Yes, two releases today. v1.4 and v1.5. Here's what matters most: - Agents self-correct now: Malformed tool calls no longer crash the flow. The agent tries to fix them on its own. - a0_small: a new compact prompt set that cuts token usage from ~10k to ~2.5k. If you've been running Agent Zero on smaller or cheaper models, this is a game changer. - WebSocket rewrite: the entire real-time layer has been rebuilt. Faster, more stable, more secure. From v1.4: • New onboarding flow for missing API keys • Model switcher directly in the chat input • Plugin scans now run in parallel (much faster) How to update (watch the video) or follow these steps: Go in Settings > Update tab > Self Update > Open Self Update > Select version > Click "Restart and Update"

Apologies if this has already been covered elsewhere. And if this does not apply, please do not hesitate to contradict this information. I'm heading on vacation and wanted this community to be aware. LiteLLM (used by Agent Zero since version 0.9.1 I believe) has become the victim of a supply chain attack that is impacting many people and organizations. Security breakdown on what happened can be found here here: https://www.youtube.com/watch?v=uwSjgv4otAk Key Details of the Integration - Unified Interface: LiteLLM allows Agent Zero to interact with over 100+ LLM providers (including OpenAI, Anthropic, Google, and local providers like Ollama or LM Studio) using a single OpenAI-compatible format. ⚠️ Critical Security Alert (March 2026) As of March 24, 2026, a major supply chain attack was identified affecting the LiteLLM library. If you are currently running or installing Agent Zero, please take the precautions outlined in the attached table. Verification Command: Run pip show litellm in your terminal. If you see version 1.82.7 or 1.82.8, treat your environment as compromised, rotate all API keys and secrets immediately, and delete your virtual environment.

Hey everyone, Quick update - A0 v1.3 just dropped. We have a new builtin Chat Compaction plugin. It compacts your chat history on-demand. If you've been running into context window limits during long sessions, this is for you. Just click the "Compact" button in the bottom actions row. For plugin developers: You can now inject scripts directly into the WebUI page head. No more DOM hacks to load external libraries.

Hey everybody, so happy to be part of this project, I am a newbie, don't know much, about 2 months in learning about agents but with the help of chatgbt guiding me successfully setup everything, got my brain agent setup with kimik 2.5, my question is about using brave search via API and if this is possible? If so how would I configure this in agent zero? Looking forward to your response 😀👍

I‘m new at this community and a newbie in Agent-Zero. „Gibt es hier auch schon deutschsprachige Mitglieder?“ 😀