# Superagent > Make your software secure itself. Add security workers that defend your software around the clock. Build an autonomous security factory for applications, repositories, agents, and infrastructure. Superagent sends findings to the coding agents and workflows you already use. Those agents return structured reports through MCP, and Superagent uses the evidence and decisions in subsequent work. Built-in capabilities cover PR security, secure dependency updates, red teaming, context guardrails, and runtime guardrails. Backed by Y Combinator. This file is a curated map of https://www.superagent.sh for LLMs and agents. The documentation under /docs is the canonical reference for product behavior. The blog under /blog covers AI security research, benchmarks, and product announcements. The authenticated dashboard and the /api and /app paths are intentionally not listed; everything below is public. Machine-readable interfaces: - REST API: https://superagent.sh/api/v1, authenticated with an organization API key. OpenAPI 3.1 spec: https://www.superagent.sh/openapi/v1.yaml - MCP server: https://www.superagent.sh/mcp, connecting customer agents to Superagent security workers and the structured agent report return path. - Security-One API: https://api.superagent.sh/v1/systemone, calibrated Security-One classification authenticated with an organization sk_live_ API key (internal/testing keys also supported). Public model document: https://api.superagent.sh/models ## Get started - [Docs overview](https://www.superagent.sh/docs): How Superagent connects software, security workers, findings, and development workflows. - [Start here](https://www.superagent.sh/docs/get-started): Connect your software, choose one security worker, and complete your first security job. - [Pricing](https://www.superagent.sh/pricing): Flexible pricing with free private usage and unlimited open-source repository usage; Secure Dependency Updates cost 5 credits per live private run, while public and dry-runs are free. Security-One costs 0.05 credits per 1 million input tokens with free output tokens. ## Product updates - [Changelog](https://www.superagent.sh/changelog): Product updates from the Superagent team. - [Choose where and how often repository scans run](https://www.superagent.sh/changelog#2026-10-repository-scan-controls): Target base branches and cap runs separately for PR security and supply chain scans. - [A decision model for security](https://www.superagent.sh/changelog#2026-10-security-one): Security-One 27B is a decision model for always-on security triage across applications, agents, code, and infrastructure. ## Your software - [Your software](https://www.superagent.sh/docs/software): Software types Superagent protects and planned infrastructure support. - [Repositories](https://www.superagent.sh/docs/concepts/repositories): Protect repositories with PR Security, dependency updates, contributor controls, Red Team, and reviewed remediation. - [Applications](https://www.superagent.sh/docs/concepts/applications): Protect deployed applications with adversarial testing, context controls, finding handoffs, and retained results. - [Agents](https://www.superagent.sh/docs/concepts/agents): Protect AI agents, use coding agents as destinations, and connect security agents through one factory. - [Infrastructure](https://www.superagent.sh/docs/concepts/infrastructure): Follow first-source and webhook onboarding, connect logs for security-one monitoring, and automatically route escalations to enabled infrastructure webhook subscriptions. ## Security capabilities - [PR Security](https://www.superagent.sh/docs/pr-scans): Inspect code, contributor, workflow, and supply chain risk before merge. Findings land on the changed line and in GitHub checks. - [Secure Dependency Updates](https://www.superagent.sh/docs/secure-dependency-updates): Superagent dependency PRs with supply-chain attack investigation first, other vulnerabilities and repository impact second, and evidence from isolated old/new package checks. - [Red Team](https://www.superagent.sh/docs/red-team): Run adversarial tests against applications, repositories, agents, packages, and infrastructure with evidence and reproduction steps. - [Context Guardrails](https://www.superagent.sh/docs/context-guardrails): Score