DAILY DROP · NOV 10, 2026

Today's drop: 2 new tools, 3 listing updates

The directory now lists 149 hand-checked tools. New today: 0, a free open-source AI security harness from 0sec Labs with a local web console, CLI and MCP server, and Neoverse, Neo's free catalog that gives MCP servers, agent skills and extensions a security verdict before you install them. Updated: Claude (Fable 5.2), Claude Code (v2.1.321) and Ollama (v0.40.16). AI for IT & Cybersecurity grows to 60 tools and Coding & Vibe Coding stays at 25. Pricing only where the official page states it.

Previous drop: Nov 9, 2026 →

Get the weekly dropThe best new AI tools, one email a week. Free.

New in the directory 2

Browse all 149
Tool
Category
Price
Status
Link
0 (0sec Labs)Free, open-source AI security harness from 0sec Labs (a Swiss lab backed by Y Combinator) for code review, pentesting, vulnerability research, reverse engineering, verifying findings and drafting fixes. Run 0 and it opens a local web console (no account needed) with chat, a findings queue and board, workflow templates for assessment, verification, fixes and research, reusable skills and source-linked memory; the same workflows run from a headless CLI (0 workflow run, with SARIF and other reports) or as an MCP server so Claude Code, Codex and other agents can call them. It is not a model: you connect your own model provider or a supported subscription. Binary analysis uses Ghidra through its 0verse add-on. Installs on Apple silicon Macs and x64/ARM64 Linux (npm, Windows, Docker and source installs are documented). Its README says the default shell runs on your host, so use an isolated executor for untrusted work, and only assess systems you are authorized to test; an optional scope plugin enforces target boundaries. About 1,190 GitHub stars; the repo dates from August 2026 but its public open-source launch was Nov 8, 2026, and it ships several releases a day (v0.28.9 on Nov 9). Very new, so treat it as early software.
Price Free and open source (MIT or Apache-2.0); you pay your model provider. Hosted 0cloud PR reviews: $100 free trial credits, then $1/credit ($5 per PR security test)
FREE TIERchecked 11/10
Neoverse (Neo)Free searchable catalog from Neo Security that gives AI add-ons a security verdict before you install them: MCP servers, agent skills, desktop apps, and browser and IDE extensions (VS Code, JetBrains, Cursor, Windsurf, the Chrome, Edge and Firefox stores, GitHub, the MCP registry and package managers such as Homebrew, Winget and Chocolatey). Neo says it has classified more than 4 million items; each analyzed one is marked Malicious, Unsafe or Safe with the headline finding behind the verdict, a summary and version history, based on static analysis, a sandboxed run, a check of the app's behavior against its own docs, plus CVE and GitHub advisory data, repeated for each new version. Free with email sign-in; full findings, evidence and API access are for Neo customers or on request. Neo says signing up does not protect your machine: it is a lookup, not a blocker. Public launch Nov 9, 2026. Verdicts come from Neo's own automated research, so treat them as one signal and still read what a tool can access.
Price Free catalog with email sign-in; full findings and API access for Neo platform customers
FREE TIERchecked 11/10

Why these two

  • 0 is a free, open-source (MIT or Apache-2.0) security harness from 0sec Labs, a Swiss team backed by Y Combinator. It is not a model: you connect your own model provider, then run code review, pentest, vulnerability research, verification and fix workflows from a local web console with a findings queue and board, from a headless CLI that writes SARIF and other reports, or as an MCP server so Claude Code or Codex can call the same workflows. Binary analysis goes through Ghidra with its 0verse add-on. About 1,190 GitHub stars; the repo dates from August, the public open-source launch was Nov 8 and it ships several releases a day (v0.28.9 on Nov 9). Its README is clear that the default shell runs on your host, so use an isolated executor for untrusted work, and only point it at systems you are authorized to test. A hosted 0cloud for PR reviews starts with $100 in trial credits, then $5 per PR test. It sits next to Strix, Shannon and Codex Security.
  • Neoverse answers the question before you install: is this MCP server, agent skill or extension safe to run? Neo, an AI security company, made its catalog free to search on Nov 9 with an email sign-in. Neo says it covers more than 4 million items from IDE marketplaces, browser stores, GitHub, the MCP registry and package managers, and marks each analyzed one Malicious, Unsafe or Safe with the key finding, a summary and version history. The verdicts come from Neo's own automated static, sandbox and documentation analysis, so treat them as one signal, not a guarantee, and Neo itself says signing up does not protect your machine. It pairs with SkillSpector and Snyk Agent Scan, which scan what you already have.

Listing updates

Checked on Nov 10, 2026 against official pages and release notes.

  • Claude: Claude Fable 5.2 (Nov 9) is Anthropic's model for the hardest reasoning and long-running agent work, on Pro, Max, Ultra, Team and Enterprise plans and in the API as claude-fable-5-2 at $8 per million input and $40 per million output tokens (down from $10 and $50 for Fable 5.1), with a 1M-token context. Anthropic still suggests starting most coding work on Claude Opus 5.5. Claude Mythos 5.2 is the same underlying model; Fable carries strong cybersecurity and biology safeguards so it can be offered to everyone, while Mythos is limited to organizations verified through programs such as Anthropic's Cyber Verification Program.
  • Claude Code: v2.1.321 (Nov 9) makes Fable 5.2 the default Fable model and fixes several security issues, including MCP OAuth requests sending secrets such as refresh tokens to another host when a server redirected them, a read-only Bash command that could run outside the sandbox without a prompt, and deny rules not applying to files written by cp or mv into a directory. v2.1.322 adds fast mode on Vertex. Worth updating.
  • Ollama: v0.40.16 (Nov 9) adds Ripple Preview, a 65B dense model for agentic coding (ollama run ripple-preview), and makes ollama launch claude always route Claude Code to the model you picked.

Category changes

Checked, not listed

  • Kitten Process (Eye Security): a 12-step vulnerability-research skill for Claude Code and Codex, used to find a CVSS 10.0 chain in ASUS Control Center; we could not confirm which GitHub repo holds it, so it waits.
  • Muse Ember (Meta): a new low-cost API model for agent subtasks; we list tools you use directly rather than every API model.
  • Strands Decider: Amazon's case study on replacing an LLM with a decision model for ticket labeling is interesting for IT ops, but it is a model release, not a tool most readers can try today.
  • Someone Was Here (Mac sign-in history) and MeowDisplay: popular Show HNs, but not AI tools.
  • STE80 Humanizer and phoneuse: a writing skill and an iPhone-control CLI; outside our coding and IT focus.
  • OpenCode v2.2.7, Hermes Agent v0.23.1 and Orca v1.4.255: routine releases, no listing change.