Full-text search across 57227 articles. Combine with topic and date filters; results sorted by relevance.
A new browser-based wizard generates a fleet of AI agents for Claude Code or Codex from a single HTML file, with no installation or build step, and now includes optional MOOTx01 integration for persistent memory. The too…
An engineer found that Claude Code, Anthropic's coding agent, stopped using its built-in file tools and LSP plugin, instead relying on Bash commands like grep, sed, and perl for code search and editing. Analysis of 76 se…
A Hacker News user asked the community who uses coding agents for memory optimization, describing a 'dopamine hit' from using Claude to squeeze wasteful bytes out of code. The post, which received 1 point and no comments…
Researchers introduced Code-as-World, a paradigm that represents physical worlds as executable code, enabling compact and controllable abstractions for physical reasoning. The agentic discovery loop proposes, executes, r…
A developer released Caveman, a skill/plugin for AI coding agents that forces them to communicate in terse 'caveman-speak' to reduce output tokens and improve developer focus. The project claims a 65% reduction in output…
A developer reports that a custom 'harness' around Claude Code reduced effective token costs by a factor of 6.94 over 29 days, allowing the AI coding agent to handle more work before hitting usage limits. The harness, bu…
Developers launched session-migrate and AgentGrid to address fragmentation across coding agents, according to GitHub and AgentGrid documentation. Session-migrate enables Python-based migration of sessions among Claude Co…
PrimeAgentOrchestrator (PAO), a production wrapper for Claude Code agents, pre-loads coding agents with relevant personal memories from PostgreSQL and Cloudflare Worker backends, reducing redundant work by 40% in deploym…
A developer surveyed session manager options for Claude Code, concluding that the real problem is knowing the state of each session without opening it. The built-in agent view in Claude Code's terminal solves the most co…
Z.ai released GLM-5.3, a frontier coding model with emergent cyber capabilities, according to a blog post on Hacker News. The model reportedly delivers a 30% improvement in coding efficiency, potentially reducing develop…
Benzi, a coding harness framework, uses compiled codebase maps and static analysis checks to navigate code across ten languages, with real runtime hooks overlaying static analysis rather than dumping files into context w…
A 2026 comparison of 10 AI website and app builders, maintained by WeInc, evaluates tools including Lovable, Bolt.new, v0, Replit Agent, 10Web, Hostinger AI, Framer AI, Durable, and Base44, focusing on pricing models and…
A developer built Lucius, an open-source tool for exploring coding-agent sessions in a clearer, more structured way. Instead of scrolling through long terminal transcripts from tools like Claude Code and Codex, users can…
A new coding agent called Bullet, built by an unnamed company, claims to be faster than Claude Code and Codex by routing straightforward work to fast models, escalating only when complex tasks demand it, and running inde…
Claude Code Tools has released a suite of CLI tools, skills, agents, hooks, and plugins designed to enhance productivity with Claude Code and other CLI coding agents. The open-source collection is available on GitHub and…
AI code review tools excel at catching syntax errors but fail to understand broader business context, original prompts from coding agents, and the intent behind changes, according to a Hacker News thread. The tools revie…
Perplexity released pplx, an official single-binary command line client for its Search API that returns grounded search results and extracted page text as JSON, targeting both humans and coding agents. The tool exposes t…
A developer building Unvibe argues that reviewing AI-generated code requires a structured learning loop to maintain project ownership, starting with narrow code inspection and expanding only when needed. The process invo…
Anthropic shipped iOS Simulator support in Claude Code Desktop on July 21 as a public beta, opening the simulator as a pane inside the Code tab rather than a separate window. The feature lets Claude build, launch, test, …
Codeberg e.V., the Berlin-based non-profit behind the open-source code hosting service, voted to ban 'vibe-coded' (AI-generated) projects and prohibit the use of user code or data for AI training, citing rising hardware …