the files, pages, packages, skills, repositories, and messages agents consume before they trust them. - [Runtime Guardrails](https://www.superagent.sh/docs/runtime-guardrails): Monitor or block risky actions where the agent runs with deterministic endpoint-local rules. - [Security Factory](https://www.superagent.sh/docs/security-factory): Turn findings into verified decisions and reviewed remediation pull requests through authenticated webhooks, coding agents, and Superagent MCP. ## Security workers - [Security workers overview](https://www.superagent.sh/docs/security-workers): A security worker is a built-in unit of security execution that runs a defined job against protected software. - [PR Security](https://www.superagent.sh/docs/security-workers/pr-security): Run four pull request checks for code, dependency, contributor, and agreement risk. - [Security scanning](https://www.superagent.sh/docs/security-workers/pr-security/security-scanning): Review the pull request diff for malicious code, workflow changes, and risky lifecycle hooks; configure target branches and per-PR run limits. - [Supply chain scanning](https://www.superagent.sh/docs/security-workers/pr-security/supply-chain-scanning): Score added or upgraded dependencies in pull requests, with configurable target branches and per-PR run limits. - [Contributor Trust](https://www.superagent.sh/docs/security-workers/contributor-trust): Use identity and contribution evidence in pull request merge decisions. - [Contributor Agreements](https://www.superagent.sh/docs/security-workers/contributor-agreements): Create, version, assign, and enforce contributor agreements on pull requests; owners can exempt GitHub accounts per repository and queue CLA rechecks. - [Secure Dependency Updates](https://www.superagent.sh/docs/security-workers/secure-dependency-updates): Generate Superagent-branded dependency PRs with isolated artifact and usage assessments, retaining updates, advisories, and release notes, with verified pnpm transitive fixes, exact-version security-fix release-age exceptions and unions, and authenticated uncached commit verification; published PRs trigger home-page notifications and webhooks; live private runs cost 5 credits, while public and dry-runs are free. - [Red Team](https://www.superagent.sh/docs/security-workers/red-team): Run adversarial security work across applications, repositories, agents, infrastructure, and package artifacts. - [Applications](https://www.superagent.sh/docs/security-workers/red-team/applications): Probe a live application with browser-driven DAST and review evidence as findings land. - [Repositories](https://www.superagent.sh/docs/security-workers/red-team/repositories): Point a security agent at your codebase for gray-box exploit-path discovery with repro steps. - [Agents](https://www.superagent.sh/docs/security-workers/red-team/agents): Run black-box adversarial tests against a deployed AI agent without source-code access. - [Infrastructure](https://www.superagent.sh/docs/security-workers/red-team/infrastructure): Cover infrastructure through the application, repository, agent, and package surfaces in scope. - [Packages](https://www.superagent.sh/docs/security-workers/red-team/packages): Adversarially test installable software in an isolated sandbox from your installation instructions. - [Agent Guardrails](https://www.superagent.sh/docs/security-workers/agent-guardrails): Check what agents consume and monitor or block risky actions where agents run. - [Context Guardrails overview](https://www.superagent.sh/docs/security-workers/agent-guardrails/context): Score external content before agents consume it and route the decision into the security factory. - [Web pages and files](https://www.superagent.sh/docs/security-workers/agent-guardrails/web-and-files): Score Web pages with identity and static checks, offline browser capture, and always-on Security-One triage; scan public text files and PDFs with Security-One and deeper review for static findings or incomplete triage. - [Email and messages](https://www.superagent.sh/docs/security-workers/agent-guardrails/email-and-messages): Score email, SMS, WhatsApp, and social messages with Security-One attempted on every completed scan, plus full web-page triage for followed public HTTPS links and deeper