Integrations

Manage optional provider credentials in Arka’s user .env file.

Arka keeps optional provider credentials in its user .env file. Setup never prints secret values and supports interactive, scripted, and stdin-based flows.

arka integration list
arka integration init --config-dir .
arka integration init --config-dir . --json
arka integration init --config-dir . --gitignore
arka integration setup all
arka integration setup serper
arka integration setup signoz --url https://signoz.example.com
printf '%s' "$OPENROUTER_API_KEY" | arka integration setup openrouter --key-stdin
arka integration setup stripe --key-file /run/secrets/stripe_key
arka integration setup stripe --config-dir ./config --key-file ./stripe_key
arka integration doctor --json
arka integration doctor --fix

Use --key for CI, --key-stdin to avoid shell history, and remove <name> --yes to revoke a local configuration entry. Common aliases include gh for GitHub, hf for Hugging Face, gemini/gcp for Google, and ctx7 for Context7.

The registry covers the following categories:

• Search, model providers, collaboration, and app services.
• Databases — postgres, redis, mongodb.
• Package registries — Docker Hub, npm, PyPI.
• Observability — SigNoz, Sentry, Datadog, New Relic.
• Infrastructure — Cloudflare, DigitalOcean, Hetzner.
• Hosting — Railway, Vercel, Netlify, Render, Fly.io.
• Email — Resend, SendGrid.
• Authentication — Clerk, Auth0.
• Analytics — PostHog, Amplitude.
• Feature flags — LaunchDarkly, Statsig. LLM observability includes Langfuse. AI development integrations also include LangSmith and Weights & Biases. Remote compute integrations include Modal and E2B. Local model runtimes include Ollama, vLLM, and LM Studio; use --url for a custom local endpoint. Hosted model integrations include Groq and Replicate. Messaging providers include Telegram and WhatsApp.

Natural language works too: set up Serper, show available integrations, or check my Sentry integration.

Local and hosted models together

Use arka hybrid status to see reachable local runtimes (Ollama, vLLM, or LM Studio) alongside configured hosted providers. arka hybrid run "..." uses local-first routing by default and falls back to hosted models. Select --policy hosted-first, local-only, or hosted-only; --policy parallel runs one local and one hosted model and returns both answers for comparison. Persist the default with arka hybrid config local-first (or another policy).

For privacy-sensitive work, force a hard local-only boundary:

arka run-only-local-llm "summarize this repository"
arka hybrid run --local-only "draft a migration plan"
arka hybrid config local-only

local-only filters the candidate chain before inference, so hosted providers are not used as fallbacks. If no reachable Ollama, vLLM, or LM Studio model is configured, Arka returns an error instead of sending the prompt to the cloud.