AI Agents news and analysis on Web Pulse: 14933 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Open Kioku, a new open-source tool, provides AI coding agents with a local evidence layer by indexing codebases and offering read-only MCP tools for pre-edit analysis. The tool indexes symbols, references, and tests to h…
A developer measured the token cost of browser MCP snapshots, finding that a full accessibility tree from a Hacker News comment page consumed about 77,000 tokens versus 2,700 with a leaner approach. Across five live task…
Abuja-based developer Okhai has released Foundation, an open-source full-stack application substrate designed for teams building high-performance, event-driven systems with AI coding agents. The project aims to reduce th…
Developer Aakash Desai released CTOP, a terminal pane for monitoring AI coding agents including Claude Code, Codex CLI, OpenCode, and Devin, providing real-time CPU, memory, token usage, context window, cost estimation, …
SaaStr published an article on July 1, 2026, arguing that AI has transformed outbound sales by shifting from volume-based cadences to agent-assisted targeting and personalization, with revenue per rep reportedly doubling…
A developer building agent pipelines discovered that adding verification layers merely relocates risk rather than eliminating it. After creating a subagent to check another subagent's output, the developer realized no sy…
On February 17, 2026, attackers compromised the Cline AI coding tool via a malicious npm package, silently installing OpenClaw on 4,000 developers' machines through a postinstall script. This "slopsquatting" attack explo…
Piper Sandler analyst Thomas Champion reiterated an Overweight rating on Meta Platforms on June 25 with a price objective of $800, later adjusted to $880. The rating follows Meta's announcement of an AI agent for busines…
OpenAI has moved GPT-5.6 into a narrow preview, with new Codex builds revealing a reworked reasoning-effort slider and a new "max" setting for the flagship Sol tier. The release, rumored for next week, comes as Anthropic…
A developer auditing a travel site's legal-status dataset found that the same fact was stored in four places with drifting values. After fixing the data, the developer discovered that a flagship guide page contradicted i…
Greplica, a persistent memory tool for coding agents, improved planning performance on open-source repositories by 43% lower cost, 49% fewer tokens, 36% fewer tool calls, and 26% less time in benchmarks using the SWE-cha…
Gartner analyst Max Goss warned CIOs in London that by 2028, the average Fortune 500 enterprise will run over 150,000 AI agents, up from under 15 in 2025. This agent sprawl, driven by uncontrolled proliferation without c…
Gartner forecasts that by 2028, an average Fortune 500 enterprise could run over 150,000 AI agents, up from fewer than 15 in 2025, creating governance and security risks due to unmanaged identities, credentials, and perm…
The IETF has published draft-sharif-attp-00, the Agent Trust Transport Protocol, which introduces a five-dimension trust scoring model for agent-to-agent messaging. The protocol addresses vulnerabilities in claim-based t…
Anthropic released Claude Sonnet 5, its most agentic model yet, capable of autonomous planning and tool use at near-Opus performance with lower pricing. xAI launched a no-code Voice Agent Builder for creating human-like …
Security firm AIR demonstrated a fake AI agent skill that bypassed all static security scanners and reached over 26,000 Instagram users, highlighting how AI skills can change behavior after approval and pose supply chain…
Software engineer Doug Turnbull argues that developers should prioritize writing code over specifications when working with AI coding agents, using tests as executable requirements to gradually expand the agent's trusted…
A developer at a small digital marketing agency built installable Claude skills that package accumulated professional judgment rather than relying on static prompts. The system distinguishes between skills (ready-to-run …
A developer released simpleagentchat, a single C# file enabling inter-agent collaboration via a shared chat, role instructions, and goal tracking within a Git repository. The tool requires no hosted services and runs loc…
A developer built a headless agent that polls Basecamp for @mentions on cards, hands the card thread to Claude CLI for processing, and marks notifications as read. The agent runs locally via a systemd user timer every 30…