FRENES

Automation · agent platform

Nexent: review, pricing, security and alternatives

Nexent is an open-source agent platform published by ModelEngine Group, in the automation family. Nexent supports no-code agent creation by combining tools, skills, memory, orchestration and execution controls. Its repository has 6,028 stars and its last commit is from October 23, 2026.

Open sourceSelf-hostableActively maintainedLow risk

What Nexent does

Nexent belongs to the automation family: platforms, often visual, that chain steps, apps and models into workflows with or without an agent. On our grid it ranks #11 of the 26 projects of this family listed in the directory.

You use it from: web app. It can run on your own machine or server.

Who is Nexent for?

It is for teams that want to connect their tools (CRM, e-mail, spreadsheets) and hand the AI the steps that require reading or deciding. Typical tasks people give it:

  • qualify incoming requests and route them
  • extract data from documents into a spreadsheet
  • generate periodic reports

It is a good candidate if you prefer doing everything in a browser, with no install and your data must stay on your machines.

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 : 15 %15 %Drive a web browserDrive a web browser : 12 %12 %Call online services and APIsCall online services and APIs : 31 %31 %Read and send messagesRead and send messages : 15 %15 %Control the screen, keyboard and mControl the screen, keyboard and m : 4 %4 %
Share of the 26 agents in the family that have each access, according to their documentation. In orange, Nexent's access.

Nexent pricing

The code is free, under the MIT licence.

Getting started with Nexent

  1. Install it: the project ships as a Python package (install with pip or uv). The exact command is in the repository README.
  2. Create an API key with the model provider and put it in an environment variable, never in a shared or versioned file.
  3. Give it a first playground with nothing at stake: a test folder, a secondary account or a throwaway project. Only open your real accounts once you have seen how it behaves.
  4. Give it a short, checkable task, review the result and its action log, then raise the difficulty step by step.

Security: risk level

A workflow runs unattended: limit the credentials it holds and log what it sends.

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 28, 2025, the ModelEngine-Group/nexent repository has 6,028 stars, 753 forks and 187 open issues, with 5,977 commits in total. It received changes this month.

Over the last 52 weeks: 1,995 commits, an average of 38.4 per week.

Nov 2, : 41 · Nov 2, 2025Nov 2,Nov 9, : 42 · Nov 9, 2025Nov 16, : 43 · Nov 16, 2025Nov 23, : 67 · Nov 23, 2025Nov 30, : 80 · Nov 30, 2025Dec 7, : 84 · Dec 7, 2025Dec 14, : 36 · Dec 14, 2025Dec 21, : 42 · Dec 21, 2025Dec 28, : 40 · Dec 28, 2025Dec 28,Jan 4, : 11 · Jan 4, 2026Jan 11, : 56 · Jan 11, 2026Jan 18, : 31 · Jan 18, 2026Jan 25, : 89 · Jan 25, 2026Feb 1, : 77 · Feb 1, 2026Feb 8, : 72 · Feb 8, 2026Feb 15, : 83 · Feb 15, 2026Feb 22, : 1 · Feb 22, 2026Feb 22,Mar 1, : 58 · Mar 1, 2026Mar 8, : 91 · Mar 8, 2026Mar 15, : 77 · Mar 15, 2026Mar 22, : 40 · Mar 22, 2026Mar 29, : 41 · Mar 29, 2026Apr 5, : 14 · Apr 5, 2026Apr 12, : 10 · Apr 12, 2026Apr 19, : 7 · Apr 19, 2026Apr 19,Apr 26, : 17 · Apr 26, 2026May 3, : 23 · May 3, 2026May 10, : 5 · May 10, 2026May 17, : 22 · May 17, 2026May 24, : 11 · May 24, 2026May 31, : 33 · May 31, 2026Jun 7, : 20 · Jun 7, 2026Jun 14, : 13 · Jun 14, 2026Jun 14,Jun 21, : 18 · Jun 21, 2026Jun 28, : 25 · Jun 28, 2026Jul 5, : 24 · Jul 5, 2026Jul 12, : 16 · Jul 12, 2026Jul 19, : 20 · Jul 19, 2026Jul 26, : 30 · Jul 26, 2026Aug 2, : 51 · Aug 2, 2026Aug 9, : 45 · Aug 9, 2026Aug 9,Aug 16, : 26 · Aug 16, 2026Aug 23, : 38 · Aug 23, 2026Aug 30, : 48 · Aug 30, 2026Sep 6, : 31 · Sep 6, 2026Sep 13, : 30 · Sep 13, 2026Sep 20, : 37 · Sep 20, 2026Sep 27, : 30 · Sep 27, 2026Oct 4, : 30 · Oct 4, 2026Oct 4,Oct 11, : 9 · Oct 11, 2026Oct 18, : 43 · Oct 18, 2026Oct 25, : 67 · Oct 25, 2026Oct 25,
Commits per week on the main repository, last 52 weeks (GitHub API, checked October 25, 2026).

