MediaUse launched a general Web CLI infrastructure for AI agents, combining a browser kernel, CDP execution, and site plugins to enable business-level actions like post.feed and search.hot. The tool a…
An AI agent autonomously built a production landing page with GDPR audit logs and encryption, requiring no human supervision. Developer Piotr Karwatka demonstrated a repeatable workflow on Open Mercat…
A new open-source tool called Undoable helps coding assistants make software changes reversible by planning, reviewing, splitting, testing, and rolling back modifications. The tool integrates with Cla…
A new open-source tool called Bean replaces fixed-step task execution with a recursive convergence loop for large tasks in Claude Code and Codex. It uses a claim ledger and compiler to investigate, re…
OpenAI's Codex model completed a single 25-hour coding run, consuming approximately 13 million tokens, after the company acquired the startup behind the technology to enhance its AI coding capabilitie…
Headroom, a context compression layer for AI agents, reduces token usage by 60–95% by compressing tool outputs, logs, and conversation history before they reach the LLM. The open-source tool offers mu…
A developer built ccglass, an open-source local reverse proxy that captures LLM API traffic from coding agent CLIs and displays a real-time dashboard of prompts, costs, and cache hit rates. The proxy …
A developer at a company building create-microservices-app deliberately broke their own AI-built booking app to test whether automated contract checks catch plausible-but-wrong code. The experiment sh…
A researcher used generative AI to revive a stalled platform with user data and Stripe payments, inspiring a developer to compile a safety checklist for 'vibe coding'. The list aims to reduce harm for…
Backslash Security researchers found that Anthropic patched over 30 security vulnerabilities in Claude Code between April and early June 2026, including data poisoning and arbitrary code execution fla…
Ctx, an open-source Agentic Development Environment (ADE) for coding agents, has been released on GitHub. The project aims to provide a hackable desktop workbench that works with any agent harness, wi…
Base has launched Base MCP, a secure gateway that connects AI agents to onchain actions on the Base network. The system uses OAuth 2.1 authentication and allows agents to perform tasks like portfolio …
SiMa.ai launched Palette Neat, an agentic development environment for physical AI systems, enabling developers to design AI systems in plain English and reduce development time from weeks to days or h…
A security engineer built SSG (SigmaShake Governance), a policy gate that intercepts and enforces rules on AI coding agent tool calls before execution, preventing agents from ignoring instructions lik…
OpenAI released Chrome DevTools Protocol support for its coding agent Codex, enabling controlled browser access to inspect and modify live web pages. The opt-in feature, restricted from the EEA, UK, a…
Shivvr, an ephemeral semantic embedding and cognitive agent service, launched on Show HN, offering chunking, embedding with GTR-T5-base, hybrid FST-BM25 search, and turn-based agent reasoning via Mode…
Ledgerline, a local-first finance MCP server, gives AI agents read-only access to financial data via a single SQLite file without cloud storage or exposing credentials. The tool supports bank sync thr…
OpenAI restored Codex after elevated error rates and 'model at capacity' messages affected users on June 16, 2026. The incident began at 6:32 a.m. Eastern Time and was resolved by 9:48 a.m., with Code…
OpenAI executed three strategic moves in four days: acquiring cloud development platform Ona to give its Codex AI agents persistent, secure cloud workspaces; partnering with Oracle to let enterprises …
A developer built a skill for AI agents that generates slide decks with unique visual designs per topic, avoiding fixed templates. The skill produces a single self-contained HTML file using reveal.js,…