AI agents for DevOps and security
Agents that watch production and attack surfaces: they investigate alerts and incidents, find root causes and test defences.
By weekly package downloads, the leaders are Strix (12.4K), HolmesGPT (4,854), CAI (Cybersecurity AI) (851). By GitHub stars, the leaders are Strix (76.8K), PentAGI (34.7K), Codex Security (14.2K). Among agents with at least 20,000 downloads in the last 30 days, the fastest grower is HolmesGPT, with downloads up 54%. As of Nov 21, 2026.
-
46
502/4 — — 14K 10d ago 14K GitHub starsGid 50 · 2/4 signals Free (OSS)
-
87
41 12.4K up 21.1% 76.8K 11d ago 12.4K downloads a week up 21.1% 30dGid 41 Free + $29/moStrix · Security · open-source autonomous penetration testing agents
An open-source multi-agent penetration testing tool that runs dynamic tests against applications, validates findings with working proofs of concept and proposes fixes; it runs locally with Docker or as a hosted service, and can run in CI/CD through GitHub Actions.
-
97
392/4 — — 14.2K 3d ago 14.2K GitHub starsGid 39 · 2/4 signals —OpenAI · Security · security scanning agent CLI and SDK
Codex Security is OpenAI's application security agent; this CLI and TypeScript SDK (@openai/codex-security) scan repositories or Git changes, validate findings, generate patches and export results such as SARIF. Running scans requires Codex Security access on an OpenAI account. A separate Codex Security Cloud plugin (research preview) scans connected GitHub repositories in Codex cloud.
-
166
29 — — 34.7K 47d ago 34.7K GitHub starsGid 29 Free (OSS)
-
177
28 79 up 128.6% 13.7K today 79 downloads a week up 128.6% 30dGid 28 Free (OSS)Tracer · DevOps & SRE · AI SRE agent framework
OpenSRE is an open-source framework and CLI for building AI SRE agents that connect to existing infrastructure tools to investigate incidents, diagnose failed builds and open fixes as pull requests. It can run self-hosted with the user's own model provider; per the README, the first launch of the CLI activates the hosted model and the interactive shell requires an OpenSRE account. A managed OpenSRE Cloud gateway, provisioned by an organization admin in the web app, is also available.
-
186
27 4,854 up 54.2% 3,949 17d ago 4,854 downloads a week up 54.2% 30dGid 27 Free (OSS)Robusta · DevOps & SRE · open-source SRE agent for incident root cause analysis
An open-source agent that investigates production incidents and alerts across Kubernetes, Prometheus, Datadog and other sources to find root causes; a CNCF Sandbox project that runs as a CLI or in-cluster operator.
-
231
20 851 up 27.4% 9,870 — 851 downloads a week up 27.4% 30dGid 20 FreeAlias Robotics · Security · framework for offensive and defensive security agents
A Python framework from Alias Robotics for building and running AI security agents for reconnaissance, exploitation, privilege escalation and defensive tasks, with guardrails and human-in-the-loop controls.
-
236
17 — — 8,344 31d ago 8,344 GitHub starsGid 17 Free (OSS)K8sGPT · DevOps & SRE · open-source Kubernetes diagnosis agent
Scans Kubernetes clusters with built-in analysers, diagnoses problems and explains them in plain English using a choice of model backends; runs as a CLI, server, MCP server or in-cluster operator.
-
—
— — — — — No public usage numbers Usage-basedDatadog · DevOps & SRE · AI SRE agent (autonomous alert investigation)
Datadog agent, now named Bits Investigation in Datadog's docs, that starts investigations when monitors alert or when asked in Slack, forms hypotheses and queries Datadog metrics, traces, logs, events, change tracking, RUM and GitHub source code to find root causes, and learns from past investigations. Third-party sources such as Grafana, Splunk, Sentry and ServiceNow are in preview. It is not available on Datadog's US government sites.
-
—
— — — — — Website rank #2.4M (Tranco top-sites list) Free + $700/moCleric · DevOps & SRE · AI SRE agent (change verification, alert investigation)
AI SRE agent that checks deployed changes in production and flags regressions, triages alerts and dismisses false positives, finds root causes with evidence, opens fix pull requests for human review and confirms the fix after deploy. It maps services and dependencies, reads from tools such as Datadog, Prometheus, kubectl and source code, and runs on alert triggers or on demand. Access is read-only by default and actions are logged.
