FRENES

Business agents · agent infrastructure component

Text-to-CAD: review, pricing, security and alternatives

Text-to-CAD is an open-source agent infrastructure component published by earthtojake, in the business agents family. Text-to-CAD gives AI agents computer-aided design capabilities for creating CAD models from text descriptions. Its repository has 22,895 stars and its last commit is from October 20, 2026.

Score
73/100
Adoption (stars) 28/40
Activity (commits, releases) 30/30
Framework (licence, control, models) 15/30
Open sourceActively maintainedLow risk

What Text-to-CAD does

Text-to-CAD belongs to the business agents family: agents specialised in one job: customer support, sales, finance, legal, HR, security. On our grid it ranks #6 of the 52 projects of this family listed in the directory.

It is not an agent in itself: it is a component other agents use (memory, isolated execution, web access, model gateway or monitoring). You pick it based on the agent or framework it has to equip.

Who is Text-to-CAD for?

It targets a specific job (customer support, sales, finance, legal…) with workflows already set up. Typical tasks people give it:

  • handle first-line customer requests
  • prepare standard documents
  • track cases and follow up

Access and human control

Its documentation does not detail the access granted to the agent: check the settings before connecting it to your accounts.

We could not establish whether it asks for human approval before sensitive actions: test it first on an unimportant account or folder.

Run commands in a terminalRun commands in a terminal : 8 %8 %Read and edit filesRead and edit files : 21 %21 %Drive a web browserDrive a web browser : 4 %4 %Call online services and APIsCall online services and APIs : 37 %37 %Read and send messagesRead and send messages : 17 %17 %
Share of the 52 agents in the family that have each access, according to their documentation. In orange, Text-to-CAD's access.

Text-to-CAD pricing

The code is free, under the MIT licence.

Getting started with Text-to-CAD

  1. Install it: the project ships as a Python package (install with pip or uv). The exact command is in the repository README.
  2. Start with the minimal example from the docs, then add one tool at a time and check what the agent does with it.
  3. Give it a short, checkable task, review the result and its action log, then raise the difficulty step by step.

Security: risk level

A business agent acts on the company's behalf: define what it may promise, refund or change, and keep a record of its decisions.

Three habits: least privilege (minimal rights, dedicated keys), human approval for irreversible actions, a sandbox for code execution. The AI agent security check reviews your setup in a few minutes.

Project activity and releases

Created on April 22, 2026, the earthtojake/text-to-cad repository has 22,895 stars, 2,229 forks and 4 open issues, with 1,462 commits in total. It received changes this month.

Over the last 52 weeks: 1,116 commits, an average of 21.5 per week.

Nov 2, : 0 · Nov 2, 2025Nov 2,Nov 9, : 0 · Nov 9, 2025Nov 16, : 0 · Nov 16, 2025Nov 23, : 0 · Nov 23, 2025Nov 30, : 0 · Nov 30, 2025Dec 7, : 0 · Dec 7, 2025Dec 14, : 0 · Dec 14, 2025Dec 21, : 0 · Dec 21, 2025Dec 28, : 0 · Dec 28, 2025Dec 28,Jan 4, : 0 · Jan 4, 2026Jan 11, : 0 · Jan 11, 2026Jan 18, : 0 · Jan 18, 2026Jan 25, : 0 · Jan 25, 2026Feb 1, : 0 · Feb 1, 2026Feb 8, : 0 · Feb 8, 2026Feb 15, : 0 · Feb 15, 2026Feb 22, : 0 · Feb 22, 2026Feb 22,Mar 1, : 0 · Mar 1, 2026Mar 8, : 0 · Mar 8, 2026Mar 15, : 0 · Mar 15, 2026Mar 22, : 0 · Mar 22, 2026Mar 29, : 0 · Mar 29, 2026Apr 5, : 0 · Apr 5, 2026Apr 12, : 0 · Apr 12, 2026Apr 19, : 0 · Apr 19, 2026Apr 19,Apr 26, : 10 · Apr 26, 2026May 3, : 6 · May 3, 2026May 10, : 1 · May 10, 2026May 17, : 9 · May 17, 2026May 24, : 12 · May 24, 2026May 31, : 36 · May 31, 2026Jun 7, : 26 · Jun 7, 2026Jun 14, : 72 · Jun 14, 2026Jun 14,Jun 21, : 27 · Jun 21, 2026Jun 28, : 84 · Jun 28, 2026Jul 5, : 23 · Jul 5, 2026Jul 12, : 100 · Jul 12, 2026Jul 19, : 0 · Jul 19, 2026Jul 26, : 1 · Jul 26, 2026Aug 2, : 34 · Aug 2, 2026Aug 9, : 85 · Aug 9, 2026Aug 9,Aug 16, : 139 · Aug 16, 2026Aug 23, : 44 · Aug 23, 2026Aug 30, : 29 · Aug 30, 2026Sep 6, : 12 · Sep 6, 2026Sep 13, : 80 · Sep 13, 2026Sep 20, : 201 · Sep 20, 2026Sep 27, : 3 · Sep 27, 2026Oct 4, : 39 · Oct 4, 2026Oct 4,Oct 11, : 36 · Oct 11, 2026Oct 18, : 1 · Oct 18, 2026Oct 25, : 6 · Oct 25, 2026Oct 25,
Commits per week on the main repository, last 52 weeks (GitHub API, checked October 25, 2026).

