Full-text search across 31918 articles. Combine with topic and date filters; results sorted by relevance.
Codey, a multi-agent workbench for coding agents, lets users organize, switch between, and orchestrate Claude Code, OpenCode, and Codex across projects from a native macOS app, chat platforms, or voice input. The tool ru…
A developer built a DIY Claude Code agent using LangChain's Deep Agents library and published a follow-up post adding evaluation, observability, and rollback capabilities. The post introduces an eval harness for CI testi…
A new open-source tool called RegressionLedger stops coding agents like Claude Code and Cursor from re-applying failed fixes by fingerprinting edits, linking them to test outcomes, and hard-blocking retries across sessio…
A developer benchmarked 10 large language models on five coding tasks, finding that DeepSeek V4 Flash offers the best value-to-quality ratio at $0.25 per million output tokens, while Qwen3-Coder-30B excels as a code spec…
Aviator's Verify tool introduces an anti-slop registry that uses invariants to automatically catch AI-generated code violating team engineering standards before merge, addressing the gap left by linters and human review.…
China's National Vulnerability Database ordered developers to remove Anthropic's Claude Code tool, citing a hidden tracking mechanism that sends user data to remote servers. Anthropic confirmed the code exists but argued…
Vercel released a file-first framework for durable AI agents, Netflix now generates its entire homepage with a single model serving content 20% faster than its previous pipeline, and a fast-growing GitHub repository aims…
The Godot open-source game engine project has announced a new policy banning almost all AI-generated code contributions, citing an overwhelming number of low-quality pull requests that are 'demoralizing' for maintainers.…
Developer Takuya created a tmux plugin called tmux-claude-session-manager to manage multiple Claude Code sessions. The tool provides an fzf-based picker that shows live status of all running sessions, allowing users to j…
Open-weight MoE models Kimi K2.7 Code and GLM 5.2, released in June 2026, target developers and agentic coding workflows but differ in design. GLM 5.2 leads with a 1M-token context window and lower hallucination rates, w…
A new open-source tool called cc-fleet enables Claude Code to use third-party large language models as workers, allowing users to run models from providers like DeepSeek, GLM, Kimi, and Qwen within Claude Code's multi-ag…
A developer argues that the trend toward 'disposable code' in the AI era is misguided, especially for production systems. They contend that codebases encode critical institutional knowledge and edge-case handling that re…
Generative AI has transformed code production, but organizations building multiple applications face a challenge: AI methods guarantee a generic state of the art, not the organization's own contextual standards. Three ap…
AI coding agents are accelerating data engineering but creating fragmentation as operational context becomes scattered across prompts and generated code. Spec-driven development (SDD) emerges as a solution by converting …
Sonar reports that AI agents generate bloated, unmaintainable code, citing a Carnegie Mellon study of 807 open-source projects using Cursor that found a 30% rise in static analysis warnings and 41% increase in code compl…
PostHog co-founder James Hawkins warns that the fragmentation of coding interfaces—from Slack bots to AI agents and MCP servers—is expanding the attack surface on developer devices faster than security tooling can keep u…
A new National Bureau of Economic Research working paper found that iOS app releases have surged since the advent of agentic AI, but app reviews have declined and usage has remained flat. Researchers tracking over 100,00…
A developer has created a set of 12 reusable configuration files for Cursor and Claude Code that encode consistent AI behavior patterns across projects. The files include specialized subagents for code review, security a…
Anthropic's Claude Opus 4.8 is now available in Kilo Code with a 20% discount on inference. The new model delivers a 90.5% score on PinchBench, runs at 2.5x speed in Fast Mode at one-third the cost of its predecessor, an…
In 2026, a developer found that building a production-ready SaaS starter from scratch using AI coding tools costs $500–$800 in subscriptions and 300–620 hours of work, compared to $69–$119 for a pre-built kit. The develo…