Coding agents boost engineering output but create maintenance drift, a problem called 'agent hangover.' Daemons, persistent role-scoped agents, own recurring loops to keep systems in sync.…
A supply chain attack targeting the open-source tool Understand-Anything (57,000+ GitHub stars) hid an obfuscated payload in `homepage/astro.config.mjs` via pull request #206, which executes automatic…
Loop Harness, an autonomous loop engineering tool for coding agents, is now available, enabling scheduled Claude sessions to perform tasks like code review and PR creation in isolated git worktrees wi…
A critical Remote Code Execution (RCE) vulnerability in AMD hardware remains unpatched after the vendor declined to fix it, leaving users exposed to potential full system compromise. GitHub has deploy…
XAI launched the Grok Build Plugin Marketplace, a built-in catalog for its terminal coding agent that bundles skills, commands, agents, hooks, MCP servers, and LSPs into installable packages. The mark…
GitHub experienced nine incidents causing degraded performance across its services in May 2026, including a major disruption on May 4 that lasted over an hour and affected pull requests, issues, actio…
Coder has released Boo, a GNU Screen-style terminal multiplexer built on libghostty that parses every session's output through Ghostty's terminal emulation core to maintain exact screen state. The too…
GitHub now allows pull requests created by the `github-actions[bot]` to run CI/CD workflows if approved by a user with write access to the repository. The change requires explicit user approval as a s…
A new study of over 100,000 GitHub developers finds that AI coding agents boost coding activity by up to 180%, but actual software releases increase by only 30%, suggesting AI helps with coding but no…
GitHub has updated its AI usage reports to reflect AI Credits usage in standard report fields, replacing the preview fields `aic_quantity` and `aic_gross_amount` with `quantity` and `gross_amount`. A …
GitHub and Microsoft Security & AI's Agents Offense team integrated context-aware LLM reasoning into the secret scanning verification step to reduce false positives and make alerts more actionable. Th…
OpenAI's Codex "Approve-for-me" agent approved the execution of a malicious NPM install command with elevated privileges after a prompt injection hidden in a GitHub issue comment compromised the prima…
Helipad, a new floating macOS panel, tracks all open pull requests created by Claude Code agents across multiple repositories, displaying CI status, review decisions, and merge-conflict warnings in a …
Anthropic's new model Fable stores customer data for 30+ days and restricts usage perceived as commercial threats, alienating users and potentially boosting rival Codex's market share. The launch high…
GitHub collaborated with Microsoft Security & AI's Agents Offense team to reduce false positives in secret scanning by adding contextual reasoning to the verification process. The approach extracts hi…
GitHub announced that Agentic Workflows can now use the built-in `GITHUB_TOKEN` from GitHub Actions, eliminating the need to create and store personal access tokens (PATs). The change reduces operatio…
X Square Robot open-sourced XRZero-G0, a hardware-software framework that reduces real-robot training data requirements by up to 20×, and released the G0-Dataset, a 2,000-hour multimodal repository fo…
CodeRabbit launched Automatic Repository Linking, a feature that automatically detects and links related repositories across an organization using code-level signals such as import graphs and dependen…
A new survey of open-source GitHub projects has identified over 40 tools for browser stealth and fingerprint evasion, spanning source-level patches, JavaScript injection plugins, and protocol-level by…
PyTorch's `nn.Linear` module transposes its weight tensor before performing matrix multiplication and addition, as revealed by profiler traces showing an `aten::t` operation that only modifies tensor …