Stanford professor emeritus John Ousterhout presented the Homa protocol at the AI Engineer Summit, claiming it cuts short-message P99 latency in AI clusters from 1.2 milliseconds under TCP to 92 micro…
A developer built Receipt Lens, an open-source tool that verifies AER-1 execution receipts and visualizes an AI agent's step-by-step trace, including timing and cryptographic Merkle root checks. The v…
The IETF's competing SCIM agent-identity drafts consolidated into a single document, draft-wzdk-scim-agent-resource-00, published in June 2026 and co-authored by M. Wahl and P. Dingle of Microsoft, D.…
Cloudflare has set a 2029 deadline to achieve full post-quantum readiness across its platform, developing an internal AI-powered tool called CryptoLabe that uses large language models to discover, ana…
Cloudflare worked with the IETF to develop and has released in beta across its IPsec products a mitigation against quantum downgrade attacks on IPsec, addressing a design flaw it rediscovered that let…
An IETF internet draft on privacy-preserving federated learning in multi-tenant agent systems argues that enterprise AI contracts quoting a differential privacy budget as a single epsilon and delta fi…
Software developer and blogger Tim Bray argues that regulating and standardizing large language model technology is premature, citing a global multi-trillion-dollar investment overhang that obscures a…
DigiCert has introduced AI Trust, a governance framework that assigns every AI agent a credential with an expiry date and a named human owner, built on the company's public key infrastructure, DNS, an…
A developer outlined a layered architecture for AI agent authentication, arguing that no single protocol suffices and that discovery, workload identity, request authentication, and delegated authoriza…
A new open-source tool called homestead-memory logs every Claude Code tool call in a hash-chained, tamper-evident local ledger at a median cost of about 124ms per call (138ms p95, measured on an M3 Pr…
The IETF's Web Bot Auth working group adopted draft-ietf-webbotauth-httpsig-protocol as its first working-group document in September 2026, folding in the separate key-directory draft so one document …
Agent identity for AI agents depends on four distinct layers — KYA (Know Your Agent), authentication, authorization, and payment authorization — with payment authorization remaining the least-solved l…
An engineer argues that OAuth tokens alone do not provide an operational identity for AI agents, and that systems need a governed identity model that tracks an agent's lifecycle, authority, and purpos…
The Model Context Protocol team published an updated roadmap and a new spec release that removes protocol-level sessions and the initialization handshake, enabling servers to scale horizontally withou…
A draft by Stephen Farrell and Chong Feng, titled 'Dealing with LLMs in IETF Discussions,' is circulating on IETF mailing lists to balance competing views on using large language models (LLMs) in IETF…
Cloudflare will begin classifying bot traffic into three purpose-based categories—Search, Agent, and Training—on July 1, 2026, and will block Agent and Training bots by default on ad-supported pages f…
A developer has introduced a technique for adding cryptographically signed receipts to MCP tool calls, using the ccs-mcp-server library. The method, which adds about 20 lines of code, helps detect arg…
Two independent implementations of the Correctover Conformance Shape (CCS) specification, an IETF Internet-Draft defining a runtime verification framework for AI agent tool calls, have achieved 14/14 …
An engineer's blog post argues that AI agent protocols like MCP and A2A fail to record human judgment in approval workflows, citing a paper by Kang and Diponegoro that scores five protocols against go…
SAML 2.0 handles authentication while OAuth 2.0 handles authorization, and choosing the wrong one leads to brittle integrations and audit findings, according to a guide on the differences. The guide n…