WhatThePort is a free, open-source macOS 14+ menu bar app that lists every running dev server, showing its branch, the agent session that started it (Claude Code, Codex, Conductor, or Vercel preview),…
Nvidia launched OpenShell at GTC San Jose, an Apache 2.0 open-source runtime that sandboxes AI agents using Linux Landlock LSM and seccomp BPF kernel-level enforcement rather than application-layer al…
AuraPunk is being built as an Agentic Development Environment (ADE) that organizes autonomous coding agents as first-class engineering work, using cards/SPECs to bind intent, execution, and evidence a…
A developer's analysis of roughly 4,300 real coding-agent sessions (Claude Code and Codex, 43 developers, ~350,000 LLM steps) found that the median LLM step re-sends about 119,000 cached prefix tokens…
AWS's Agent Toolkit for AWS, an open-source Python project with 2.7k GitHub stars last updated in September 2026, provides official MCP servers, skills and plugins that let coding agents build and dep…
A developer launched Omnesis, a self-hosted private context layer that connects ChatGPT, Claude, Codex, Openclaw and Hermes agents to personal data sources including WhatsApp, iMessage, bank transacti…
A developer is building Crewlo, an open-source desktop workspace that visualizes coding-agent interactions as a voxel studio, forked from Munder Difflin and retaining its agent-engine foundation while…
TypeSafe AI's Jev decision model returns type-safe structured values — a choice, a score, or a probability — instead of generated text, priced at 4 cents per million input tokens with no output charge…
A developer released an open-source API library that syncs any blog to Substack in one click, covering both Notes and newsletter articles. The project ships as three products — a Python client and CLI…
Darktrace's Signal Labs reported that coding agent harnesses store conversation history locally without verifying that responses came from the model, allowing any process with write permission to inje…
OpenAI said in a September 10, 2026 update that an investigation found Tristan Buckmaster's Codex prompts from the two months before its Navier-Stokes announcement could not have influenced its system…
NVIDIA released OpenShell 0.1.0, an open-source runtime that enforces which systems and data an AI agent can access through sandboxed execution, controlled service access, credential management, and f…
David Zhang released jevgrep, a command-line tool that searches code repositories for coding agents, and its current repository reports a 28.6% reduction in coding-agent costs — from $7.62 to $5.44 ac…
A study of 213 validated test cases found that malicious behavior split across multiple individually benign agent skills can evade per-skill scanners and runtime monitors on systems including OpenClaw…
Agnostic-ai released v0.71.0, adding user-level MCP server installation for Claude Code, Codex, Cursor, Copilot, Gemini, Qoder, OpenHands, and Augment, plus a settings spec that sets default model and…
A developer built ELY Agent Input Preflight, an open-source CLI that independently verifies AI coding agent runs instead of trusting the agent's exit code 0. The tool checks required project inputs be…
A Cloudflare security-audit skill for AI coding agents surged to roughly +15.4k GitHub stars in seven days, according to a lead software engineer who examined the project. The skill turns agents such …
OpenRig released @openrig/cli, a multi-agent harness that lets developers define an agent team in YAML and boot it with one command, running Claude Code and Codex in the same rig. The tool requires No…
A developer built rai-attribution-bench, a benchmark testing whether AI models correctly apply rai-lint's five-tier AI attribution rubric when assigning git commit footers. Three flagship models score…
Developer marciob released agenttab, a macOS tool that displays AI agent state as icons in terminal tab titles for Claude Code, Codex, and OpenCode. The tool maps states to icons — a blank title when …