fallback review when needed. - [Extensions and packages](https://www.superagent.sh/docs/security-workers/agent-guardrails/extensions-and-packages): Check agent skills, MCP repositories, and registry packages before installation with always-on Security-One triage and deeper fallback review when needed. - [Runtime Guardrails overview](https://www.superagent.sh/docs/security-workers/agent-guardrails/runtime): Monitor or block risky coding-agent actions with endpoint-local rules. - [Write and enforce rules](https://www.superagent.sh/docs/security-workers/agent-guardrails/rules): Create, validate, assign, monitor, and enforce Runtime Guardrails rules. ## Your integrations - [Your integrations](https://www.superagent.sh/docs/connect): Connect source control, coding agents, and development workflows to Superagent. - [Connect GitHub](https://www.superagent.sh/docs/connect/github): Install the Superagent GitHub Apps, select repositories, and run the first repository security job. - [Set up Cursor](https://www.superagent.sh/docs/connect/cursor): Connect Cursor to Superagent MCP and complete a finding-to-report workflow. - [Set up Codex](https://www.superagent.sh/docs/connect/codex): Connect Codex to Superagent MCP and complete a finding-to-report workflow. - [Set up Claude Code](https://www.superagent.sh/docs/connect/claude-code): Connect Claude Code to Superagent MCP and complete a finding-to-report workflow. - [Connect another agent](https://www.superagent.sh/docs/connect/other-agents): Use the vendor-neutral webhook and MCP contract with another coding or security agent. ## Models - [Models overview](https://www.superagent.sh/docs/models): Security-One is a calibrated security decision model for always-on triage across applications, agents, code, and infrastructure. - [Security-One 27B](https://www.superagent.sh/docs/models/security-one): Featured on the homepage as “security-one 27b”; model details, prompt-injection and decision evaluations, intended use, limitations, and Apache 2.0 license. - [Examples](https://www.superagent.sh/docs/models/examples): End-to-end Security-One pipelines that decide clear cases immediately and escalate uncertain or risky ones to a stronger OpenAI model. - [Detect prompt injection](https://www.superagent.sh/docs/models/examples/prompt-injection): Screen untrusted input with Security-One, decide clear cases by threshold, and escalate uncertain inputs to a stronger OpenAI model. - [Check pull requests](https://www.superagent.sh/docs/models/examples/pr-check): Triage pull request diffs with Security-One in GitHub Actions and escalate risky or uncertain files to a stronger OpenAI model for review. - [Security-One API](https://www.superagent.sh/docs/models/api): Authenticate hosted Security-One with `SUPERAGENT_API_KEY`; review schemas, limits, errors, and pricing. - [Self-hosting](https://www.superagent.sh/docs/models/self-hosting): Run the open Security-One weights on your own GPUs with SGLang and reproduce the calibrated readout. ## Interfaces - [Interfaces](https://www.superagent.sh/docs/build): Choose MCP, Webhooks, REST, or Security-One; MCP, REST, and Security-One accept organization sk_live_ API keys. - [MCP](https://www.superagent.sh/docs/mcp): Connect an agent to Superagent, trigger and poll dependency update runs, use security tools, and return structured agent reports. - [Webhooks](https://www.superagent.sh/docs/webhooks): Send signed security events, including one publication event per verified dependency update pull request, to your systems and workflows. - [Telemetry](https://www.superagent.sh/docs/telemetry): Export security events as OpenTelemetry logs to Datadog, Grafana Cloud, and other collectors with encrypted authentication headers. - [Infrastructure log sources](https://www.superagent.sh/docs/infrastructure-log-sources): Connect OTLP/HTTP or Vercel logs for durable security-one screening, scoped correlation, incident review in a single-view detail panel, automatic webhook subscription routing, incident API and MCP tools, and unlimited daily analysis by default with optional admin controls. - [REST API](https://www.superagent.sh/docs/api): Authenticate with the Superagent REST API and manage reports, findings, contributor trust, dependency updates, context scores, telemetry, and monitored