Insights, tutorials, and updates from our team. Stay up‑to‑date with the latest in AI development and LLM integration.
We recently partnered with brno.ai for a workshop on running open-source LLMs locally. Here’s a summary of what we covered, from the benefits of local AI to getting hands-on with Ollama and RAG.
More reliable real-time chat: improved WebSocket handling, graceful support for unknown LLM addons, and new addon configuration options for greater extensibility and stability.
Improved error traces with Sentry user context and replay sessions for faster debugging; GTM integration for analytics.
Introduced onboarding dialog, improved session editing, and added dark mode support.
Introduced session deletion, improved error handling, and enhanced sidebar interaction.
Enhanced session creation and extended LLM model information in chat interface.
New LLMs browsing page to explore and pick models, more reliable session handling so your chat history stays consistent, UI improvements (tooltips and sidebar polish), and integrated Sentry error tracking for faster issue detection.
Improved chat creation popovers, clearer model/provider listing (OpenAI models in two columns), a responsive size indicator, and seamless session creation from site activity via cross-site cookie reading. Includes package updates for stability and compatibility.
I’ll show you how I fixed a common performance issue in SvelteKit by correctly ordering my <head> tags, which boosted my Lighthouse score and improved my Largest Contentful Paint (LCP).
Enhanced session management, allowing you to hide and unhide sessions from a new dedicated management page. We’ve also updated user profiles to include first and last names and reorganized chat settings for better usability.
Enhanced chat session management, including renaming and deleting sessions, the ability to copy prompts, and a new reset option for favorite models.
We’ve moved all chat-related settings into one convenient place. Customise your favourite models, manage custom instructions, and organise your sessions faster than ever.
This release introduces favorite model management and several UI improvements in chat and settings.
This release brings PDF assets and UI tweaks in the chat.
Integrate xAI's powerful new flagship model, Grok-4, through our Unified API or test it directly in the chat playground. Learn about its advanced reasoning and long-context capabilities.
This release brings image assets in completions, easier sharing, improved chat management, and a more readable chat experience.
In response to recent security advisories, all DeepSeek models will be removed from the Nomodo.ai platform on July 1, 2025, to ensure the security and integrity of our services.
File upload with image processing, clipboard image support in chat, improved chat text and layout.
Custom instructions, team switcher, improved sidebar, forced logout, and better team management.
User and session caching, new dashboard charts, feature flags, insights in chat, and improved statistics layout.
API key management, model testing, improved balance and transaction history, and backend-driven LLMs page.
Chat sessions, improved chat footer, dynamic API docs, clearer navigation, currency formatting, new analytics graphs, and standardized layouts.
Improved citation widget reliability and Google Tag Manager integration
Account management, login and signup flows, password reset, request history, and improved LLM comparison with charts and tables.
Compare multiple LLMs side-by-side to identify which performs best for your specific use cases. Stop wasting hours testing models individually across different platforms.