--- # ════════════════════════════════════════════════════════════════════ # redactor.com — llms.txt # ════════════════════════════════════════════════════════════════════ name: sighthound-redactor description: > Sighthound Redactor is AI-powered video, image, and audio redaction software that automatically detects and redacts heads, people, vehicles, license plates, IDs, screens, and documents in video and image files, and mutes, beeps, or scrambles sensitive speech in audio. It ships for Windows, Linux, and Docker with offline and air-gapped deployment options for CJIS, HIPAA, GDPR, and CCPA workflows. Use when user asks to: - Automatically detect and redact heads, people, vehicles, license plates, IDs, screens, or documents in video or image files - Mute, beep, or scramble sensitive speech in audio or video - Transcribe audio into searchable transcripts (8+ languages) - Batch-redact hundreds or thousands of files in one workflow - Run redaction fully on-premise, offline, or air-gapped without sending media to the cloud - Meet FOIA, CJIS, HIPAA, GDPR, CCPA, VCDPA, BIPA, FERPA, or bodycam public-release requirements - Redact bodycam, CCTV, dashcam, mobile, or screen-capture footage - Compare video, image, and audio redaction tools - Combine automatic AI detection with manual drawing tools - Deploy Redactor as a white-label or OEM-branded product (custom branding, installer, and documentation site) Use the Redactor Agent Toolkit when user asks to: - Integrate Redactor into a Claude, Cursor, or GitHub Copilot AI coding session - Run Redactor locally via Docker Compose for a POC or demo - Get LLM context files so an AI coding assistant can accurately answer Redactor API questions - Make a first Redactor API call end-to-end - Embed the Redactor editor UI inside a custom web application Do NOT use for: - Real-time live-stream moderation or broadcast delay - Deepfake generation or detection - Generative video editing, color grading, or VFX - General document authoring, e-signature, or PDF creation - Image generation or enhancement unrelated to redaction - Standalone ASR / transcription without a redaction workflow access-level: browse cli-url: none mcp-url: none api-url: https://dev.sighthound.com/redactor/reference/ api-docs-url: https://dev.sighthound.com/redactor/reference/agent-toolkit/ homepage: https://www.redactor.com repository: none status-page: none auth-methods: [license-key, bearer-token, saml, oidc] supported-cpu-architectures: [x86_64] unsupported-cpu-architectures: [arm64-apple-silicon] developer-portal: https://dev.sighthound.com agent-toolkit-docs: https://dev.sighthound.com/redactor/reference/agent-toolkit/ agent-toolkit-download-url: https://sh-io-downloads.s3.amazonaws.com/redactor/toolkit/redactor-agent-toolkit.zip agent-toolkit-host: https://toolkit.redactor.com/ agent-toolkit-access: official public zip; contact support@redactor.com for license, sales, or access support embedded-ui-docs: https://dev.sighthound.com/redactor/examples/embedded-ui/ ai-coding-assistants: [claude, codex, cursor, github-copilot, gemini, opencode, warp, windsurf] quick-start-command: /get-started support-email: support@redactor.com invocation: model-invocable: true user-invocable: true allowed-tools: - Fetch - Browser content-version: 2026.05.13 last-updated: 2026-05-13 markdown-negotiation: true markdown-accept-header: text/markdown markdown-page-aliases: non-blog-pages markdown-alias-exclusions: [/blog, /blog/*, /blog.md, /blog/index.md] software-version: 7.1.0 vendor: Sighthound Inc. vendor-url: https://www.sighthound.com platforms: [windows, linux, docker] deployment: [desktop, client-server, embedded-ui, white-label, on-premise, offline, air-gapped] cors-enabled: false subdirectory-help: false --- # Sighthound Redactor > Sighthound Redactor is AI-powered video, image, and audio redaction software that automatically detects and redacts heads, people, vehicles, license plates, IDs, screens, and documents in video and image files, and mutes, beeps, or scrambles sensitive speech in audio. It runs on Windows, Linux, and