87 releases in total; 30 in the last twelve months. Latest release: v0.7.26, on October 20, 2026.

v0.7.8 · Oct 2, 2026v0.7.8Oct 2, 2026v0.7.7 · Oct 2, 2026v0.7.11 · Oct 3, 2026v0.7.10 · Oct 3, 2026v0.7.9 · Oct 3, 2026v0.7.14 · Oct 5, 2026v0.7.13 · Oct 5, 2026v0.7.12 · Oct 5, 2026v0.7.15 · Oct 6, 2026v0.7.18 · Oct 8, 2026v0.7.17 · Oct 8, 2026v0.7.16 · Oct 8, 2026v0.7.19 · Oct 9, 2026v0.7.20 · Oct 10, 2026v0.7.21 · Oct 11, 2026v0.7.24 · Oct 18, 2026v0.7.23 · Oct 18, 2026v0.7.22 · Oct 18, 2026v0.7.26 · Oct 20, 2026v0.7.25 · Oct 20, 2026v0.7.25Oct 20, 2026
The latest 20 releases published on GitHub (hover a point for details).

Text-to-CAD vs other business agents

GitHub stars of the best-rated open-source projects in the business agents family. Stars measure attention, not quality: a heavily promoted project collects them fast, a specialised tool will have few.

DeepTutorDeepTutor : 42.5K42.5KVibe-TradingVibe-Trading : 36.5K36.5KPentAGIPentAGI : 32.3K32.3KGenOfficeGenOffice : 10.7K10.7KHolmesGPTHolmesGPT : 3.7K3.7KText-to-CADText-to-CAD : 22.9K22.9KYouTube Automation AgentYouTube Automation Agent : 4.6K4.6KRedAmonRedAmon : 3.2K3.2K
Log scale; Text-to-CAD in orange. Checked October 25, 2026.

Text-to-CAD and other business agents at a glance

The 7 best-ranked agents in the same family, 7 of them open source. The score out of 100 only applies to open-source projects; for proprietary services we show the published entry price. A dash marks information the documentation does not state.

Quick comparison: business agents
AgentModelScoreStars or entry priceSelf-hostableHuman approval
Text-to-CADopen source7322.9K ★––
DeepTutoropen source8242.5K ★yes–
Vibe-Tradingopen source8136.5K ★yes–
PentAGIopen source7732.3K ★yesno
GenOfficeopen source7410.7K ★yes–
HolmesGPTopen source743.7K ★yes–
YouTube Automation Agentopen source734.6K ★yesyes
RedAmonopen source733.2K ★yesyes

How we rated it

Score: 73/100, computed only from public, verifiable data, with no subjective testing or partnership:

  • Adoption 28/40: 22,895 stars on a log scale (40 points from about 200,000).
  • Activity 30/30: last commit less than a month ago, 30 releases in six months, 1,116 commits in a year.
  • Framework 15/30: licence, default human approval, self-hosting, model choice and documentation site.

The score does not say whether the agent will succeed at your tasks: it measures how solid the project is. The full grid is on the method page.

Verdict

Text-to-CAD is a serious option; check the limitations below before granting it access.

Strengths

  • Widely followed: 22.9K stars
  • Very active development
  • Frequent releases (30 in a year)
  • Permissive licence (MIT)

Frequently asked questions

Is Text-to-CAD free?

The software is free (MIT licence). You still pay for the model calls, unless you use a local model.

Is Text-to-CAD safe?

Our risk level: low. Give it minimum rights and approve irreversible actions.

Which models does Text-to-CAD use?

Its documentation does not specify the supported models.

Can Text-to-CAD be installed on your own server?

This is not clearly documented: check with the vendor.

What are the alternatives to Text-to-CAD?

In the same family: DeepTutor, Vibe-Trading, PentAGI, and GenOffice.

Text-to-CAD or DeepTutor: what is the difference?

Both belong to the business agents family. Text-to-CAD has 22.9K stars against 42.5K for DeepTutor. The right choice mostly depends on the access you are willing to give it.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score