55 releases in total; 30 in the last twelve months. Latest release: v2.8.0, on October 23, 2026.

v1.8.0 · Feb 13, 2026v1.8.0Feb 13, 2026v1.8.0.1 · Feb 28, 2026v1.8.0.1-hotfix · Mar 4, 2026v1.8.0.2 · Mar 8, 2026v1.8.1 · Mar 14, 2026v2.0.0 · Mar 29, 2026v2.0.1 · Apr 10, 2026v2.0.2 · Apr 18, 2026v2.1.0 · Apr 30, 2026v2.1.1 · May 15, 2026v2.2.0 · Jun 3, 2026v2.2.1 · Jun 18, 2026v2.2.2 · Jul 1, 2026v2.3.0 · Jul 16, 2026v2.4.0 · Aug 5, 2026v2.5.0 · Aug 29, 2026v2.6.0 · Sep 16, 2026v2.6.1 · Sep 22, 2026v2.7.0 · Sep 30, 2026v2.8.0 · Oct 23, 2026v2.8.0Oct 23, 2026
The latest 20 releases published on GitHub (hover a point for details).

Nexent vs other automation

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

LangflowLangflow : 156K156Kn8nn8n : 208.5K208.5KSimSim : 29.9K29.9KAutoGPTAutoGPT : 187.7K187.7KDifyDify : 159.4K159.4KKestraKestra : 30K30KTrigger.devTrigger.dev : 16.6K16.6KActivepiecesActivepieces : 25.2K25.2KNexentNexent : 6K6K
Log scale; Nexent in orange. Checked October 25, 2026.

Nexent and other automation 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: automation
AgentModelScoreStars or entry priceSelf-hostableHuman approval
Nexentopen source716K ★yes–
Langflowopen source93156K ★yes–
n8nopen source85208.5K ★yes–
Simopen source8529.9K ★yes–
AutoGPTopen source84187.7K ★yes–
Difyopen source83159.4K ★yes–
Kestraopen source8030K ★yes–
Trigger.devopen source7716.6K ★yes–

How we rated it

Score: 71/100, computed only from public, verifiable data, with no subjective testing or partnership:

  • Adoption 21/40: 6,028 stars on a log scale (40 points from about 200,000).
  • Activity 30/30: last commit less than a month ago, 12 releases in six months, 1,995 commits in a year.
  • Framework 20/30: 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

Nexent is a serious option; check the limitations below before granting it access.

Strengths

  • Very active development
  • Frequent releases (30 in a year)
  • Can run on your side: data under control
  • Permissive licence (MIT)

Frequently asked questions

Is Nexent free?

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

Is Nexent safe?

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

Which models does Nexent use?

Its documentation does not specify the supported models.

Can Nexent be installed on your own server?

Yes, from the ModelEngine-Group/nexent repository. Data then stays with you, but security and updates are your job.

What are the alternatives to Nexent?

In the same family: Langflow, n8n, Sim, and AutoGPT.

Nexent or Langflow: what is the difference?

Both belong to the automation family. Nexent has 6K stars against 156K for Langflow. 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