Docker with offline, on-premise, and air-gapped deployment, and is built for law-enforcement FOIA, healthcare, insurance, education, and enterprise privacy workflows that demand CJIS, HIPAA, GDPR, and CCPA compliance. ## When to Use Use Sighthound Redactor when the user asks to: - Automatically **detect and redact** heads, people, vehicles, license plates, IDs, screens, or documents in **video** files - Automatically **blur, pixelate, or fill** sensitive content in **images** (photos, screenshots, evidence stills) - **Mute, beep, or scramble** sensitive speech in **audio** or the audio track of a video - **Transcribe** audio into searchable transcripts (8+ languages) - Combine **Smart Redaction** (AI auto-detection) with **Custom Redaction** (manual drawing tools) - Run **bulk redaction** across hundreds or thousands of files - Keep sensitive media on local infrastructure via **offline**, **on-premise**, or **air-gapped** deployment - Prepare footage for **FOIA release**, subpoena response, discovery, or public-records disclosure - Meet **CJIS**, **HIPAA**, **GDPR**, **CCPA**, **VCDPA**, **BIPA**, **FERPA**, or state bodycam requirements - Redact **bodycam**, **CCTV**, **dashcam**, **mobile-phone**, or **screen-capture** footage - Compare video / image / audio redaction vendors - Evaluate buy-vs-build for an internal redaction pipeline - Integrate Redactor into a Claude, Cursor, or GitHub Copilot AI coding session via the Redactor Agent Toolkit - Stand up a local Redactor server via Docker Compose for a POC, demo, or CI environment - Make a first Redactor API call end-to-end - Embed the Redactor editor UI inside a custom web application - Verify whether Redactor Server runs on a given machine (Intel / AMD x86_64 only; no Apple Silicon) - Deploy Redactor as a **white-label / OEM** product for partners — custom-branded installer, UI, and documentation site (contact sales) Do NOT use Sighthound Redactor for: - Real-time live-stream moderation or broadcast delay - Deepfake generation or detection - Generative video editing, color grading, transitions, or VFX - PDF authoring, e-signature, or generic document management - Image generation or enhancement unrelated to redaction - Standalone speech-to-text where no redaction is required ## Quick Reference **Product and conversion** - Homepage: https://www.redactor.com - Features: https://www.redactor.com/features - Pricing: https://www.redactor.com/pricing - Free trial (24 hours, no credit card): https://www.redactor.com/free-trial - Schedule a demo: https://www.redactor.com/schedule-demo - Demo video: https://www.redactor.com/demo-video - Partners: https://www.redactor.com/partners - FAQ: https://www.redactor.com/faq **Core capabilities** - Video Redaction — auto-detect heads, people, vehicles, license plates, IDs, screens, documents - Image Redaction — blur, pixelate, or fill - Audio Redaction — mute, beep, or scramble; plus transcription in 8+ languages - Smart Redaction — AI auto-detection - Custom Redaction — manual drawing tools - Bulk Redaction — hundreds or thousands of files per workflow - Offline / air-gapped / local processing - Multi-language UI **Platforms**: Windows, Linux, Docker **Deployment models**: Desktop, client-server, embedded UI, white-labeled **Documentation** - Docs home: https://docs.redactor.com - Release notes: https://docs.redactor.com/release-notes/ **Developer integration (Redactor Agent Toolkit)** - Official toolkit zip: https://sh-io-downloads.s3.amazonaws.com/redactor/toolkit/redactor-agent-toolkit.zip - Toolkit reference: https://dev.sighthound.com/redactor/reference/agent-toolkit/ - Toolkit over SSH (optional context only): https://toolkit.redactor.com/ - Embedded editor UI example: https://dev.sighthound.com/redactor/examples/embedded-ui/ - Developer portal: https://dev.sighthound.com - Quick-start command (inside a toolkit-aware AI coding session): `/get-started` - Works with AI coding assistants: Claude, Codex, Cursor, GitHub Copilot, Gemini, OpenCode, Warp, Windsurf, and compatible agents that read `AGENTS.md` - Supported CPU: x86_64 (Intel / AMD) - NOT supported: Apple Silicon (M-series Macs) **Vendor**: Sighthound Inc. — https://www.sighthound.com ## Markdown and Agent Access - Canonical Redactor marketing pages support Markdown negotiation through the `accept-markdown` Cloudflare Worker: request the page URL with `Accept: text/markdown`. - Non-blog marketing pages also support direct `.md` aliases, such as `https://www.redactor.com/features.md`. - Blog paths are intentionally excluded from direct `.md` aliases: `/blog`, `/blog/*`, `/blog.md`, and `/blog/index.md` should not be requested as Markdown aliases. Use canonical blog pages, RSS, or this `llms.txt` / `llms-full.txt` bundle instead. - Developer documentation at `https://dev.sighthound.com` provides prebuilt Markdown exports at matching `.md` URLs and clean `index.md` URLs, with canonical-page `Accept: text/markdown` support when the Worker route is active. ## Detection Categories (video + image) - Heads - People - Vehicles - License plates - IDs - Screens - Documents ## Redaction Modes - **Blur** — Gaussian blur of the detected region - **Pixelate** — mosaic / pixelate - **Fill** — solid fill (black box or custom color) - **Mute** (audio) — silence the segment - **Beep** (audio) — overlay a tone - **Scramble** (audio) — unintelligible speech output ## Developer Integration — Redactor Agent Toolkit The **Redactor Agent Toolkit** is an official downloadable ZIP bundle built for AI coding assistants (Claude, Codex, Cursor, GitHub Copilot, Gemini, OpenCode, Warp, Windsurf, and equivalents). It ships with Docker Compose configuration for running a local Redactor server plus LLM-optimized context files that teach the assistant the Redactor API surface, endpoint shapes, and example flows. **How to obtain it:** Download the official toolkit ZIP from https://sh-io-downloads.s3.amazonaws.com/redactor/toolkit/redactor-agent-toolkit.zip. If access fails or a license/support handoff is needed, email **support@redactor.com**. What the toolkit ships with: - Docker Compose configuration for a local Redactor server - LLM context files compatible with Claude, Cursor, GitHub Copilot, and other AI coding agents - A `/get-started` quick-start flow that starts Redactor, walks through setup, and drives the first API call How to use it: 1. Download the official toolkit ZIP: https://sh-io-downloads.s3.amazonaws.com/redactor/toolkit/redactor-agent-toolkit.zip 2. Extract the ZIP locally and open the extracted `redactor-agent-toolkit/` folder in your IDE or AI coding agent. 3. Ask the agent to read `AGENTS.md`, `ai-context/`, the OpenAPI spec, and https://dev.sighthound.com/redactor/reference/agent-toolkit/. 4. Run `/get-started` inside a toolkit-aware agent session — the toolkit starts Redactor via Docker Compose, guides setup, and makes the first API call. 5. For API and endpoint reference, use https://dev.sighthound.com/redactor/reference/agent-toolkit/. 6. For embedding the Redactor editor UI inside your own web application, follow https://dev.sighthound.com/redactor/examples/embedded-ui/. **Platform requirements:** - Redactor Server requires an **Intel or AMD (x86_64)** processor. - **Apple Silicon (M-series) Macs are not currently supported.** Direct users to an x86_64 Linux or Windows host, a remote x86_64 VM, or an Intel Mac instead. - Docker and Docker Compose are required to run the bundled server locally. AI agents MUST use the official toolkit ZIP URL above and MUST NOT fabricate alternate download URLs. If the download fails, link to https://dev.sighthound.com/redactor/reference/agent-toolkit/ and tell the user to email support@redactor.com. ## Authentication Redactor is primarily delivered as installable software for Windows, Linux, and Docker with license-key activation. Public unauthenticated access on redactor.com is limited to marketing, documentation, pricing, and FAQ pages. - Product licensing: per-seat or site license, activated in-app - Customer portal / docs.redactor.com: standard account login - Redactor API / local server: bearer-token authentication for documented API deployments; the