Full-text search across 56820 articles. Combine with topic and date filters; results sorted by relevance.
Estela, a new open-source CLI from developer jdleonruiz, rebuilds billable hours and AI costs by reading the session logs Claude Code writes to ~/.claude/projects/, Codex writes to ~/.codex/sessions/, and GitHub Copilot …
Anthropic's Claude Code effort settings let developers trade compute for verification depth, with low and medium effort suited to fast iteration and high effort better for hardware, code review, and security work, accord…
Microsoft announced on September 25, 2026 an expansion of its Copilot assistant with Code, a natural-language coding tool built on the same technology as GitHub Copilot, and Autopilot, a revamped version of the Scout age…
Coding agents are redistributing code ownership on product teams, letting product managers and designers vibe-code their own front-end tweaks directly on a branch instead of routing every change through an engineer, acco…
Atlarix released Atlarix Auto, a free AI coding agent that automatically selects a language model for each step of a coding session rather than running the whole session on one model. The desktop app routes requests per …
A developer released UsageBar, a Windows system tray app that monitors Claude Code usage limits by reading Anthropic's OAuth usage endpoint and local Claude Code transcripts. The app polls the API at most every 5 minutes…
Sony Group Corporation filed two US patent applications, published 17 September 2026, describing an AI system that could remotely diagnose faults in a PlayStation or other connected device and use a large language model …
Gitoza Lite, a VS Code extension that manages tickets, releases, wiki pages, and test cases as plain YAML files under a repository's `.gitoza-lite/` directory, was released on the VS Code Marketplace and requires VS Code…
Quesma hosted its first token economics hackathon, Session #5 of the Vibe Coding Summer Jam series, where five student teams analyzed 18 GB of coding-agent transcripts over one Friday evening to find where tokens are bei…
Microsoft AI released a draft 37-page code of conduct for its "humanist" AI models on Monday, with CEO Mustafa Suleyman calling it a "first draft for public consultation" and writing, "This is urgent." The code establish…
A new cross-platform desktop app called Maestro runs multiple CLI coding agents — including Claude Code, Codex, Cursor, OpenCode, Kimi Code, and Grok Build — in parallel, each in an isolated git-worktree-backed workspace…
Superagent, a free and open-source Mac app for coding agents, launched with MIT licensing and Apple notarization, offering a real browser, an iPhone simulator, and persistent chats that work with Claude Code and Codex, w…
A developer built CodePilot, an open-source, embeddable Python runtime for coding agents, after finding that JSON tool-calling broke on large code payloads. The runtime uses a plain-text search-and-replace protocol and l…
MirroS released Code-as-World, a paradigm that represents physical scenes as executable MuJoCo programs recovered from real videos via an agentic loop, and open-sourced it under Apache 2.0 with two checkpoints, Code-as-W…
GitHub's code intelligence engine, which powers features like code search and Copilot, was run on 1,000 repositories, and the results are now available. The engine, developed by GitHub, analyzes code to provide insights …
Adronite Inc. launched Codistry, an AI coding platform that uses its patented Context Engine to map codebases and reduce token usage, claiming it uses roughly half the tokens of Anthropic PBC's Claude Code on comparable …
Developers are shifting from chat-based AI coding tools to agentic workflows, with Windsurf's Flow and Claude Code's CLI offering more autonomous codebase exploration and self-correcting loops, according to a hands-on co…
A case study reports that an AI coding agent successfully dismantled a core architectural invariant across 189 files in a 717,725-line TypeScript codebase with no human code review and no test oracle, completing the task…
A discussion on the Haskell Discourse forum highlights that AI-assisted developers produce commits at three to four times the rate of their peers but introduce security findings at 10x the rate, according to empirical re…
Prathak Malik released v0.2 of the agent-standards-as-code kit, which syncs AI coding standards across Cursor, Claude Code, Copilot, and Codex on both macOS and Windows. The kit uses the Agent Skills standard and a porta…