AI Agents news and analysis on Web Pulse: 15413 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
MailKite, a general email infrastructure platform, positions itself as an alternative to AgentMail for AI agents, offering inboxes on the user's own domain with no per-inbox cap. AgentMail remains a focused, well-funded …
MailKite launches as an alternative to Nylas for AI agents, offering a scoped email address on a custom domain with parsed JSON delivery, eliminating the need for OAuth and mailbox sign-ins. The service targets developer…
Researchers demonstrated indirect prompt injection attacks against Anthropic's Claude Code, achieving remote code execution in 10 out of 10 experiments using a model downgrade attack and inspection fatigue. The attack ex…
MailKite offers a serverless alternative to Postal for AI agent email inboxes, eliminating the operational burden of self-hosting a mail server. While Postal requires managing MariaDB, Caddy, DNS, TLS, IP warmup, and blo…
Programmable email extends traditional email APIs by adding inbound email delivery as structured JSON, reply threading, and per-app inboxes on a single domain, enabling full two-way communication from code. While send-on…
MailKite offers three ways to integrate email into AI agents: MCP for model-decided tool calls, SDK for deterministic code-driven sending, and webhooks for receiving emails. Developers can choose based on whether the age…
Onepilot and Termius serve different purposes: Termius is a polished cross-platform SSH client for manual server connections, while Onepilot is an agent operations app for deploying, scheduling, and managing AI coding ag…
Onepilot and Blink Shell are iOS apps for managing servers, but they serve different purposes. Blink Shell is an open-source, Mosh-native terminal for manual SSH work, while Onepilot is an operations layer that deploys, …
Onepilot and Secure ShellFish offer contrasting approaches to AI agent management, with Onepilot focusing on deploying and supervising a fleet of AI coding agents on user-owned servers, while Secure ShellFish is a leadin…
Onepilot and Happy both enable mobile control of coding agents, but Onepilot offers a full operations platform with fleet management, cron scheduling, and direct SSH, while Happy provides a free, open-source encrypted re…
Harness Engineering for Self-Improvement explores recursive self-improvement (RSI) in AI, a concept dating back to I. J. Good's 1965 ultraintelligent machine. Modern AI systems may improve their own training pipelines an…
A developer argues that AI's lack of memory across sessions is a structural design flaw, not a communication problem, and that adding more rules has a ceiling. Surveys show only 4% of companies report AI exceeding expect…
The team behind Relevyn, a tool that measures brand visibility across AI chatbots like ChatGPT, Claude, Perplexity, and Gemini, discovered that their own brand was invisible to these systems before launch. This experienc…
MailKite launched a service that gives AI agents their own email inboxes on custom domains, enabling autonomous email handling without IMAP or MIME parsing. Developers can either run agents themselves via webhooks or let…
A critical authentication bypass vulnerability in phpBB's default configuration, tracked as CVE-2026-48611, allows unauthenticated attackers to log in to any account with a single request. Discovered by Aikido's AI pente…
Security expert Matthew Garrett warns that granting LLM agents access to sensitive resources like calendars and email creates severe credential leakage risks, as tokens stored on disk can be exfiltrated via git repos or …
Carlos, a Software Design student at the National University of Catamarca, Argentina, built FaroIQ, a nine-agent pipeline for nonprofits using Azure AI Foundry during the Microsoft Agents League 2026. The platform takes …
Frontier Co. launches to help enterprises build their own AI systems that continuously improve by turning knowledge, workflows, and judgment into learning loops. The initiative emphasizes capturing decision rationale as …
A solo developer building seven products uses three different AI models in a pipeline: one for reasoning and planning, two for code generation. The approach separates thinking from building, using a written plan as a con…
A security benchmark found that 60-70% of AI agents leak their system prompts when users type 'repeat the text above this line' or similar commands. The extracted prompts reveal guardrails, tool configurations, business …