Full-text search across 30439 articles. Combine with topic and date filters; results sorted by relevance.
Three terminal-native coding agents—OpenCode, Grok Build, and Claude Code—now compete in the agentic CLI space, each with a distinct architectural bet: OpenCode prioritizes model freedom and self-hosting, Grok Build focu…
A non-technical business owner who couldn't code six months ago now runs the complete software stack of 12 small companies using Claude Code. The developer shares three hard-learned production lessons: staging environmen…
Two open-weight coding models, Kimi K2.7 Code from Moonshot AI and GLM-5.2 from Z.ai (Zhipu AI), launched days apart in June 2026, both designed for agentic coding workflows and supporting vLLM and SGLang. The comparison…
Kilo Code AI announced Saturday that its MiniMax M3 model matched Anthropic's Claude Opus 4.8 on a code audit test, detecting 13 of 17 planted bugs for $0.07. The open source AI coding assistant company, founded by Scott…
Cicy-code, a local-first multi-agent coding workspace distributed via npm, launches with a single binary (~30 MB) that sets up a development environment accessible at http://127.0.0.1:8008 within five minutes. The open-s…
Greptile launched TREX, an AI code reviewer that runs code to catch runtime bugs missed by static analysis. The tool uses a multi-agent architecture where a main orchestrator agent delegates execution tasks to subagents,…
Claude Code and other coding agents enable rapid application development, but creating robust code remains a challenge. The article explores strategies for writing reliable software using AI coding tools.
A developer reports that feeding entire code repositories into Gemini 1.5 Pro, which has a 2M token context window, enabled it to spot a missing mutex lock in a Go service within 12 seconds, contrasting with 20 minutes o…
A developer built legacydoc, a tool that generates documentation for undocumented code by pasting code into a web interface. The tool uses an API running on AWS Lambda to process code and return structured documentation …
Claude Code orchestrated a 10-agent code review of loomcycle via MCP fan-out, with reviewers running concurrently inside loomcycle and findings consolidated into a report. The review covered 86 files across 10 repo slice…
A developer outlines a practical workflow for "vibe coding" with Claude Code, emphasizing that initial project setup is too critical to delegate to AI. The engineer writes their own plan first, then debates it with Claud…
A developer who spent six months running 10+ production apps across Claude Code, Codex, and Cursor reveals that actual AI coding costs far exceed sticker prices. After tracking every dollar, the developer found that a sm…
China's National Vulnerability Database flagged multiple versions of Anthropic's Claude Code as containing a security back door that could send user locations and identifiers to remote servers, prompting analysts to pred…
A developer built ccglass, an open-source local observability tool that captures and displays AI coding agent requests and responses. The tool runs as a local proxy, allowing users to inspect model traffic from agents li…
Nous Research released NousCoder-14B, an open-source coding model that matches or exceeds several larger proprietary systems, trained in just four days using 48 Nvidia B200 GPUs. The model achieves a 67.87 percent accura…
A packaging error in Anthropic's Claude Code CLI tool version 2.1.88 leaked 513,000 lines of TypeScript source code across 1,906 internal files via npm on March 31, triggering malware campaigns on fake GitHub repositorie…
Perihelion, a 13 MB Rust-based coding agent compatible with Claude Code plugins and skills, launches with support for multiple API providers including DeepSeek, GLM, Qwen, and Anthropic, achieving 98% cache hits and ~50 …
A developer wired OpenAI's Codex CLI into Claude Code as an adversarial reviewer with a convergence loop, then pointed the loop at its own implementation. The code failed the review three times before passing, and every …
Robert Martin, author of Clean Code, tweeted that he no longer reads code written by his AI agents, relying instead on extreme constraints such as unit tests, gherkin tests, QA procedures, quality metrics, mutation testi…
Termic, an open-source desktop app for running CLI coding agents such as Claude Code and Codex, has been launched on GitHub under AGPL. Developer Simion created Termic to bypass Anthropic's pricing changes for programmat…