Shipped,every week.

The whole marketing site has been redesigned: home, pricing, docs, blog, changelog, status and legal pages share one new look with scroll animations, a pricing plan finder, and a searchable docs hub. "Talk to us" now opens our booking calendar right on the page, so you can pick a time with the founders without leaving the site.

The app has a cleaner layout. The sidebar is grouped into Build, Monitor, Developer and Team; Activity (API, Playground, Team) and Team (Members, Settings) are now single pages with tabs; Settings, Plans and Billing moved into the avatar menu. All your old bookmarked links still work.

Connectors added in a team workspace are now available to every active member, not just the person who added them. Tarqa also falls back to the older SSE transport for MCP servers that don't support Streamable HTTP, discovers tools automatically after an OAuth connect, and clears stored credentials if a connector is pointed at a new URL.

Chats in a team workspace now count against the team's plan and shared pool (plus any per-member caps) instead of the member's personal plan, and they show up in the team's usage and billing reports.

Gemini models no longer reject a turn when the model calls several tools at once.

Choose how often a browser asks for your two-factor code: every sign-in, or once every 1, 5, 7 or 30 days per device. Set it in Settings → Profile → Two-Factor Authentication.

Connect any MCP server to your workspace and its tools become available to models in the Playground and the chat API. Tarqa runs the tool calls server-side and shows each call and its result in the conversation. OAuth-protected servers are supported. Available on Pro and team plans.

Tools now work with Gemini models (tool schemas Gemini rejects are cleaned up automatically) and with your own GPU-tunnel models, so switching models in the Playground no longer breaks tool calling.

The app no longer crashes on first load in browsers that block site storage (strict tracking prevention or enterprise policies), and rapidly toggling light/dark mode no longer freezes the page. Failed API calls are now always recorded correctly in your analytics.

Send an Idempotency-Key header on non-streaming requests and a retry within 24 hours replays the original response instead of running (and billing) twice.

Failed webhook deliveries are retried automatically in the background. Every delivery carries a stable ID you can dedupe on, plus an HMAC-SHA256 signature header; the new Webhooks docs page covers event types, payloads and how to verify signatures.

API keys now show which workspace they belong to (personal or team) and whose plan they count against. The rate-limits and error docs explain the two separate limits (monthly quota vs. short-term burst), when Retry-After is sent, and a retry pattern that handles both.

Build tools with a form instead of hand-writing JSON (the JSON editor is still there for advanced cases). Tool calls now show a readable card — the tool name in plain English and its arguments as a labelled list, with raw JSON one click away — and the result box explains what to do. Tool calls are kept when you reopen a conversation, and tool calling now works with your own GPU-tunnel (hosted) models too.

Two-factor sign-in now uses a one-time code sent to your email. The authenticator app (TOTP) and passkey options have been removed.

Account, billing, and team emails have a refreshed, consistent layout.

Fixed duplicate payment handling, subscription cancel/retry, and cross-team isolation in Razorpay webhook processing.

Improved document chunking and text extraction, and fixed memory extraction pulling in irrelevant context.

Plan filtering, pagination, CSV export, and an expanded audit log across user and team management.

Fixed webhook delivery retries and duplicate project name handling in team workspaces.

Closed fail-open paths when the MFA encryption key is misconfigured, stopped malformed verification requests from returning a 500, and fixed a shared rate-limit lockout during verification.

Connect Google Drive or Notion to sync documents straight into your knowledge base, with automatic background re-syncing.

Verify sign-in with a one-time code sent to your email as an alternative second factor.

Added CAPTCHA and disposable-email checks on signup and login to block automated abuse.

The chat API now supports tool calling across Claude, GPT, Gemini, and Bedrock models — the model can request a call into your own application (e.g. to query your database) and use the result to answer.

Register your functions once and the JS/Python SDKs auto-discover them on every call — no need to pass tool schemas and handlers each time. You can also let the model search your knowledge base as a tool it calls itself.

Fixed a CORS configuration issue that could block legitimate cross-origin requests to the API.

Code and document responses in chat now render as downloadable artifact cards with correct file extensions.

Resolved several high-severity security and billing issues found in an internal audit, and removed unused legacy code paths.

You can now subscribe to product updates via a newsletter signup.

Fixed inaccurate token and usage counts shown in analytics, billing, and the admin panel.

Securely reveal a previously created API key (with MFA verification) instead of having to generate a new one.

Fixed a billing calculation issue affecting team plan subscriptions.

Fixed the docs site crashing after deploys and serving stale content for up to a year on repeat visits.

Improved admin tools for managing team seats and billing subscriptions.

Fixed the search scope dropdown not finding indexed documents, and RAG chat answers pulling in unrelated knowledge base content instead of the documents attached to the conversation.

Added a Contact Us form for reaching the team directly, and this changelog page to track product updates going forward.

Team workspaces now automatically downgrade when a subscription lapses, keeping billing and access in sync.

Improved search and live monitoring tools in the admin panel for faster account and usage lookups.

Reorganized docs with new guides for GPU tunneling and hosted model deployment.

Billing now tracks usage per workspace, giving teams clearer visibility into spend across projects.

Chat responses and documentation now render Mermaid diagrams inline.

Added Vertex AI as a model provider, plus embeddings support for retrieval-augmented chat.

Team workspaces now have an activity log tracking member actions, API key usage, and knowledge base changes.