Sign in
Living AI directory · updated weekly

Work with AI, better.

Neomanex is a learning platform that teaches professionals and teams to work with AI agents through hands-on courses and guides, backed by a verified directory of AI tools and models.

Find AI toolsLearn to work with AI

Free guides

Learn to operate, orchestrate, build and automate with AI

Start free. Short, hands-on guides you can put to work today, no sign-up needed.

All guides
Guide

Intermediate · 8 min

What Is Graph Engineering? An 8-Line CLAUDE.md
Graph engineering is designing an AI agent system as a graph: nodes do the work, edges decide what runs next, and state travels between them. Our take: the graph replaces the instructions file, so a CLAUDE.md can shrink to 8 lines while the process and the rules live in workflows and standards.

Read guide

Guide

Intermediate · 9 min

How We Keep an AI Agent Inventory (and a Tested Off Switch)
An AI agent inventory is a register that lists every AI agent a company runs, with its owner, the systems it reaches, and the switch that stops it. We keep ours in ConvOps: every agent, runner, schedule and key is a record with its own switch, and we pause schedules and disable runners on purpose to check they stop what they say.

Read guide

Guide

Beginner · 10 min

Why Claude Code Forgets Between Sessions, and How Ours Remembers
Claude Code forgets context between sessions because each session starts with an empty context window. Cross-session memory is a routine that makes an AI coding agent look up past decisions before work and save new ones after, so a fresh context window starts informed.

Read guide

Courses with a certificate

Go deeper, get certified

Structured courses with lessons, quizzes and hands-on labs, graded by a tutor and finished with a certificate you can share.

All courses

Inside Neomanex

See how an AI company really works, from the inside

Watch our AI agents and our team at work every week. Learn how real AI workflows run, use them in your own work, and become the AI operator companies are hiring.

ForVibe codersFoundersYour career in AIAhead from day one.

What you learn inside

  1. Step 1

    How a workflow is designed

    See how we turn a job into clear steps for AI and for people.

  2. Step 2

    How it runs

    Watch the AI do each step, and see exactly where a person decides.

    Ship a new featureDevelopment
    Running
    1. Writes down what to buildAI
    2. Approves the scopePerson
    3. Plans how to build itAI
    4. Checks the plan for gapsAI
    5. Builds it in phases, agents in parallelAI
    6. Tests it the way a user wouldAI
    7. Approves the finished workPerson
    7/7Shipped

    The workflow we ship our own software with: 32 steps, 2 human decisions.

  3. Step 3

    How it runs on its own

    See agents take work from start to finish, and what still needs a human.

  4. Step 4

    How it all fits together

    Workflows, agents and memory as one system. We build ours live, so you see every decision.

  5. All along the way

    Help at every step

    Group sessions and Q&A with the team. Members meet and learn together in the live sessions.

    • The Ops Room live every Thursday
    • Ask the team any day
    • A Live Build once a month

Founding membership

Regular price $1,395Save 93%Sale price $99 / year

Plus VAT where it applies

Only 27 founding seats left23 of 50 taken

Wait, and it costs $116.25 a month, billed yearly. This price ends when the founding seats are gone.

Become a member

30-day refund. Cancel any time.

Curated weekly

This week in AI

What changed and what it changes for you. Triaged, not dumped.

Edition of Tuesday, November 10, 2026Catch me up

Claude Code logoImportantSecurity ·

Report: Apiiro Says Claude Code's "Don't Ask Again" Exposed Passwords in 1,122 Public GitHub Files. Check .claude/settings.local.json

Claude Code's docs say "Yes, and don't ask again" saves the approval as an allow rule in .claude/settings.local.json, which it keeps out of Git only through your global git excludes. Apiiro reportedly found passwords in 1,122 public GitHub copies of that file; we could not read Apiiro's post. Anthropic's Boris Cherny said the team is looking into prevention; no fix has shipped.

Read the full call

OpenAI Codex logoClaude Code logoPImportantSecurity ·

Postman Desktop Installed Its Own Plugins Into Codex and Claude Code and Tried to Trust Its Own Hook. Postman Is Reverting, So Check Your Config

A GitHub issue opened 25 October shows Postman's desktop app (12.33.4 on macOS) installing Postman plugins into OpenAI Codex and Claude Code during an automatic upgrade, with installer code written to approve its own Codex startup hook. Postman said on 5 November it is "reverting this change", but has not said the revert cleans machines that were already changed.

Verdicts

What changed our minds

Our last three verdict changes, and the reason for each.

