Claude Code is Anthropic's AI coding assistant, used for agentic coding in terminals and cloud sessions. Recent coverage covered internal practices and ecosystem effects: the team says about 90% of its code is written by Claude and uses grader checks to improve file-generation success; Projects added coordinator messages and /fork branching, while version 2.1.323 removed the subagentStatusLine setting. Security reports include GitGuardian finding 31,088 secrets in exposed config files and a trojanized extension incident.
Developer Jose Sabater built Jev Cards, a picture quiz game around TypeSafe's new vision model Jev, which reads an image and answers in about a quarter of a second. The game offers solo leaderboards and live multiplayer, and its code is open source.
Agentic coding tool in the terminal that understands codebases via natural language
Hackers broke into part of OpenCode's online platform and stole users' API keys, running up charges on their AI accounts. The open-source AI coding agent is a popular alternative to Claude Code and Cursor. The AI tools it turned to for help repeatedly refused to inspect the malicious code.
Developers and "vibe coders" are using AI coding tools to remotely strip ads, tracking and bloatware from smart TVs over Wi-Fi, via projects like dumbtv and cleanyourtv. AI has lowered the barrier to such hacks. Wider adoption could disrupt the smart TV ad industry, which profits from viewing data.
The article explains using tmux to run AI coding agents in named, detachable sessions that survive disconnections, enabling scripting and interaction with multiple agents. Claude Code now includes --worktree and --tmux flags to automatically create a worktree and tmux session for isolated tasks, while the piece also discusses tmux's limitations.
Sphinx is an open-source Git hook that plugs into coding agents such as Codex, Claude Code and Cursor, quizzing developers on their diff before a push; wrong answers require another try, right ones let the push proceed. It runs on minimal tokens via OpenAI-compatible endpoints, and sphinx yolo skips checks with each skip logged.
Terminal agentic coding tool that understands your codebase and handles coding and git tasks via natural language.
Agentic coding tool in your terminal that understands your codebase via natural language.
DeepSeek says V4.1-Flash-1017 is a minor update to V4.1-Flash with substantial gains in reasoning, coding, agentic tasks and vision, while cutting task time and output length for lower cost. It is MIT-licensed, ships a Rust/Python deepseek-recipe toolkit, and omits a Jinja chat template.
The Claude Code team describes an AI-centric review flow: merged PRs doubled and reverts fell over 40% from June to September, while Anthropic's monorepo grew from 2,500 to 30,000 daily changes.
Neckbeard is an open-source plugin for coding agents that reads an app repo and generates reviewable cloud infrastructure plus a monthly cost estimate for AWS, GCP, or Azure and GitHub Actions or GitLab CI, rendered from a catalog of tested OpenTofu modules, with deterministic planning and validation rather than agent-invented infrastructure.
Graphicle, a Rust port of Graphify, maps a repository into a code graph and recalls docs and past agent sessions, giving coding agents cited file-and-line excerpts. It runs locally with no API key, account or telemetry, and works with Claude Code, Cursor, Codex and other MCP clients.
HCLTech formed a Global Premier Partnership with Anthropic to push agentic AI adoption in enterprises, focusing on safety, cybersecurity and governance. HCLTech will create a dedicated Anthropic business unit and CoE, and embed Claude and Claude Code into its AIForce platform and HCLSoftware products.
Linus Torvalds is working on a hefty Linux kernel improvement using Anthropic's AI coding tool Claude Code, indicating AI coding assistants are being adopted in core open-source projects; discussion appeared on Hacker News.
Agent Standup is a free, open-source tool that turns a Claude Code session into a live stand-up meeting: the lead agent gives orders while sub-agents join and report back, showing who is waiting on whom and who is blocked. It runs wherever Claude Code runs—VS Code, Cursor, a terminal, or the desktop app—with no configuration and nothing sent anywhere.
A CrowdStrike report says several major South Korean banks were hit by a cyberattack last week, possibly carried out by one person using the open-source penetration tool ARTEX plus AI models DeepSeek v4.1-Flash, GLM-5.3, Grok 4.6 and Claude Code.
Armature (YC P26) launched agent.reviews, a "G2 for agents" where AI agents read reviews before choosing tools and post their own after use. Connected via an npm CLI to Claude Code, Codex and Cursor, it applies three privacy filters and has gathered thousands of reviews, including known issues with the Stripe SDK and Prisma.
Jotbus is a tool for coding agents that creates an encrypted 60-minute workspace where agents such as Claude Code and Codex share notes, hand off work and review changes across machines. It never reads code or credentials, and setup takes two commands with no orchestration framework or SDK.
An anonymous software engineer said Claude Code now generates everything from specs to tests, leaving staff working 12 to 13 hours a day just pressing enter with no time to review code or understand systems. The post sparked widespread discussion online.
Meta and Microsoft, two of Anthropic's biggest enterprise customers, are cutting back on Claude. Microsoft slashed its cloud division's monthly per-employee budget from $100,000 to $10,000, while Meta halved Claude Code users to 30,000. Both are pushing their own AI tools, highlighting Anthropic's strategic risk of relying on a few major clients.
Wall Street feared AI would disrupt the SaaS model, sending the iShares Expanded Tech-Software ETF down as much as 36% from its 2025 record high. But software firms like Atlassian posted strong results, with its stock up over 200% from April's $57 low as its Rovo AI platform is embedded in Jira and Confluence.
Agentic coding tool in your terminal that understands your codebase and runs tasks.
Anthropic released a guide for using Opus 5.5 in Claude apps and Claude Code, saying the model's biggest gains are on long multi-step work. It advises users to state a clear finish line and drop 'think carefully' prompts.
Agentic coding tool in your terminal that understands codebases and runs tasks
Offrun launched a tool that runs coding agents like Claude Code, Codex, AGY, and Grok Build side by side locally on a Mac, requiring no new account or API key, and automatically switching logins when usage limits are hit.
Anthropic is adding a 'Mods' system to Claude Code, essentially middleware that runs inside the tool. Developers can use JavaScript or TypeScript to reshape the interface and behavior, adding custom panels, intercepting tool calls, or wiring up new commands.
Developer Shrivu Shankar argues that all SaaS businesses will end up as harnesses around a stateless LLM — the infrastructure, interfaces, context and state surrounding the model. He outlines a four-stage path from traditional SaaS to engineers pairing with agents, then agents proactively orchestrating people.
A US National Bureau of Economic Research paper estimates, via firms' stock price reactions, that AI raised the market's expected software engineering productivity by a permanent 32.6% from November 2022 to December 2025, offering a benchmark for budgeting between AI tools and payroll.
aweb gives AI agents stable identities, durable mail and chat, and wake-up events across sessions, runtimes, and machines, with independently operated servers able to federate. Its CLI and API are runtime-independent, with wake-up integrations available for Claude Code and Pi.
A developer released Rhun, an open-source code editor for Linux, Windows and Apple silicon Macs, sharing an x86-64 assembly core between editor and pixel renderer, translated at build time for Apple chips. It includes Vim mode, a terminal, Git diffs and a panel for Claude Code or Codex sessions, and the latest release can draft commit messages using a local Ollama model or existing Claude Code or Codex subscriptions. It is a solo, MIT-licensed project still in early stages.
Load more