agents. - [Reports](https://www.superagent.sh/docs/api/reports): Start repository, application, Agent, and Package Red Team runs, then retrieve their red-team reports through the REST API. - [Incidents](https://www.superagent.sh/docs/api/incidents): List threshold-qualified infrastructure incidents, retrieve assessments and evidence, and update review status through REST or MCP with version checks and an API-key audit trail. - [Findings](https://www.superagent.sh/docs/api/findings): List, retrieve, update, delete, and triage findings through the REST API, including evidence and proposed remediation. - [Contributor Trust](https://www.superagent.sh/docs/api/contributor-trust): Retrieve cached contributor trust and start asynchronous scans through the REST API. - [Context Guardrails](https://www.superagent.sh/docs/api/context-guardrails): Score web pages, email, messages, files, agent skills, public GitHub MCP repositories, and registry packages through the REST API. - [Agents](https://www.superagent.sh/docs/api/agents): Create persistent Agent assets, configure red teaming, and manage runtime pairing, groups, rules, and alerts through REST. - [Applications](https://www.superagent.sh/docs/api/applications): Create persistent Application assets and configure browser red teaming through REST. - [Dependency Updates](https://www.superagent.sh/docs/api/dependency-updates): Start and poll scoped Renovate runs, subscribe to PR publication events, and understand the 5-credit private-run charge, free public and dry-runs, and free-plan capacity errors. - [Telemetry](https://www.superagent.sh/docs/api/telemetry): Create, retrieve, update, delete, and test OpenTelemetry log destinations through the REST API. - [OpenAPI specification](https://www.superagent.sh/openapi/v1.yaml): OpenAPI 3.1 reference for the Superagent REST API. ## Use cases - [Use cases overview](https://www.superagent.sh/docs/use-cases): Follow complete security workflows across Superagent and your integrations. - [Build an always-on pentester with Cursor](https://www.superagent.sh/docs/use-cases/continuous-adversarial-testing-with-cursor): Schedule repository Red Team runs and route newly created findings from one repository to Cursor via finding.created for reviewed remediation. - [Build always-on security triage for your Supabase app](https://www.superagent.sh/docs/use-cases/always-on-supabase-security-triage): Review Supabase production logs with the hosted Security-One decision model, retain evidence, and route suspicious activity for human review. - [Protect Pi agents from PII and PHI leaks](https://www.superagent.sh/docs/use-cases/protect-pi-agents-from-pii-phi-leaks): Enforce a deterministic sensitive-data rule where Pi runs and send blocked actions to your monitoring workflow. - [Quarantine hostile email before agents read it](https://www.superagent.sh/docs/use-cases/quarantine-hostile-email-before-agent-delivery): Put Context Guardrails between Resend and your agent so phishing, prompt injection, and malicious attachments never enter agent context. - [Red-team your agent against OWASP and MITRE ATLAS](https://www.superagent.sh/docs/use-cases/red-team-agents-against-owasp-mitre): Configure recurring Agent Red Team runs with mandatory OWASP LLM Top 10, OWASP Agentic Top 10, and MITRE ATLAS coverage. - [Validate dependency updates end to end with Devin](https://www.superagent.sh/docs/use-cases/validate-dependency-updates-with-devin): Validate agent-assessed Superagent vulnerability pull requests with Devin and review security checks before merging. ## Reference - [Dashboard](https://www.superagent.sh/docs/reference/dashboard): The Superagent home page: onboarding checklist, org activity, and shortcuts into each product. - [Settings](https://www.superagent.sh/docs/reference/settings): Organization profile, members, and API keys in the Superagent dashboard. - [Findings and reports](https://www.superagent.sh/docs/concepts/findings-and-reports): Distinguish findings, red-team reports, structured agent reports, retained context, and their lifecycles. - [Glossary](https://www.superagent.sh/docs/reference/glossary): Definitions of terms used in the Superagent dashboard and documentation. - [Troubleshooting](https://www.superagent.sh/docs/reference/troubleshooting): Common issues with GitHub Apps, pull