Engineering manager jbreu published Autopoiesis, a proof-of-concept on GitHub that ships a fully configured AI platform inside a repository using containers, configs, and scripting in roughly 20 KByte…
CleanCode launched as a canvas-based Agentic Development Environment (ADE) that gives each feature its own isolated Git worktree, canvas, terminals, execution scope, and Agent sessions, letting coding…
Security firm Air Security disclosed on Thursday that a flaw it named Plugin4Shell lets an attacker who controls a plugin's code repository swap the plugin an AI coding agent installs for malicious co…
Security researchers at Accomplish AI found two sandbox escapes in OpenAI's Codex coding agent, including one called Heapjack that achieves unsandboxed remote code execution on a developer's machine f…
Developer Geoffrey Huntley released underclass, an OpenAI-compatible local proxy that pools multiple ChatGPT/Codex and GitHub Copilot subscriptions behind a single endpoint at /v1/responses, /v1/chat/…
A coding agent marketed as the fastest available claims to run more than 5x faster than Codex, according to promotional material for the tool. The agent is powered by OpenCode and is pitched at "high …
A new open-source tool called WTF (agent-wtf) lets developers auto-audit changes made by coding agents such as Claude Code, Cursor, Copilot, Codex, and Aider by inspecting the resulting Git diff rathe…
Enjambre, a new open-source Python kernel for coordinating swarms of AI agents, has been released with a single PyYAML dependency and support for Python 3.10 or newer on Linux, macOS and Windows. The …
OpenAI claimed a solution to the Navier–Stokes existence and smoothness problem on 8 September 2026, but mathematician Tristan Buckmaster stated roughly 12 hours earlier that his and Levent Alpöge's a…
AgentSec Audit launched as an automated security scanner, policy linter, and compliance certification tool for autonomous AI agents, tool configurations, and Model Context Protocol (MCP) servers. The …
OpenAI will retire GPT-5.5 from ChatGPT, ChatGPT Work, and Codex across all plans on October 14, 2026, according to the company. Codex users signed in with a ChatGPT account are directed to migrate to…
Orca is a desktop Agent Development Environment (ADE) that runs multiple AI coding CLI agents in parallel, giving each task its own git worktree so agents can work on the same repository without overw…
A developer who maintains Alca, a provider-tracking site, documented four distinct categories of "free" AI model quotas after repeatedly exhausting paid tiers: harness-locked pools usable only through…
AlphaDesk launched a market-research terminal that lets users query market data, SEC filings and US Treasury records through their own AI agent via 37 read-only MCP tools, with the code released under…
A design analysis of OpenAI's Codex agent framework argues that context compaction is fundamentally a control problem rather than a compression problem. The writeup examines Codex commit 8444cf63, sho…
TypeSafe's Jev model generated platformer levels in real time at 319–375 ms latency and an estimated $0.00057 per request, according to a September 15, 2026 test by developer Hugo. The zero-shot class…
A developer built Turnstile, a machine-wide, memory-aware gate for macOS that coordinates builds and tests across parallel coding agents by placing lightweight shims for tools including swift, npm, vi…
A step-by-step guide published on building Codex skills details how to write skill.md files — markdown documents with YAML front matter that define when an AI agent should trigger a repeatable process…
AIR Security researchers Or Nevo, Dor Granat and Niv Hoffman published a September 17, 2026 advisory detailing Plugin4Shell, a flaw in which four coding agents pinned plugins to a commit hash but chec…
A developer released Worktrunk, an open-source Rust command-line tool that simplifies Git worktrees for running parallel AI coding agents like Claude Code and Codex. The tool, released in early 2026 u…