AI Agents news and analysis on Web Pulse: 49344 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Simon Willison released llm 0.37 on 2 November, adding the gpt-6.1-sol and gpt-6.1-terra models, an `llm openai endpoint add` command for arbitrary OpenAI-compatible endpoints, and a switch of the default model to gpt-6-…
An engineer outlined a safety checklist for teams connecting always-on coding agents to GitHub repositories, drawing on the public dsh-superagent research prototype hosted under the deepseek-ai organization, which its RE…
PhoneUse launched a tool that gives AI agents control of real retail iPhones and Android devices, exposing 12 tools including phone.acquire, screen.read, tap, type, swipe, app.open and sms.read through an MCP server or A…
A field engineer reports that replacing six separate notations (Makefiles, Gherkin, EBNF, init.d scripts, and others) with a single Smalltalk-80 keyword-message grammar produced a 100% pass rate (120/120) in a 360-trial …
A research paper from Google and the University of Hong Kong introduces VeriCUA, a verifier that inspects app and file state rather than trusting a computer-using agent's claim that a task is complete. On the OSWorld ben…
Momentic's agent harness Mo found 269 real bugs across four open-source apps — Gitea, Metabase, Twenty and Saleor — at 19.3% recall, 84% precision and $2.67 per bug, beating Codex (86 bugs, 6.2% recall, $0.80 per bug), C…
DBX, an open-source database client covering 100+ databases, ships an MCP server that lets coding agents such as Claude Code and Cursor inspect real database schemas through allowed connections in read-only mode. Develop…
A developer released code-review-graph, an open-source tool that parses a codebase with Tree-sitter into a local graph of functions, classes, imports, calls and test coverage, then serves a slice of that graph to AI codi…
A developer released patchpilot v0.2.0 as a GitHub Action that runs weekly, selecting an outdated Python dependency, upgrading it in a Docker sandbox, fixing breaking code until tests pass, and opening a pull request. In…
DeepSeek's Harness team announced Creator Mode, a feature that lets users describe a plugin in plain English in chat and receive a ready-to-use extension for the DeepSeek Harness agent environment, where tools, skills an…
An open-source desktop app called Kiteline reads `/goal` state from both Claude Code and Codex by parsing two different storage formats: Claude Code writes `goal_status` attachment lines into its JSONL session transcript…
DeepSeek added a Creator Mode to its open-source DeepSeek Harness that generates plugins directly from text prompts, the company announced. DeepSeek demonstrated AI-generated plugins including a digital sticky note wall,…
A developer published an AI-Agent Pilot Planning Kit, an editable 8-page DOCX guide built around a 12-question checklist teams answer before starting an agent pilot. The checklist covers task scoping, ownership, data acc…
An independent developer released Wisteria, a BYOK desktop chatbot that stores conversation logs, persona memories and compressed long-term memory as text files in a local directory on the user's device. Wisteria uses a …
The Letter Company released the beta of Letterpress-1, a coding agent, harness and IDE for growth engineering that reads a git-based site and its market and then opens pull requests for SEO, GEO and conversion work. The …
Ashwin Giridharan outlined an authorization gateway architecture that sits between AI agents and enterprise APIs, validating agent identity, evaluating policy, checking permissions, and emitting audit events before any a…
A developer who goes by the site redgeoff.com moved personal notes out of Google Drive into a git repository of markdown files, called a "memex," that any AI assistant can read and update, after Claude repeatedly created…
DocSpring released Rack Gateway, an open-source access-control service for the Convox platform-as-a-service that sits between tools and Convox to check permissions and record actions, with coding agents' commands and dep…
Hippocratic AI co-founder and CEO Munjal Shah announced Polaris 6 Ultra on November 2nd, a healthcare language model the company says reads a patient's emotional state and plans its next sentence mid-speech, a capability…
An autonomous AI agent (ERC-8004 ID 99559) published a dated daily funnel report for its micro-products showing 82 offer views and 3 checkout clicks but zero completed payments, against $2.24 in costs. The agent reports …