request scans, reports, findings, and CLA checks. ## Blog - [Introducing Security-One 27B](https://www.superagent.sh/blog/introducing-security-one): A 27B decision model for always-on security triage across applications, agents, code, and infrastructure, available through our API or open weights. - [The OpenAI / Hugging Face incident and the case for autonomous security](https://www.superagent.sh/blog/openai-hugging-face-security-factory): OpenAI evaluation agents reached Hugging Face through familiar failures, showing why security must connect detection, investigation, and repair. - [Building a Security Factory with Superagent and Cursor](https://www.superagent.sh/blog/building-a-security-factory): Superagent acts as the attacker and Cursor as the executor, turning verified findings into reviewed pull requests in minutes. - [When a Trusted Contributor Gets Compromised](https://www.superagent.sh/blog/when-a-trusted-contributor-gets-compromised): We analyzed 8,897 evidence-backed GitHub posture findings to measure how repository controls limit a compromised contributor. - [When Terminal Output Owns Your Clipboard: OSC 52 in Warp](https://www.superagent.sh/blog/when-terminal-output-owns-your-clipboard-osc-52-in-warp): Affected Warp builds honored OSC 52 clipboard escape sequences from terminal output, allowing silent clipboard reads and writes with no default-deny gate. - [A bad patch is worse than no patch.](https://www.superagent.sh/blog/a-bad-patch-is-worse-than-no-patch): AI makes vulnerability discovery cheap, but closing vulnerabilities still requires validation, safe fixes, and human-reviewed merges. - [Backburning Open Source: Partnering with dotenvx to Find Vulnerabilities Before Attackers Do](https://www.superagent.sh/blog/backburning-open-source-partnering-with-dotenvx): How the dotenvx partnership finds vulnerabilities before attackers do and closes the silent window with hardened packages. - [Frontier models miss 57% of threats in agent context](https://www.superagent.sh/blog/frontier-models-miss-57-percent-of-threats): 485 real artifacts through Claude 4.6 Opus with a security-focused system prompt missed 57% of the threats brin had already identified. - [The Cline Incidents and the Broken Security Model](https://www.superagent.sh/blog/cline-incident-broken-security-model): Two Cline security incidents expose the same problem: AI agents treat untrusted content as instructions. - [Launching brin.sh — realtime threat detection for agents](https://www.superagent.sh/blog/launching-brin-sh): Brin scores everything your agent is about to consume before it does. Free to use, no auth, no SDK, no signup. - [What Can Go Wrong with AI Agents](https://www.superagent.sh/blog/what-can-go-wrong-with-ai-agents): Data leaks, compliance violations, unauthorized actions — how AI agents fail in ways traditional software doesn't. - [We Bypassed Grok Imagine's NSFW Filters With Artistic Framing](https://www.superagent.sh/blog/grok-image-jailbreak): Text-to-image safety is broken; explicit content of a real person via basic compositional tricks. - [AI Code Sandbox Benchmark 2026: Modal vs E2B vs Daytona vs Cloudflare vs Vercel vs Beam vs Blaxel](https://www.superagent.sh/blog/ai-code-sandbox-benchmark-2026): Modal vs E2B vs Daytona vs Cloudflare vs Vercel vs Beam vs Blaxel, evaluated on developer experience and pricing. - [The Threat Model for Coding Agents is Backwards](https://www.superagent.sh/blog/threat-model-for-coding-agents-is-backwards): With coding agents, the user is the victim, not the attacker. - [AI Guardrails Are Useless](https://www.superagent.sh/blog/ai-guardrails-are-useless-in-their-current-form): Most guardrails are generic, static, and disconnected from what matters for your specific agent. - [Introducing Superagent Guard](https://www.superagent.sh/blog/superagent-guard-frontier-guardrails-for-ai-agents): Purpose-trained models that detect prompt injections, identify jailbreak attempts, and enforce guardrails at runtime. - [SOC-2 is table stakes now. Here's what actually matters for AI products.](https://www.superagent.sh/blog/soc-2-is-table-stakes): What actually matters for AI products beyond the certification badge. - [Red Teaming AI Agents: What We Learned From 50 Assessments](https://www.superagent.sh/blog/red-teaming-ai-agents-learnings): Critical