-
—
— — — — — Website rank #1M (Tranco top-sites list) CustomDropzone AI · Security · SOC alert triage and investigation agent
AI SOC analyst that investigates security alerts end to end, querying connected SIEM, EDR, cloud, identity, email and threat-intelligence tools through their APIs without moving data, and returns a verdict with supporting evidence and a report. The platform also includes an AI Threat Hunter and a chatbot for ad-hoc investigation; an AI Threat Intel Analyst is in beta. Single-tenant enterprise, multi-tenant MSSP and EU deployments are offered.
-
—
— — — — — No public usage numbers $25/moincident.io · DevOps & SRE · AI SRE agent (incident investigation)
AI SRE from incident.io, called Investigations, that starts when an incident is declared: it gathers context from telemetry, code repositories, deploys, feature flags and config changes, runbooks in Confluence, Notion or GitHub, Slack channels and past incidents, tests hypotheses, and posts a root cause with evidence, confidence score and next steps to the incident channel. It runs on incident.io's Nexus model and can act only by proposing pull requests for human review.
-
—
— — — — — No public usage numbers Usage-basedMicrosoft · Security · security operations agents (phishing and alert triage, identity, vulnerability remediation)
Microsoft- and partner-built agents that run in Security Copilot and inside Defender, Entra, Intune, Purview and Sentinel to automate security and IT tasks, such as the Security Alert Triage Agent (preview, extending the Phishing Triage Agent), threat intelligence briefings, threat hunting with KQL, dynamic threat detection and Conditional Access optimisation. Agents run on triggers or on demand, use Security Compute Units and come from the Security Store or custom builds.
-
—
— — — — — Website rank #150K (Tranco top-sites list) $15/moHorizon3.ai · Security · autonomous penetration testing agent
Horizon3.ai's autonomous pentesting platform that runs real attack techniques in production without installed agents, covering internal and external networks, AWS and Azure cloud, Kubernetes, Active Directory and Entra ID, web applications and phishing impact. Tests are managed in the cloud NodeZero Portal and run from a host inside the customer network; results rank fix actions and can be retested with 1-Click Verify. It offers an API, CLI and MCP server.
-
—
— — — — — Website rank #505K (Tranco top-sites list) Usage-basedResolve AI · DevOps & SRE · AI SRE agent (on-call, incident investigation)
AI SRE platform whose agents act as primary on-call: they triage alerts as they fire, investigate incidents across observability tools, code and infrastructure to propose root causes and fixes, and help coordinate incident response. Custom agents handle work such as monitoring deploys, tuning alerts and health checks, and agents can update Jira tickets, open pull requests and pass production context to coding agents. Aimed at large engineering and SRE organizations.
-
—
— — — — — Website rank #507K (Tranco top-sites list) CustomTraversal · DevOps & SRE · AI SRE agent (incident root cause analysis)
Enterprise AI SRE platform that investigates production incidents by testing many root-cause hypotheses in parallel over a continuously updated causal model of the production system, built on existing observability data. Its workers triage alerts, join incident channels, investigate on their own and draft post-mortems. It is used through a web app, Slack and MCP clients such as Claude and Cursor, and deploys read-only by default, with bring-your-own-cloud and model options.
-
—
— — — — — Website rank #183K (Tranco top-sites list) Usage-basedXBOW · Security · autonomous penetration testing agent
Autonomous offensive security platform that tests web applications and APIs within a set scope, explores them as an attacker would, chains vulnerabilities into multi-step attack paths and validates each finding with a reproducible working exploit. Reports include the attack path, a decision log and remediation guidance. It runs continuously as applications change, is used through the XBOW Console and a REST API, and integrates with Jira, Sentinel and Security Copilot.
No agents match these filters.
“#” is the position among products of the same kind (agents, frameworks, tooling) by Gid Score, our 0–100 composite of adoption, community, attention and momentum. Use the filters and sorting above, or switch to the table view. Methodology · All AI agents.
Two jobs
- DevOps and SRE agents investigate alerts and incidents across logs, metrics, traces and recent changes, and propose a root cause and fix.
- Security agents run autonomous penetration tests or triage security alerts like a SOC analyst.
Both work on production systems, so start read-only, keep humans approving any change, and log everything the agent does.