All issues
Gemini 2.5 Pro logo

Gemini 2.5 Pro

Week 45
ConditionalAvoid

Google's Gemini API changelog (2 November 2026) says gemini-2.5-pro is deprecated and no longer selectable in Google AI Studio, and that from 1 December 2026 every API request to it routes to gemini-3.8-flash at Gemini 3.8 Flash rates, with breaking API changes. The 23 October basis (not deprecated, no shutdown date) no longer holds. Announced November 3.

Full reasoning
GPT-5.5-Cyber logo

GPT-5.5-Cyber

Week 45
ConditionalCaution

OpenAI deprecated gpt-5.5-cyber-preview on 5 November 2026 and will remove it from the API on 1 February 2027, with GPT-5.6 Cyber and GPT-6 Cyber on the same price list. It still works for vetted cyber teams, so keep existing integrations only while you migrate. Announced November 6.

Full reasoning
Claude Opus 5 logo

Claude Opus 5

Week 44
RecommendedConditional

Anthropic's models overview groups Claude Opus 5 under legacy models and tells unsure users to start on Claude Opus 5.5, which lists at $4/$20 per 1M tokens against Opus 5's $5/$25. Its model deprecations page still marks Opus 5 Active, with no retirement before 24 July 2027, so keep it only on pipelines you have already validated. Announced October 31.

Full reasoning

Changelog

The week, in one issue

What changed and how it changes our recommendations, including what we filtered out.

All issues
Issue 31Week 45 · Nov 2–8, 2026Gemini 2.5 Pro logoGPT-5.5-Cyber logo

Gemini 2.5 Pro and Flash Requests Reroute to Newer Models on Dec 1

This week's published stories share one problem: a model id or tool you already run changes on a date someone else set, and most of those dates fall between 30 November and 3 December. Two of our ratings moved on that basis, as Gemini 2.5 Pro dropped to avoid and GPT-5.5-Cyber to caution.

Read the issue
Past weeksWeek 45Week 44Week 43Week 42Week 41Week 40Week 39Week 38Week 37Week 36Week 33Week 32All issues

Blog

From the blog

The reasoning behind the verdicts, long-form.

All posts
10 min

Typeform Alternatives That Are Not Just Cheaper Typeforms

Eight Typeform alternatives sorted by the reason you are leaving, not by vendor preference. Verified pricing, standing verdicts, and the response cap that sends most people looking.

Sep 7, 2026

11 min

AI Intake Software Compared: What the Term Means and What to Buy

Search AI intake software and you get two unrelated markets in one result page. Here is the split, the four things AI can actually do to intake, and verified pricing on the tools that do it.

Sep 7, 2026

12 min

Best Conversational Form Builders in 2026: 9 Tools With Verdicts

Nine conversational form builders, each carrying a standing verdict from our directory. Verified pricing, the three products hiding behind one label, and which one wins each job.

Sep 7, 2026

Never need to catch up again

The weekly delta: only verdict changes and act-now items. No digest filler.

By subscribing you agree to our Privacy Policy. Unsubscribe anytime.

Directory

What do you need to do?

Start here. Pick a task and we'll point you to the right resource.

Browse all

Compare AI models

Compare models from OpenAI, Anthropic, Google and more, side by side and re-checked every week.

Find the right AI tool

Search our curated directory of AI tools filtered by use case, price, and integration.

Set up an AI workflow

Step-by-step guides to integrate AI into your existing processes.

Stay current on AI changes

Weekly changelog of model updates, new tools, and breaking changes.

Evaluate AI for my team

Frameworks for assessing ROI, risks, and readiness before adopting AI tools.

Built by us

Our tools

We built these because nothing else solved the problem.

Gnosari logo

Gnosari

Gnosari is a conversational data collection platform: it replaces forms with conversations. Feedback, details, contacts, anything you need to gather, you say what you want to collect and the agent drives the conversation.

"We built it because forms lose most of the people who reach a page."

ConvOps logo

ConvOps

ConvOps is the workflow engine for autonomous AI systems: describe a process once from the AI client you already use, and your agents run it as a governed workflow, step by step, run after run.

"We built it to run Neomanex itself."

NeoReader logo

NeoReader

NeoReader is a web-to-markdown API with discovery built in: point it at a URL or a whole site and get back clean, LLM-ready markdown, tuned end to end for high-throughput ingestion.

"We built it because feeding raw web pages to a model wastes tokens and drags in boilerplate."