Skip to content
Fabraix

Self-hosted alternatives to Fabraix

200 self-hosted apps like Fabraix, closest match first.

Top picks

  1. A

    Adrian

    Launch

    Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.

    FreeOpen sourceSelf-hosted

  2. P

    Pentagi

    Launch

    PentAGI is a self-hosted AI agent system for penetration testing, which the site describes as a fully autonomous agent that works through a terminal, a browser, an editor and external search. Everything runs in a sandboxed Docker environmen

    FreeOpen sourceSelf-hosted

  3. P

    Pentest Harness

    Launch

    Pentest Harness — Heaven for Hackers. A self-hosted AI agent harness for authorized pentests, bug bounty, security labs, and CTFs. Bring your own AI model API; sessions stay local.

    FreeOpen sourceSelf-hosted

  4. D

    Darkmoon

    Launch

    Open-source autonomous AI penetration testing. 50 specialist agents across web, API, cloud, Active Directory, Kubernetes, CI/CD and AI/LLM (OWASP LLM Top 10). Runs on a local LLM behind a Privacy Gateway. Integrates with GitHub, GitLab, Jen

    FreeOpen sourceSelf-hosted

  5. P

    Prismor

    Launch

    Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

    FreeOpen sourceSelf-hosted

  6. R

    RedAmon

    Launch

    Open-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens PRs that fix what it finds. MCP both ways: plug in any MCP s

    FreeOpen sourceSelf-hosted

More like Fabraix

7
B

BugTraceAI

Open-source, self-hosted web pentesting suite

Launch
8
F

FCaptcha

Self-hosted, invisible CAPTCHA that detects AI agents driving real browsers

Launch
9
L

Langfuse

Trace, evaluate, and improve AI agents with one open platform

Launch
10
V

Valmis

The AI Agent designed for work with security in mind

Launch
11
P

Prediction Guard

Seamlessly integrate private, controlled

Launch
12
O

OS

Enables organizations to create and deploy customizable AI agents

Launch
13
A

AgentX

Enhance customer engagement with intelligent, customizable AI chatbots

Launch
14
O

Open Kritt

Open-source, self-hosted AI vulnerability research tool

Launch
15
Z

ZizkaDB

Audit trail database for AI agents

Launch
16
A

Allama

🔥🔥🔥 AI security automation platform

Launch
17
A

Agenta

Open-source LLMOps platform for prompt management, LLM evaluation

Launch
18
P

PandaProbe

open source agent engineering platform: traces, evals

Launch
19
A

Airecon

AIRecon is an autonomous cybersecurity agent

Launch
20
E

EpicStaff

Source-available, self-hosted platform for building AI agent flows

Launch
21
S

Switch

Connect any AI agent to your team in Slack, Teams & Discord

Launch
22
P

Promptmask

Never give AI companies your secrets

Launch
23
H

Helix

Private Agent Fleet with Spec Coding

Launch
24
P

Pocketpaw

Your AI agent in 30 seconds

Launch
25
E

emisar

Let AI agents investigate and operate infrastructure through declared actions

Launch
26
A

Agentsystems

Self-hosted app store and runtime for AI agents

Launch
27
A

aweb

Communication for AI agents: stable identity, durable mail and chat

Launch
28
S

Skillhub

Self-hosted, open-source agent skill registry for enterprises

Launch
29
A

AiSOC

Open-source AI Security Operations Center: alert fusion, LLM-agent triage

Launch
30
A

Alma by Olivares.AI

Self-hosted control plane that maps and governs what your AI agents can reach

Launch
31
O

Opengeni

Open, self-hostable agentic service for organizations

Launch
32
P

Proxy

Personal Agent Proxy is an open-source, self-hostable access layer

Launch
33
O

obsei

Obsei is a low code AI powered automation tool

Launch
34
C

ClawFleet

Deploy a fleet of AI agents (OpenClaw, Hermes) on your machine in 10 minutes

Launch
35
P

Pad

Project Management for the agent era

Launch
36
A

Auto Browser

Give your AI agent a real browser — with a human in the loop

Launch
37
M

Muxi

Deploy intelligence. Open-source infrastructure for AI agents in production

Launch
38
C

CyberVerse

Self hosted, real-time digital human agent platform

Launch
39
A

Agenvoy

Self-hosted 24/7 personal AI agent that runs on your own machine

Launch
40
A

Anubis

Web AI firewall utility which protects upstream resources from scraper bots

Launch
41
G

Go Away

[Mirror] Self-hosted abuse detection

Launch
42
F

Flamehaven-Filesearch

Self-hosted RAG search engine — 34 formats, BM25+hybrid search, multi-LLM…

Launch
43
S

Spanlens

Drop-in observability platform for OpenAI, Anthropic, and Gemini

Launch
44
G

GoModel

AI gateway written in Go with a unified OpenAI-compatible API

Launch
45
O

Open Multi-Agent

Self-hosted TypeScript agent runtime

Launch
46
L

LitterBox

A self-hosted sandbox for red teams

Launch
47
O

OpenTaint

The open source taint analysis engine for the AI era

Launch
48
O

OpenAgentCore

Open-source, self-hosted implementation of the OpenAI Agents API

Launch
49
C

Cycles

Control AI agent costs and actions

Launch
50
O

Openclaw Runbook

Unofficial OpenClaw runbook for running agents day to day without burning money

Launch

About Fabraix

F

Fabraix

Adversarial Verification for AI Agents

Fabraix builds AI agents that red-team other AI systems. Its product, Nyx, runs automated adversarial tests against customer-facing AI, such as chatbots, autonomous agents, multi-agent systems, browser agents and voice agents, to find vulnerabilities like prompt injection, jailbreaks, PII leakage, tool hijacking and fraud. The tests are multi-turn and adaptive, and they can be run as a blackbox without special access. The company says it has found vulnerabilities in agents at dozens of Fortune 500 companies. The site lists use cases by industry, including finance, healthcare, retail, telecommunications and travel, and shows case studies. A public Playground is an open source arena for breaking real agents, and the company publishes research on adversarial cost to exploit. It is aimed at companies that deploy AI to customers and need to test it before attackers do. The site asks visitors to book a demo.

Category
AI
Website
fabraix.com