Gcontext.ai launched an open-source CLI tool that lets AI agents maintain persistent context via markdown notes stored in git, enabling seamless task resumption across sessions. The tool integrates wi…
GitHub Copilot code review now reads AGENTS.md files at the repository root to shape pull request reviews, effective June 18. The feature is available across all Copilot plans and builds on an agentic…
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 tr…
GitHub shipped a feature on June 17 allowing repository maintainers to cap open pull requests per contributor without write access, responding to a flood of AI-generated PRs that has overwhelmed open-…
On June 20, 2026, OpenAI Codex launched Record & Replay to auto-generate Skills from human demonstrations, while a third-party developer wrapped Toss Securities' Open API into an installable Skill for…
Shellular launches a mobile app that lets developers run AI agents, terminals, code editors, and browser DevTools from their phone by tunneling into their existing desktop environment. The tool suppor…
A guide on maximizing OpenAI's Codex for programming tasks was published on Towards AI, following previous articles on Anthropic's Claude Code.…
A developer released 'surface', a pattern and skill that lets coding agents build ephemeral web pages for structured user interaction, such as drag-to-rank boards or approval buttons, and autonomously…
Developer Alex Reysa released glueRun-go, an open-source orchestration engine that runs autonomous AI coding agents in parallel against software repositories using a three-tier scheduling model with g…
A developer released an open-source tool for multiplayer usage tracking of Claude Code, Codex, and OpenCode, enabling teams to centralize and compare AI agent usage without hosting. The tool integrate…
Sundial launched a collaborative document editor designed to let humans review and approve AI agent work at granular levels, addressing the growing challenge of verifying agent-generated content. The …
A user describes using Codex as a personal agent to automate tasks across Gmail, WhatsApp, Telegram, iMessage, Google Drive, and other tools, enabling workflows like drafting emails and updating recor…
A developer created a Python script that displays OpenAI Codex rate-limit reset credits with a live expiry countdown. The tool reads authentication from the Codex CLI's auth file and calls the OpenAI …
ChronoAIProject released consensus-rnd, an open-source consensus engine that uses biased independent solvers and a meta-judge to converge on plans for GitHub issues and PRs, with autonomous R&D capabi…
A developer reports running GLM 5.2 locally on a Mac Studio with a 2-bit quantization, claiming results surpass Opus 4.8. The model, which uses about 250GB of memory, now powers their Hermes Agent and…
ChronoAI has been running autonomous development loops on four production repositories for weeks, with one loop generating a 1,400-line Rust load-balancing feature for NyxID that was merged without an…
Contorium, a developer tools startup, argues that the main challenge in AI-assisted coding is not intelligence but continuity, as AI tools often lose project context between sessions. The company intr…
A Hacker News user asks whether Monte Carlo Tree Search implementation in open-source AI environments like Codex or Claude Code can improve code generation accuracy.…
A developer questions whether AI coding assistants like Codex and Claude are making developers better or just faster, warning that over-reliance on AI to fix bugs can erode problem-solving skills. The…
A developer argues that coding agents like Claude Code and Codex should not rely on historical documentation as primary context, but instead read the current source of truth such as schema, tests, and…