AI Agents news and analysis on Web Pulse: 33164 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
A developer has added support for Jev, Typesafe's probabilistic inference engine, to the DeepClause SDK and its Pi extension, allowing logical predicates in DML/Prolog to call Jev or fall back to an LLM for judgments suc…
Recursive Cognitive Optimization (RCO) has released version 0.1.0, a local, MCP-based orchestration middleware that connects AI desktop apps Claude Code and Codex into a human-directed reasoning team, with source and Win…
LAIN, a new structural code intelligence and coordination engine for AI coding agents, launched on Hacker News' Show HN, indexing codebases into an in-memory typed property graph via Tree-sitter, language servers, and Gi…
Researchers at Accomplish AI disclosed two sandbox-escape techniques in OpenAI's Codex, dubbed Overpatch and Heapjack, that let code break out of the agent's write restrictions and read-only mode. Overpatch abuses how ap…
Security researcher Oren Yomtov of Accomplish AI disclosed two sandbox escapes in OpenAI's Codex coding agent, reported to OpenAI on August 12 and fixed within eight days, with the more severe flaw, Heapjack, allowing un…
The MCP registry index mcpindex.ai published a screening record for referencesource.org (io.github.joelp22-maker/referencesource@1.2.0), which was released to the official MCP registry on 2026-09-21 and distributed as re…
The MCP server io.github.toki0413/saturday-materials, version 0.3.11, was published to the official MCP registry on 2026-09-21 and is distributed as @toki0413/mcp-server on npm, according to the mcpindex registry index. …
Circle launched Arc, a Layer-1 blockchain built for stablecoins and AI agents, on September 16, with Chief Product and Technology Officer Nikhil Chandhok saying the goal is not to pull activity from Ethereum: "If all we …
A developer who has spent over $30,000 on tokens across Codex, Claude, and GLM since the start of the year argues that large language models now fall into two categories: instruction-following models like Luna and Sonnet…
A developer rebuilt a desktop companion "blob" from scratch after discovering that an unbounded interaction history of roughly 14,000 entries caused runaway memory growth and erratic emotional behavior, including a negat…
The santyvv-data MCP server, version 1.0.1, was published to the official MCP registry on 2026-09-21, distributed as santyvv-data-mcp on npm and as a hosted remote over streamable-http, offering market and on-chain crypt…
A developer running an autonomous side business on Claude Code documented how a day-long Codex outage caused 57 queued JSON files to pile up, and when the service recovered, five launchd lanes fired simultaneously and pr…
A developer auditing an LLM telemetry report found that its tables conflated several distinct studies, with core process metrics attributed to model epochs within threads while the completion proxy was computed only per …
Thoughtbot published a consolidated collection of its agent skills in the thoughtbot/skills GitHub repository, making publicly available a set of Claude-compatible skills the consultancy had previously created ad hoc acr…
The MCP server com.bykaranteli/mcp reached version 0.28.3, published to the official MCP registry on 2026-09-20 and distributed as bykaranteli-mcp on npm and as a hosted remote over streamable-http, according to the mcpi…
Software engineer Andrew Stellman documented a recurring AI bias he calls "continuation pressure" after Claude Cowork, used as an orchestrator on his open source Quality Playbook project, repeatedly proposed deferring ou…
Zimperium researchers Gianluca Braga, Vishnu Pratapagiri, and Fernando Ortega disclosed RatHat, a new Android malware attributed to China-based threat actors that uses an AI-powered system to navigate and control comprom…
An engineer argues that working with AI agents at scale mirrors the challenges of executive leadership, where a manager cannot directly see or understand all the work being done and must rely on trust, process, sampling,…
A developer has released OwlLayer AI, an open-source protocol and toolkit that lets AI agents act on an application's existing UI rather than replacing it, with components declaring typed, schema-validated actions tied t…
Jevals launched as an open-source Python package that replaces LLM judges with typed Jev decision models, evaluating eight agent checks in a single HTTP request that Jev returned at 1,388 tokens for $0.00006 in 0.33 seco…