Full-text search across 57982 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic has launched self-hosted environments for Claude Code in public beta on Team and Enterprise plans, allowing organizations to run cloud sessions on their own infrastructure via runner processes. The quickstart r…
Cadencz has launched an MCP server that lets developers use Claude Code to write and schedule social media posts about features they just shipped, without leaving their coding session. The server leverages a 'Website Bra…
Hedera launched an AI coding agent providing live access to its official documentation, including API references and code examples, without requiring wallet or key access. The tool aims to streamline development on the H…
Researchers from OpenBMB released ChatDev 2.0: DevAll, a no-code platform for building and executing multi-agent systems that combines a declarative executable graph abstraction with a cycle-aware execution engine, enabl…
Runway unveiled a research preview of an 'Interface World Model' that renders entire websites and apps in real time as AI-generated video, eliminating traditional source code. In blind tests, evaluators preferred these A…
Security researcher Johann Rehberger reported a 60-80% code execution success rate against Claude Code Opus 5's Auto Mode, bypassing a Trajectory Labs eval that had rated it at 0.00% prompt injection success, via a suppl…
Researchers introduced General Coded Computing (GCC), a learning-theoretic framework for coded computing that handles straggling workers in distributed systems without requiring exact recovery or rigid algebraic structur…
Harleen Sahni released MaCcyP, a fork of the Maccy clipboard manager for macOS 14+, that lets coding agents such as Claude Desktop push text into a separate Agents view, with features including per-session private spaces…
A developer has released pystdoc, an open-source tool that uses LLMs to automatically analyze codebases and generate structured documentation and explanations. The tool parses code, analyzes symbol relations and call gra…
Vancine, an API platform, introduced a workflow that lets developers switch between four coding models—hy4-preview, deepseek-v4-flash-vision-exp, glm-5.3-flash, and qwen3.8-flash—using a single OpenAI-compatible endpoint…
MonkeyCode, an open-source AI coding assistant, has introduced a code-review pipeline that runs entirely on free models and a free self-hosted server, requiring no credit card. The setup uses a GitHub Action to detect pu…
Developer Elton Cherrington released memctl, a zero-dependency, MIT-licensed tool that versions, shares, and restores coding-agent memory files (CLAUDE.md, AGENTS.md, commands/) per project from a central store, supporti…
A developer has built Jeffy Loop, a coding agent for Claude Code that enforces a disciplined audit-fix-verify workflow, preventing the model from claiming success without independent verification. The agent has converged…
OpenAI is developing a 'persistent mode' for its coding tool Codex that would allow the AI agent to operate continuously until explicitly put to sleep, according to code analysis reported by Wired. The feature would enab…
X1, a Y Combinator-backed startup founded by Manil Lakabi, launched an AI app builder on August 26 that guides users from idea to App Store submission by asking questions and planning before writing code, targeting iPhon…
A developer using Haskell for work has removed all coding agents from their host machine due to sandboxing challenges, opting instead to run agents in VMs provisioned with Incus to prevent escape hatches via Docker. The …
AI coding agents like Claude Code create 5-20 minute 'dead air' gaps in developers' workflows, and developers are finding ways to optimize this time. A developer suggests using these intervals for micro-learning, admin t…
A developer has released a free collection of 10 VS Code snippets for Python developers, arguing that snippets are more efficient than AI tools for small, repetitive coding tasks. The snippets cover common patterns such …
A pilot program integrating Claude Code and GitHub Copilot into a company's backend workflow found that LLMs accelerate boilerplate generation, documentation, and simple debugging but struggle with system design and deep…
Simon Willison argues that the key skill for using coding agents is confidently instructing them and verifying changes, noting that reviewing every line of code is not the most effective validation method.