patterns from red teaming 50 AI agents across companies, industries, and setups. - [Open Source AI Models: A Safety Score Reality Check](https://www.superagent.sh/blog/open-source-ai-model-a-safety-reality-check): Safety scores for open-weight models you can deploy without vendor lock-in. - [Your System Prompt Is the First Thing Attackers Probe](https://www.superagent.sh/blog/your-system-prompt-is-the-first-thing-attackers-probe): Attacks on AI agents start by probing the instructions that define behavior, tools, and boundaries. - [Your RAG Pipeline Is One Prompt Away From a Jailbreak](https://www.superagent.sh/blog/your-rag-pipeline-is-one-prompt-away-from-a-jailbreak): Malicious files, knowledge base poisoning, and indirect prompt injection turn RAG into an attack surface — and how to defend against it. - [Practical guide to building safe & secure AI agents](https://www.superagent.sh/blog/practical-guide-to-ai-agent-safety): System prompts aren't enough; runtime protection against prompt injection, poisoned tool results, and the lethal trifecta. - [AI Is Getting Better at Everything—Including Being Exploited](https://www.superagent.sh/blog/ai-is-getting-better-at-everything): The GPT-5.1 safety score drop shows capability and attack surface scale faster than safety. - [Are AI Models Getting Safer? A Data-Driven Look at GPT vs Claude Over Time](https://www.superagent.sh/blog/gpt-vs-claude-ai-safety-benchmark): 18 months of Lamb-Bench safety scores for GPT and Claude models. - [Introducing Lamb-Bench: How Safe Are the Models Powering Your Product?](https://www.superagent.sh/blog/introducing-lamb-bench): An adversarial testing framework that gives buyers and sellers a common AI safety measurement standard. - [VibeSec: The Current State of AI-Agent Security and Compliance](https://www.superagent.sh/blog/vibesec-the-current-state-of-ai-agent-security-and-compliance): Notes from dozens of conversations with developers building AI agents and LLM-powered products. - [The March of Nines](https://www.superagent.sh/blog/the-march-of-nines): The hidden reliability engineering between a working demo and a production AI system. - [The case for small language models](https://www.superagent.sh/blog/the-case-for-small-language-models): Single-job agents deserve purpose-built models that run locally and can be retrained as your data evolves. - [Why Your AI Agent Needs More Than Content Safety](https://www.superagent.sh/blog/why-your-ai-agent-needs-more-than-content-safety): Content filtering isn't enough when your AI takes actions. - [Shipped: Runtime Redaction and Command-Line Security](https://www.superagent.sh/blog/runtime-redaction-and-cli-ship-week): Runtime redaction, a powerful CLI, URL whitelisting, and security directly in the developer workflow. - [Three years later: AI can (now) defend AI](https://www.superagent.sh/blog/three-years-later-ai-can-now-defend-ai): What changed since Simon Willison's 2022 argument that "adding more AI" was the wrong fix for prompt injection. - [Introducing Superagent — Defend Your AI Agents in Runtime](https://www.superagent.sh/blog/introducing-superagent): The runtime defense platform against prompt injections, malicious tool calls, and data leaks. - [Alignment Faking: The New AI Security Threat](https://www.superagent.sh/blog/alignment-faking-the-new-ai-security-threat): Strategic deception by LLMs complicates traditional safety measures and necessitates technical countermeasures. - [Announcing Support for Cursor Agent and OpenCode](https://www.superagent.sh/blog/cursor-agent-opencode-support): VibeKit's universal agent support provides a consistent security and observability layer across preferred agents. - [Introducing VibeKit CLI](https://www.superagent.sh/blog/introducing-vibekit-cli): The safety layer for running AI coding agents with direct access to your environment. - [Introducing Dagger Local Sandboxes](https://www.superagent.sh/blog/dagger-local-sandboxes): VibeKit support for Dagger-powered local AI code execution with container isolation and zero cloud dependencies. - [Grok CLI Gets MCP Support](https://www.superagent.sh/blog/grok-cli-mcp-support): MCP support turns Grok CLI into a connected terminal agent that can use 1000+ development tools. - [Introducing Cloudflare