Results for “self-hosted”

Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to self-hosted inference on GKE, or asks follow-up questions during such a migration (hardware sizing, model staging, manifest generation, validation, traffic cutover). DO NOT use for brand new GKE inference deployments with no existing workload to migrate (use gke-inference instead). DO NOT use if the user intends to automate the migration via the Gemini Cloud Assist MCP server.

The English summary is being prepared. Showing the original description.

Expert en n8n avancé (workflows, nodes, expressions, webhooks, self-hosted, custom nodes, scaling, error handling)

The English summary is being prepared. Showing the original description.

Self-hosted assets: production-level fonts, icons, dynamic imports, offline. Use when implementing, reviewing or testing self-hosted assets for React, Vite, Next.js or Perfect_AI projects.

The English summary is being prepared. Showing the original description.

Free meta-search via SearXNG — aggregates results from 70+ search engines. Self-hosted or use a public instance. No API key needed. Falls back automatically when the web search toolset is unavailable.

The English summary is being prepared. Showing the original description.

Self-hosted auth for TypeScript/Cloudflare Workers with social auth, 2FA, passkeys, organizations, RBAC, and 15+ plugins. Requires Drizzle ORM or Kysely for D1 (no direct adapter). Self-hosted alternative to Clerk/Auth.js. Use when: self-hosting auth on D1, building OAuth provider, multi-tenant SaaS, or troubleshooting D1 adapter errors, session caching, rate limits, Expo crashes, additionalFields bugs.

The English summary is being prepared. Showing the original description.

Clarify the availability and requirements of model serving on booked Itô GPUs. The supplied implementation does not support serving, so it reports that limitation and documents future booking verification, configuration review, and explicit confirmation requirements.

• Checking documented serving availability after an Itô GPU booking
• Clarifying limitations for an OpenAI-compatible endpoint
• Reviewing future model-serving configuration requirements

Search across multiple engines through SearXNG, a service that combines search results. Filter by category, date range, or engine, and get titles, links, and snippets. Public instances require no API key.

• Search multiple engines for research sources
• Find recent news within a chosen date range
• Use an alternative when the main search tool is unavailable

Set up and troubleshoot Honcho memory for Hermes so user preferences and facts carry across conversations. Configure how memory is recalled, manage separate agent identities across profiles, and adjust context size, observation settings, and reasoning frequency.

• Setting up cloud or self-hosted memory for Hermes
• Investigating missing memories or profile synchronization issues
• Sharing user context across multiple agent profiles

Review links and external resources for domains that ad blockers commonly block. Find navigation and loading failures, test behavior with uBlock Origin, and suggest direct links, self-hosted scripts, or server-side forwarding where appropriate.

• Investigate links that fail with ad blockers enabled
• Check loading of external scripts and images
• Review tracking redirects in navigation links

Use Strix to test web apps, APIs, and source code for exploitable security flaws. Choose local or cloud execution, set testing scope and budget, and review validated findings with reproducible examples and structured reports.

• Security testing an application or API
• Testing source code alongside a deployed application
• Choosing between local and cloud execution

Test a running web application with Strix to find authentication, access control, and other security flaws. Review working proof-of-concept exploits, which demonstrate each issue, and use the evidence to guide fixes and retesting.

• Security testing a staging web application
• Checking access between accounts and organizations
• Testing a local development server

Set up Strix security checks in CI/CD to test pull request changes, report verified vulnerabilities, and gate merges. Covers both a CLI running on your own infrastructure and a managed service with pull request comments.

• Check pull request changes for vulnerabilities before merging
• Add Strix scans to GitHub Actions or GitLab CI
• Choose between managed reviews and scans on your own runners

Assess how marketing channels contribute to conversions and revenue. Compare attribution models, which assign credit to customer interactions, reconcile conflicting reports, and design first-party tracking that connects browsing history to bookings or purchases.

• Reconciling conversion counts across advertising tools, analytics, and CRM
• Comparing first-touch and last-touch credit
• Designing surveys to capture word-of-mouth discovery

Review GitHub Actions workflows for unsafe input handling, excessive token permissions, exposed secrets, and changeable action references. Get findings grouped by issue type, with severity ratings, exact YAML locations, and concrete fixes to review.

• Reviewing CI workflows for security issues
• Checking privileged triggers that run fork code
• Restricting GITHUB_TOKEN permissions

Set up Cloudflare Access and Tunnel to protect internal applications using user identity and device health checks. Covers application access policies, WARP device enrollment, and audit logging for teams replacing VPN access.

• Replace VPN access with application-specific permissions
• Expose internal apps without opening inbound ports
• Limit contractors to approved applications

Set up encrypted connections between devices with Tailscale and control access by user or device. The skill covers network routing, device name resolution, and self-hosting the coordination server with Headscale.

• Replacing a traditional VPN with Tailscale
• Restricting server access by team or device
• Connecting remotely to internal networks

Build searches with Qdrant that find similar content and filter results by attributes. The skill covers document retrieval for AI answers, vector storage, memory optimization, and distributed deployment for larger collections.

• Building document retrieval for AI answers
• Combining similarity search with category or date filters
• Reducing memory use for large vector collections

Build document search and AI retrieval workflows with Chroma, a database for numerical representations of text. Cover document storage, meaning-based search, metadata filters, persistence, and connections to LangChain and LlamaIndex.

• Building document search based on meaning
• Adding document retrieval to AI answers
• Filtering search results by document attributes

Ask questions about your journal, Obsidian vault, or other text notes, and continue conversations that remember earlier chats. The companion uses cognee memory with local databases, reads your notes without changing them, and saves conversations for later reference.

• Asking questions about journal entries
• Finding information in an Obsidian vault
• Continuing a conversation with earlier chats in memory

Review an AI plan through six questions covering evaluation examples, error targets, fallback behavior, regulatory risk, model choices, costs, and hiring. Produce a structured verdict with gaps to address and three concrete next steps.

• Reviewing an AI feature before release
• Comparing APIs, fine-tuning, and self-hosting
• Checking AI regulatory risk before an EU launch

Support startup AI strategy by comparing API use, fine-tuning—additional training of an existing model—and in-house development. Assess three-year costs, regulatory risk, self-hosting breakeven points, and hiring priorities to inform leadership decisions.

• Compare API use, fine-tuning, and in-house development
• Assess regulatory risks for an AI use case
• Calculate when self-hosting becomes cost-effective

Set up a Windows sandbox in Daytona to test OpenWork with a simulated corporate certificate authority. Check successful and broken HTTPS connections, the desktop app’s use of Windows trust, and certificate handling in runtimes it launches.

• Reproducing corporate certificate failures on Windows
• Checking OpenWork’s use of trusted Windows certificates
• Comparing valid and broken HTTPS certificate chains

Set up OpenSEO in an AI agent through its plugin or MCP connection, a way to access external tools. The workflow checks skills, guides sign-in, verifies access, and explains any manual steps needed.

• Connecting OpenSEO to Codex or Claude Code
• Getting setup instructions for ChatGPT or Claude Cowork
• Checking an existing connection and missing skills

Guides development and releases for Kortix Capture, a standalone recording app. Covers installers for Windows, macOS, and Linux, app behavior, sync troubleshooting, and coordinated changes to the recording storage format and its tests.

• Prepare or troubleshoot a Capture release
• Update installers for supported operating systems
• Investigate sync failures on a self-hosted instance