Self-hosted alternatives to Fabraix
200 self-hosted apps like Fabraix, closest match first.
Top picks
- A

Adrian
LaunchOpen-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
- P

Pentagi
LaunchPentAGI 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
- P
Pentest Harness
LaunchPentest 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
- D
Darkmoon
LaunchOpen-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
- P

Prismor
LaunchSelf-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
- R

RedAmon
LaunchOpen-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
Alma by Olivares.AI
Self-hosted control plane that maps and governs what your AI agents can reach
Flamehaven-Filesearch
Self-hosted RAG search engine — 34 formats, BM25+hybrid search, multi-LLM…
Openclaw Runbook
Unofficial OpenClaw runbook for running agents day to day without burning money
About Fabraix
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


