This is the speed release, with some serious resilience work underneath. We halved the time between your prompt and the first token in Agent Zero. In the Launcher, startup time is also cut in half, and saving settings and Instance operations are about 30x faster. Context Doctor: A brilliant community contribution that brings a new recovery layer that repairs malformed tool-call JSON and recovers from empty, repeated, or misformatted model responses. If you run small local models or providers that occasionally misbehave, your runs stop derailing. Context-window indicator: You can now see live token usage, remaining context space, provider-reported costs, cache hits, and generation updates while the agent works. No more guessing what a run costs or when compaction will kick in. Vision sidecar: Another community contribution. Configure a separate vision model alongside your main model. Perfect when your favorite text model has no vision support, or when you want a cheaper model handling images. Also in Core: - The WebUI is faster and steadier during high-rate streaming with progressive Markdown and LaTeX rendering. - Transports now default to Chat Completions, which makes life easier for plugin developers bringing in new providers. - The interactive Browser gets configurable keyboard layouts with better macOS Option and AltGr handling. CLI: - WebSocket recovery keeps running through long outages with safe ownership transfer during reconnects, host changes, and shutdown. - Authorized Chrome/CDP sessions are more stable with persistent browser identities. - Now you get terminal-native ready notifications when TUI or headless runs complete. Launcher: - Startup, Versions, Settings, and Instance operations reuse current data, so everything feels instant while explicit refreshes stay authoritative. - There is a brand new Advanced section for power users: a file-first workspace for Dockerfiles and Compose files with fixed build, run, and teardown actions. - Running local Instances get a native Restart that waits for the Agent Zero UI to be ready.

Hi Team! Does any of you have problems when switching models? For example, when my gpt account credits expire, I switch to Agent Zero API, and when those credits expire (5 minutes after 😓) I switch to a local model on LM Studio but since 2-3 updates ago I am struglingnto switch them and, e en when the settings show the correct model, I keep receiving the Openai quota limit blah blah. Any help would be really appreciated. Thanks in advance!

Hey everyone, The new Agent Zero website update has just been deployed. Why did we update it? To make the site faster (better SEO/loading) and the staking process safer (isolated connector), with a nice gamification touch. The Big Changes: 1. Locking: You can now "Lock" your tokens for a set time to get a Score Multiplier. This is great for those who are in it for the long haul. 2. Leaderboard: We added a public ranking of top stakers. 3. User Experience: Much better step-by-step guides inside the portal. Do I need to do anything? No. If you are already staked, everything works as before. Your API access is unchanged. However, if you want to climb the leaderboard using the new Locking Multiplier, you can choose to unstake and restake with a lock. Let us know what you think of the new design! https://www.agent-zero.ai/

Hi there! Just wanted to ask you which model you have found to be the Best local model you have used with A0 so far (with a requirement limit of 24GB of RAM). I'm downloading gemma3:27b-it-q8_0.gguf right now.

Hi team! Could anyone help me on this issue? O have tryed se eral vision models and I keep getting this misformat error. Thanks in advance!