Sandboxes Support](https://www.superagent.sh/blog/cloudflare-sandboxes-support): VibeKit support for Cloudflare Sandboxes — AI code execution at the edge across 300+ global locations. - [Introducing @vibe-kit/auth: Unlock Your AI "Max" Subscriptions](https://www.superagent.sh/blog/introducing-vibekit-auth): Use Claude, Gemini, or Grok Max subscriptions across any application through secure OAuth flows. - [Vibex: Rebuilding OpenAI Codex with VibeKit](https://www.superagent.sh/blog/vibex-rebuilding-openai-codex-with-vibekit): An open-source coding agent that runs tasks in secure E2B containers and produces working GitHub pull requests. - [On vibe coding](https://www.superagent.sh/blog/on-vibe-coding): A new way of building software that skips the traditional engineering process. - [Prompting is not a skill, prompting is engineering](https://www.superagent.sh/blog/prompting-is-not-a-skill-prompting-is-engineering): Prompts should be treated as engineered systems, not isolated tasks. - [The death of AI agents](https://www.superagent.sh/blog/the-death-of-ai-agents): Why today's complex, over-engineered agent systems are about to be replaced. - [ReAG: Reasoning-Augmented Generation ](https://www.superagent.sh/blog/reag-reasoning-augmented-generation): Query documents with full context instead of retrieve-then-read chunking. - [Agents that write their own tools](https://www.superagent.sh/blog/agents-that-write-their-own-tools): Really useful agents need specialized tools — and can write their own. - [The 1700s paradox](https://www.superagent.sh/blog/the-1700s-paradox): Klarna CEO Sebastian Siemiatkowski's analogy about AI capability, examined. - [The future of LLM costs](https://www.superagent.sh/blog/the-future-of-llm-costs): Competing visions of where Large Language Model pricing goes. - [$2K Per Task](https://www.superagent.sh/blog/openai-s-o3-at-2k-per-task): OpenAI's o3 model marks PhD-level performance at a pivotal price point. - [AI Agents vs RPA](https://www.superagent.sh/blog/ai-agents-vs-rpa): The widespread adoption of hardcoded workflows sold as AI agents. ## Customer stories - [Customer stories](https://www.superagent.sh/customer-stories): How teams use Superagent in production. - [How Capchase ships AI features without losing sleep](https://www.superagent.sh/customer-stories/capchase): Capchase runs every file, prompt, and web fetch through Superagent before it reaches an agent — enforced with a lint rule, not a README. - [How dotenvx hardens open source secrets management](https://www.superagent.sh/customer-stories/dotenvx): Superagent probes dotenvx continuously and turns findings into upstream patches the dotenvx team can review, merge, and ship. ## Company - [About Superagent](https://www.superagent.sh/about): Mission and team — an AI security team that finds, patches, and discloses vulnerabilities in code and agents. Backed by Y Combinator. - [Changelog](https://www.superagent.sh/changelog): Product updates, including OpenTelemetry security event export to Datadog and other collectors, live PR scan progress in GitHub checks, verified security findings, Security Factory, Secure Dependency Updates, and Context Guardrails. - [Blog index](https://www.superagent.sh/blog): All posts on AI security research, benchmarks, and product announcements. ## Optional - [Legal](https://www.superagent.sh/legal): Hub for all Superagent legal documents. - [Privacy Policy](https://www.superagent.sh/legal/privacy-policy): How Superagent collects, uses, discloses, and protects personal information. - [Cookie Notice](https://www.superagent.sh/legal/cookie-notice): Cookies and similar technologies used across the Superagent website and application. - [Website Terms of Use](https://www.superagent.sh/legal/terms-of-use): Terms governing the public Superagent website. - [Services Agreement](https://www.superagent.sh/legal/services-agreement): Terms for Superagent products, plans, APIs, integrations, MCP access, and webhooks. - [Global Data Processing Addendum](https://www.superagent.sh/legal/dpa-global): Global data protection terms for Customer Data processed by Superagent. - [Subprocessor List](https://www.superagent.sh/legal/subprocessors): Infrastructure, email, AI, security, billing, and authentication providers that may process service-related data.