoning-27B, an uncensored Qwen 3.6 27B fine-tune with full reasoning traces for roleplay. Built on Pantheon, Opus-4.6-Reasoning-24k, WorldSim, text adventure, and general RP data. GGUF quants available.

Claude Code v2.1.139 Adds Agent View, /goal Command, and Major MCP Improvements
Claude Code v2.1.139 introduces a new agent view for session management, a /goal command for multi-turn tasks, expanded hook capabilities, and fixes for MCP server memory issues and terminal corruption.
AMD Threadripper Halo Station: 96-Core AI Workstation with MI350P
At IFA 2026, AMD announced the Threadripper Halo Station, a workstation packing a 96-core Threadripper Pro 9995WX and dual liquid-cooled MI350P accelerators, designed to run trillion-parameter models.

Microsoft's BitNet Enables 100B Parameter LLM Inference on Single CPU
Microsoft's open-source BitNet project achieves 100B parameter LLM inference at 5-7 tokens/second on a single CPU, with the 2B parameter model using 0.4GB memory and 29ms latency while matching full-precision models on benchmarks.