Simon Willison, a software engineer and blogger, launched Agentic Engineering Patterns, a new project documenting coding practices for building software with coding agents such as Claude Code and Open…
Developer Randal Schwartz has open-sourced dart-sdk-skills, a version-by-version skill package that equips AI coding agents with complete knowledge of Dart features from 1.0 to 3.14, addressing the tr…
JetBrains' AI Coding Agent Adoption Trends report, based on surveys of 15,000+ professional developers from May through July 2026, shows GitHub Copilot's adoption fell from 29% to 21% in 12 months, Op…
Chaitanya Giri's Munder Difflin v0.4.5 fixes inaccurate cost reports, broken semantic memory on Apple Silicon, and unreliable communication between AI workers in the local-first agent harness that wra…
Proliferate, an open-source, self-hostable AI IDE from YC S25, unifies Claude Code, OpenAI Codex, OpenCode, Cursor, and Grok in a single interface, allowing inter-agent delegation and reusable workflo…
A new agent skill called Clean, available via `npx skills add andalabx/skills --skill clean`, freed 5.3 GB on its first run and up to 7.3 GB in a super scan, clearing dev junk such as node_modules, .n…
The Linux Kernel's adoption of an 'Assisted-by' attribution tag for AI-generated code in 2024 has set a precedent for engineering teams. The policy, championed by Linus Torvalds, requires contributors…
Spotify's engineering platform team released Xirp, a free public beta macOS session manager for AI coding agents, on August 10. Xirp supports Claude Code, Gemini CLI, and OpenAI Codex, using git workt…
Security researcher Elad Meged of Novee Security demonstrated at Black Hat USA 2026 that a single GitHub issue can trigger remote code execution and exfiltration of API keys and tokens from AI coding …
A closed feature request on Anthropic's Claude Code repository asking the tool to support the open AGENTS.md format instead of its own CLAUDE.md drew 181 points and 103 comments on Hacker News, with c…
AGENTS.md, an open format for coding-agent project context now read automatically by 23 tools, has been shown by three research groups to double as an instruction-injection vector for credential theft…
A new interactive adaptation of the JAX scaling book chapter on transformer training parallelism lets readers drag sliders to see how data, tensor, pipeline, and expert parallelism affect communicatio…
SpaceXAI launched Grok Bot, a system of persistent AI agents that operate on dedicated cloud computers and can execute multi-step tasks across business applications, currently in beta for SuperGrok He…
DevSwarm 2.5.0 introduces DevSwarm Chat, a dedicated chat interface for locally installed coding agents including Claude, GitHub Copilot, and OpenAI Codex, and extends the user's VS Code theme across …
PRO-LONG, a minimal memory addition for LLM agents that appends every observation, action, and outcome to a structured log.txt and retrieves it programmatically, improves performance on the ARC-AGI-3 …
Pi, a minimal terminal coding harness, achieved a 66.7% pass rate (20 of 30 tasks) in Composio's benchmark using DeepSeek V4 Flash, the best among four newly tested harnesses, and was the cheapest at …
A developer found that their AI coding agents performed worse after upgrading to newer models like Claude Opus 5 and GPT-5.6, but an audit revealed the issue was stale custom prompts, not model regres…
LLM Wiki, a new open-source tool released as a plugin for Claude Code, OpenAI Codex, and OpenCode, enables parallel multi-agent research and session memory without hoarding transcripts, using human-ow…
Sol-Luna, an MCP server for OpenAI Codex, lets a supervising GPT-5.6 Sol agent delegate bounded implementation tasks to isolated GPT-5.6 Luna worker threads, with scope enforcement and verification. I…
Sankalp placed 12th among 183 entrants with a time of 1,804.779 microseconds on an NVIDIA B200 in GPU Mode's qr_v2 competition, using OpenAI Codex to make over 1,500 submissions over 14 days. His resu…