Filigran XTM One (CTEM AI agents and autonomous attack chaining for OpenCTI and OpenAEV)

What it does

XTM One is the AI orchestration layer of Filigran's eXtended Threat Management (XTM) platform, launched June 9, 2026 and described by the vendor as available now. Its pre-packaged agents work across OpenCTI and OpenAEV: a CTEM Assistant routes work between agents; a Threat Hunt Creator searches for high-value indicators, converts them to platform-native detection rules and assembles them into an OpenCTI grouping; Scenario and Payload Creators turn intelligence into adversary-emulation scenarios in OpenAEV; and exposure-validation agents run scenarios against live environments, identify control gaps and generate detection rules for tools such as Splunk and CrowdStrike. In OpenAEV, Autonomous Attack Chaining (an Enterprise Edition feature documented in the OpenAEV docs) lets an XTM One orchestrator agent take a plain-language objective and scope, build the attack graph, execute injects, read the results, pivot and keep going until the objective is reached or it needs input; operators can steer a live run, answer its questions or stop it. Q3 2026 updates added human approval gates before agents take sensitive actions, a desktop app, a visual flow builder for multi-agent workflows, custom agents and bring-your-own-LLM, with SaaS or on-prem deployment. Enterprise Edition customers of OpenCTI/OpenAEV get a built-in set of agents; advanced capabilities are licensed separately. A free open-source MCP server and a 30-day platform trial are offered. Pricing is not published.

Frameworks (vendor-stated)

No framework tags yet.

Vendor-claimed SOC 2, ISO 27001

Pricing (as published)

Not published (pre-packaged agents included for OpenCTI/OpenAEV Enterprise Edition customers with a usage quota; advanced XTM One capabilities licensed separately; 30-day trial and free open-source MCP server)

Tasks

threat intelligencepen test managementexposure managementthreat detection

Sources

1. filigran.io/products/xtm-one (primary)
2. filigran.io/press-releases/filigran-launches-xtm-one/
3. filigran.io/fr/blog/xtm-platform-q3-2026-updates-opencti-openaev-xtm-one-and-xtm-hub
4. docs.openaev.io/latest/usage/attack-chaining/autonomous/overview/
5. docs.openaev.io/latest/usage/attack-chaining/autonomous/configuration/
6. filigran.io/api/media/file/filigran_on-prem-community-ed._terms-and-conditions_europe_aug-2025.pdf
7. annuaire-entreprises.data.gouv.fr/entreprise/901384479

Last verified 20 Oct 2026. Framework tags indicate relevance, not certification; “vendor-claimed” items are as marketed by the vendor. Spotted an error? Submit a correction or email [email protected]. See our methodology.

Use-case comparisons

• Agentic pentesting AI agents — 33 verified listings (Autonomous or AI-assisted penetration testing, attack-surface testing and exploitable-path verification)

Compare Filigran XTM One (CTEM AI agents and autonomous attack chaining for OpenCTI and OpenAEV) with

• 
  7AI agentic security platform vs Filigran XTM One (CTEM AI agents and autonomous attack chaining for OpenCTI and OpenAEV)
• 
  Abnormal AI Security Mailbox (Abnormal AI for Government) vs Filigran XTM One (CTEM AI agents and autonomous attack chaining for OpenCTI and OpenAEV)
• 
  Adaptive Security Agentic Email Security and Phish Triage vs Filigran XTM One (CTEM AI agents and autonomous attack chaining for OpenCTI and OpenAEV)
• 
  Aikido Attack AI Pentesting vs Filigran XTM One (CTEM AI agents and autonomous attack chaining for OpenCTI and OpenAEV)
• 
  AIpentix (agentic continuous security testing and agentic red teaming, by Swipergy) vs Filigran XTM One (CTEM AI agents and autonomous attack chaining for OpenCTI and OpenAEV)
• A
  Andesite Human-AI SOC (Azimuth for Government) vs Filigran XTM One (CTEM AI agents and autonomous attack chaining for OpenCTI and OpenAEV)
• 
  Anomali Agentic AI in ThreatStream Next-Gen and the Anomali Data Lake (autonomous triage, scoring and investigation agents) vs Filigran XTM One (CTEM AI agents and autonomous attack chaining for OpenCTI and OpenAEV)
• 
  AppOmni Marlin AI (autonomous SaaS and agentic-AI risk investigation) vs Filigran XTM One (CTEM AI agents and autonomous attack chaining for OpenCTI and OpenAEV)
• 
  Arctic Wolf Aurora Agentic SOC (Swarm of Experts agents) vs Filigran XTM One (CTEM AI agents and autonomous attack chaining for OpenCTI and OpenAEV)
• 
  Ares Cyber agentic AI security testing platform (autonomous exploit chaining and runtime verification across SAST, SCA, DAST, VA and pentest) vs Filigran XTM One (CTEM AI agents and autonomous attack chaining for OpenCTI and OpenAEV)

Alternatives

• 
  7AI agentic security platform — Boston-based agentic security platform where swarms of specialised AI agents categorise, investigate and reach a determination on every alert, escalating only what needs a person, with optional managed service (PLAID ELITE).
• 
  Abnormal AI Security Mailbox (Abnormal AI for Government) — Autonomous agent for email security operations that triages user-reported emails, removes related malicious campaign messages across the organisation and replies to reporters; included in Abnormal AI for Government, which is FedRAMP and GovRAMP Moderate authorized.
• 
  Adaptive Security Agentic Email Security and Phish Triage — API-based 'agentic email security' that re-analyses inbound mail after native filtering with ML and LLM reasoning and removes confirmed threats across every inbox automatically (configurable human-in-the-loop thresholds). AI Phish Triage classifies employee-reported emails and acts on them, feeding Adaptive's simulations and awareness training.
• 
  Aikido Attack AI Pentesting — Belgian autonomous AI pentest: many agents map the app, test attack paths and re-exploit each finding to confirm it, with a same-day audit-grade report.
• 
  AIpentix (agentic continuous security testing and agentic red teaming, by Swipergy) — German continuous security-testing platform with an AI agent that signs in to the customer's application on its own, chooses follow-up checks and documents attack paths, with every tool run evidenced. Findings are grouped into remediation actions with owners, deadlines and Jira sync, and retests confirm fixes. Agentic red-team campaigns (recon, access, lateral and report agents led by human red teamers) are also offered for TIBER-EU and DORA TLPT style testing.
• A
  Andesite Human-AI SOC (Azimuth for Government) — Agentic SOC platform with configurable agents for alert triage, enrichment, investigation and remediation under analyst oversight; its government offering is FedRAMP High authorized.

See all Filigran XTM One alternatives →

FAQ (from this dataset)

What does Filigran XTM One do?

Agentic AI layer for Filigran's open-source threat-intelligence (OpenCTI) and exposure-validation (OpenAEV) platforms: pre-built agents turn threat intelligence into hunting packages, detection rules and attack scenarios, and an autonomous attack-chaining orchestrator plans, runs and adapts an AI penetration test against an authorized environment, with optional human approval for sensitive actions.

How much does Filigran XTM One cost?

Not published (pre-packaged agents included for OpenCTI/OpenAEV Enterprise Edition customers with a usage quota; advanced XTM One capabilities licensed separately; 30-day trial and free open-source MCP server)

Where is Filigran (Filigran SAS) headquartered?

France

What are alternatives to Filigran XTM One?

See the Filigran XTM One alternatives page for category-sharing listings in relevance order, not a ranking. Filigran XTM One alternatives.

Stay updated