AI Tools news and analysis on Web Pulse: 35748 curated articles tracking the latest AI Tools 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. …
The local-first AI video editor proofcut reached version 0.38.0, published to the official MCP registry on 2026-09-21 and distributed as proofcut on PyPI, according to the mcpindex server index. The index's semantic scre…
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 built MagicKit, a free open-source AI toolbox combining image generation, AI writing, and video creation in a single page with no sign-up, API key, or paywall required. The Node.js/Express backend uses the Po…
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…
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…
A web developer published a Show HN project converting Winamp's AVS audio visualization to WebAssembly using GPT 5.6, describing it as an early-stage "vibed Sunday afternoon project" built without prior C++ experience. T…
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…
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,…
Vincent Bernat replaced GoAccess with GoatCounter, an open-source, privacy-friendly web analytics platform, on his NixOS-hosted blog after AI scrapers inflated GoAccess's visitor counts to around 2,000 per day. Bernat wr…
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…
TypeSafe AI's Jev, the company's first System One Model, selects internal-link targets from a bounded candidate set as a typed Choice question, returning one selected option, a probability for every option, and a confide…