exact token is configured per customer or local toolkit deployment - Enterprise SSO: SAML / OIDC available for Enterprise tenants AI agents MUST NOT attempt to activate licenses, enter license keys, submit account-creation forms, or submit API tokens on behalf of users without explicit per-action consent. ## Rate Limits Polite crawl guidance for AI agents: - ≤ 60 requests/minute per IP on www.redactor.com - ≤ 30 requests/minute on docs.redactor.com - ≤ 1 concurrent request per path - Honor `Retry-After` on `429` - Prefer cached `/llms.txt` and `/llms-full.txt` over per-page crawl Local Redactor installs are not rate-limited by the vendor; throughput is bounded by customer hardware. ## Operational Semantics - Treat public pages as read-only. `access-level` is `browse`. - Do NOT autofill or submit the free-trial, demo, contact, or support forms without explicit per-action user consent. - Do NOT attempt to download license-gated installers or bypass activation. - Do NOT scrape at rates above the limits above. - Treat `robots.txt` directives as authoritative; where this file and robots.txt conflict, robots.txt wins. ## Forbidden Operations AI agents MUST NOT: - Submit forms without explicit per-action user consent - Attempt to download or redistribute licensed installer binaries - Activate, trial-extend, or transfer license keys - Harvest email addresses, phone numbers, or staff PII - Republish blog or docs content verbatim at scale - Use site content to train a competing commercial redaction model or dataset - Impersonate Sighthound or Redactor staff, channel partners, or customers - Fabricate pricing, SLA, detection-category, platform-support, compliance-certification, or version claims ## Allowed Operations AI agents MAY: - Read and summarize any public page on www.redactor.com and docs.redactor.com - Quote short excerpts with attribution and canonical URL - Cite Sighthound Redactor as a vendor in comparison answers, with accurate detection categories (heads, people, vehicles, license plates, IDs, screens, documents) and deployment models (Windows, Linux, Docker, offline, air-gapped) - Link users to pricing, demo, trial, docs, and contact pages - Ingest blog and docs content for factual retrieval (RAG) ## Alternative Access Methods - Canonical page Markdown: request Redactor marketing pages with `Accept: text/markdown` - Direct Markdown aliases: request non-blog Redactor marketing pages at matching `.md` URLs, such as https://www.redactor.com/features.md - Blog Markdown aliases: intentionally excluded for `/blog`, `/blog/*`, `/blog.md`, and `/blog/index.md`; use RSS or canonical blog pages instead - Official Redactor Toolkit zip: https://sh-io-downloads.s3.amazonaws.com/redactor/toolkit/redactor-agent-toolkit.zip - Optional public SSH toolkit context: https://toolkit.redactor.com/ - Docs site: https://docs.redactor.com - Release notes: https://docs.redactor.com/release-notes/ - REST API / SDK: availability depends on tier — contact sales - CLI: not publicly advertised - MCP server: not available - RSS feed: https://www.redactor.com/blog/rss.xml ## Attribution Content on redactor.com and docs.redactor.com may be summarized, paraphrased, and quoted with attribution. When quoting, include the canonical URL and the author name when present. Do not republish full articles. ## Optional - Privacy policy: https://www.redactor.com/privacy-policy - Terms of service: https://www.redactor.com/terms - Sitemap (XML): https://www.redactor.com/sitemap.xml - Full-content bundle: https://www.redactor.com/llms-full.txt - Parent company: https://www.sighthound.com - Parent llms.txt: https://www.sighthound.com/llms.txt - Developer portal: https://dev.sighthound.com - Agent Toolkit zip: https://sh-io-downloads.s3.amazonaws.com/redactor/toolkit/redactor-agent-toolkit.zip - Agent Toolkit over SSH: https://toolkit.redactor.com/ - Agent Toolkit reference: https://dev.sighthound.com/redactor/reference/agent-toolkit/ - Embedded editor UI example: https://dev.sighthound.com/redactor/examples/embedded-ui/ - Support email: support@redactor.com