Skip to content
Back to the index

MARLA

PyPIInfrastructure

PulseGate's liveness check found it on 3 Oct 2026; it is registered on GitHub and PyPI and has been in the index since 10 Aug 2026. How this is checked

MARLA is an open-source multi-agent reinforcement learning architecture for training agents in NASimEmu offensive-security simulations. It supports PPO-based reinforcement learning and multi-agent workflows for developers and researchers.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI

Overview

5 features

Purpose: Training and evaluating multiple reinforcement-learning agents in NASimEmu security simulations.

Inferred · not functionally tested

Audience: reinforcement-learning researchers and security simulation developers

Inferred · not functionally tested

Functions: agents

Inferred · not functionally tested

Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

MARLA sits in PulseGate's Multi-agent & orchestration category. Inferred · not functionally tested: It focuses on training and evaluating multiple reinforcement-learning agents in NASimEmu security simulations. Inferred · not functionally tested: MARLA is an open-source project aimed at reinforcement-learning researchers and security simulation developers. Basis unknown · not verified: MARLA is open source under the MIT license. Basis unknown · not verified: MARLA is available on the command line, and it can be self-hosted.

Behind MARLA is Fran Enguix, and it first shipped in 2026. Development happens publicly on GitHub with 16 commits in the last 90 days. Inferred · not functionally tested: Among its 5 catalogued features are multi-agent learning, reinforcement learning, and PPO training.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Multi-agent learning
  • Reinforcement learning
  • PPO training
  • NASimEmu integration
  • Offensive security simulation

Topics: Inferred · not functionally tested

Tags
multi-agent-learningreinforcement-learningnasimemuoffensive-securityppo

JSON profile · Text profile · Access guide

Built with & integrations

Connectors
github
Runs on
CLISelf-hosted

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceFree tierGitHubActive maintenance

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed10 Aug · 17:45 UTC
    marla-agents seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about MARLA

What is MARLA?
Inferred · not functionally tested: MARLA focuses on training and evaluating multiple reinforcement-learning agents in NASimEmu security simulations. It is catalogued under Multi-agent & orchestration on PulseGate.
Who should use MARLA?
Inferred · not functionally tested: MARLA is an open-source project built for reinforcement-learning researchers and security simulation developers.
Does MARLA have a free plan?
Basis unknown · not verified: Yes — MARLA is open source under the MIT license and free to use.
What platforms does MARLA run on?
Basis unknown · not verified: MARLA runs on the command line. It can also be self-hosted.
Is MARLA still maintained?
PulseGate's liveness check found it on 3 Oct 2026. Its GitHub repository shows 16 commits in the last 90 days.
Who makes MARLA?
MARLA is developed by Fran Enguix.
When did MARLA launch?
MARLA first shipped in 2026.
Is MARLA open source?
Basis unknown · not verified: Yes — MARLA is open source under the MIT license, developed on GitHub.

Similar projects

Closest matches by what these projects do