The Stack

Open Source Radar — September 13: agents learn to hack

Today's trending list skews hard toward security: an autonomous pentest system, a red-team skill library for Claude, and a Rust CLI that solves the unglamorous problem of running five AI agents in the same repo without them stepping on each other.

Worktrunk (Rust, 7,391 stars) — A CLI for git worktree management built specifically for parallel AI agent workflows. Each Claude Code or Codex instance gets its own isolated working directory off the same repo, addressed by branch name, with none of the path-juggling that plain git worktrees demand. It's the tool for anyone who's tried to run five Claude Code or Codex sessions against one repo and watched them collide. Dual MIT/Apache-2.0 licensed, and the project's own September note claims it is now the most popular git worktree manager.

PentAGI (Go, 23,640 stars) — An autonomous penetration testing system that spins up a sandboxed Docker environment, deploys specialized AI agents (researcher, developer, infrastructure), and lets them loose on a target with 20+ built-in security tools including nmap, metasploit, and sqlmap. Agents share a smart memory system backed by a Neo4j knowledge graph, so they learn from previous recon and skip dead-end probes. Supports over ten LLM providers including local models via Ollama, ships with a clean web UI, and is fully self-hosted. MIT-licensed and one of the most complete open-source answers to the question of whether AI agents can run a pentest without burning your server down.

Claude-Red (Python, 3,799 stars) — A library of 78 structured SKILL.md files that turn Claude into an offensive security operator. Each file encodes domain expertise for a specific attack surface — SQL injection, shellcode generation, EDR evasion, ADCS abuse — across 23 categories. Drop the repo into your skills directory and Claude auto-loads the relevant skill based on conversation context, so you only pay the context cost for tools in use. Works across the Claude skills system, Claude Code, and manual Claude.ai projects. Aimed at authorized red-team engagements, bug bounty triage, and CTF preparation.

Worth watching this week.

Do you think AI agents should have unrestricted access to offensive security tools? Tell us in the comments.

Sources: Worktrunk (GitHub) · PentAGI (GitHub) · Claude-Red (GitHub)

Salesforce's Dreamforce pitch: let agents replace the UI

Two stories from today worth your time: Salesforce arguing that its own interface is the thing standing between customers and its data, and Huawei's chairman saying out loud what his compute business is aiming at. Salesforce opened Dreamforce by launching AIforce, a layer that pushes the company'

Commerce ordered Kalshi to pull its AI compute price tracker

Two stories today about where AI's bottlenecks actually are: who is allowed to put a price on compute, and whether an agent that works today will work tomorrow. The US Commerce Department ordered Kalshi to take down its AI-compute forward curve last month, citing national security concerns,

Musk wants rivals to run test harnesses on each other's models

Two stories today run the same test on AI's gatekeepers: who gets to check the work before it ships, and what the answer looks like when the checker isn't the government. Then a biology dataset turned into a toy shows what happens when the public gets

A cop searched 19,000 Flock cameras to type "LMAO"

The pitch for automated license-plate cameras is that they catch stolen cars and wanted suspects. Flock Safety's own audit logs suggest a lot of the searches were for something else entirely. A review of Flock Safety's search logs found officers using the one field meant

Read more

Salesforce's Dreamforce pitch: let agents replace the UI

Commerce ordered Kalshi to pull its AI compute price tracker

Musk wants rivals to run test harnesses on each other's models

A cop searched 19,000 Flock cameras to type "LMAO"