ToolBrain roadmap

What shipped, not what is promised. The figures below are computed when the site is built, so they are as fresh as the last build and never contain a promise that can quietly stop being true.

Generated on build: November 18, 2026 (UTC)

Shipped in the last 7 days (UTC)

11 posts published from Nov 12 to Nov 18, grouped by kind.

Reviews (3)

Guides (2)

Comparisons (3)

News (1)

Other posts (2)

Publishing rhythm (UTC weeks)

Measured from publish dates: 123 posts in the last 98 days, about 8.8 per week. Week 1 is the most recent 7 days.

Posts per week, last 14 weeks

  1. Week 1 Nov 12 – Nov 18 11
  2. Week 2 Nov 5 – Nov 11 11
  3. Week 3 Oct 29 – Nov 4 13
  4. Week 4 Oct 22 – Oct 28 10
  5. Week 5 Oct 15 – Oct 21 14
  6. Week 6 Oct 8 – Oct 14 9
  7. Week 7 Oct 1 – Oct 7 5
  8. Week 8 Sep 24 – Sep 30 8
  9. Week 9 Sep 17 – Sep 23 3
  10. Week 10 Sep 10 – Sep 16 2
  11. Week 11 Sep 3 – Sep 9 2
  12. Week 12 Aug 27 – Sep 2 7
  13. Week 13 Aug 20 – Aug 26 14
  14. Week 14 Aug 13 – Aug 19 14

By kind, last 98 days (UTC)

KindPostsShare
Reviews 40 33%
Guides 31 25%
Comparisons 23 19%
News 21 17%
Other posts 8 7%

Shares are rounded, so they may not add up to exactly 100%.

Most recent briefing: , 55 days before the build date.

How kinds are assigned: the slug is checked first for review, comparison, guide, then news keywords; if none match, the tags are checked the same way; anything else is Other. Arena-tagged entries are excluded here because they appear under Latest arena results. Guides that have been retired are still counted.

New in the comparison database

129

tools in the comparison database.

Open the comparison database →

Most recent additions

  • XERJ · AI Agent ·
  • OpenDesign · AI Design Agent Workspace ·
  • Retell AI · AI Voice Agents ·
  • Qodo · AI Code Review ·
  • Greptile · AI Code Review ·

The database rows carry no add dates, so this list is our own running record of the most recent additions.

Latest arena results

  • What can you actually run on 12 GB VRAM in 2026: the three 12 GB cards (RTX 3060 12GB, RTX 4070, RTX 5070), quantization and KV-cache math, why published tokens/sec for the same card disagree by up to 3.7x, and 12 GB vs 16 GB buying advice
    2026-11-18 · winner claude-haiku-5-5 · judge score 9.02 out of 10
  • GLM-5.3-Flash-E224-DGX-Spark review — a community GLM-5.3-Flash re-cut for two DGX Sparks
    2026-11-18 · winner glm-5.3-flash via OpenCode Go · judge score 8.73 out of 10
  • Claude Code vs GitHub Copilot for Beginners in 2026: Which Coding Agent Fits You?
    2026-11-17 · winner gpt-6-luna via Command Code · judge score 8.82 out of 10

Scores are as recorded for each match; not every match type uses the same scale.

See all arena results →

Shipped tools

12 dev tools are live.

In the queue

A queue is not a promise, and the order can change. These are the reviews we have lined up but not published yet, highest priority first. They carry no dates.

20 items queued, highest priority first.

P1 — 9 items

  1. Beginner's Guide to Coolify: Getting Started in 2026 · Beginner guide
  2. Beginner's Guide to DALL-E 3: Getting Started in 2026 · Beginner guide
  3. Beginner's Guide to Jasper: Getting Started in 2026 · Beginner guide
  4. Beginner's Guide to OpenDesign: Getting Started in 2026 · Beginner guide
  5. Beginner's Guide to Perplexity: Getting Started in 2026 · Beginner guide
  6. Beginner's Guide to Retell AI: Getting Started in 2026 · Beginner guide
  7. Beginner's Guide to Wix ADI: Getting Started in 2026 · Beginner guide
  8. Build Log: moving a tool-review pipeline onto local models and measuring the quality drop · Build log
  9. Build log: Claude Code to Codex handoff checklist (documented workflow) · Build log

P2 — 11 items

  1. Build log: small local model for MCP tool selection · Build log
  2. DeepSeek-V4.1-Flash-1017-obliterated Review 2026 · Tool review
  3. Generative engine optimization checklist for AI tool review sites · Tool review
  4. GLM-5.3-CYBERSECURITY-FP8 Review 2026 · Tool review
  5. GLM5.3-Flash-E224-DGX-Spark Review 2026 · Tool review
  6. Kromoss Review 2026 · Tool review
  7. LFM3-Omni-2B Review 2026 · Tool review
  8. MCP Protocol Deep Dive: Model Context Protocol for Tool Integration · Tool review
  9. Qwen3.5-4B-GLB-3D-Coder Review 2026 · Tool review
  10. Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 Review 2026 · Tool review
  11. Understanding Aug for AI Development · Tool review

Already published in this space

  • Beginner's Guide to Kimi K3: Getting Started in 2026
  • Claude Code vs GitHub Copilot for Beginners in 2026: Which Coding Agent Fits You?

How we review and publish

This is the pipeline behind every review and comparison on the site. It is here because older posts link here with wording like "our cron pipeline" and "how this guide was built".

Every tool is scored the same way

Each tool in the comparison database is scored on five dimensions — price, features, performance, documentation and support — so two tools are comparable on the same axes. The score is a reading of what the vendor publishes, not a lab measurement.

Browse the scored database →

Reviews are drafted by a panel, then judged

Review drafts are written by a panel of different AI models, scored by a separate judge, and then fact-checked against the vendor's own pages before anything is published. The arena keeps the record: which model wrote it, who judged it and what the scores were.

See the arena records →

What we did not do is stated

Guides carry a "How this guide was built" section naming their sources and saying plainly what was not tested. If we did not run something hands-on, the guide says so instead of implying we did.

Read the guides and their sources →