Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More

Owned by Daniel

Create with AI from your desktop. Private. Unrestricted. No API keys. No subscriptions. Setup workflows with AI Agents that run using local LLMs

45 contributions to Agent Zero
Agent Zero v2.14 is out
This release focuses on the Core: optimization and stability, with a few new things on top. Faster startup and chat switching: Boot to first token time is down 35%, and opening a chat is 4x faster than the previous version. Embedding warm-up now overlaps chat restoration and startup services, and chat rendering proceeds independently of model, context-usage, and goal refreshes. Paradee Heart local speech: A 9MB text-to-speech model, added alongside Kokoro and made the default for unconfigured settings. Existing voice selections are preserved. It is English-only for now, a starting option. Cost controls: Configurable context breakdown and usage rows, plus selectable price currencies with cached exchange rates. Browser configuration: Streamlined quick settings, centralized extension management, Chromium management pages, download preferences, and optional annotation screenshots. Scheduler editing: Resizable and expanded prompt fields, drafts preserved after failed saves, correct initial state and project inheritance, and optional YAML task storage. Subagents and chats: Directly delegated agents show their working state and can be stopped independently. Parent cancellation propagates correctly, and nested children appear in the sidebar. Fixed disappearing chat and task lists when Sidebar Folders is disabled. Manual chat names stay intact under always-on automatic naming, and rejected custom names no longer disable it. Model preset editing reloads current presets before opening, so stale drafts cannot delete presets created elsewhere, and late selector responses cannot overwrite another chat's selection. Models and providers: Prompt caching preserves cacheable prefixes in long Responses conversations, adds cache routing for Venice and the Agent Zero API, and accepts configurable hints for custom providers. Better model compatibility with reasoning-field fallback, Claude prompt adaptation across third-party providers, and corrected repeat detection for native tool calls. Nebius, Venice, Z.AI/Coding, and OpenRouter embeddings now route through LiteLLM instead of custom endpoints.
Agent Zero v2.14 is out
1 like • 23d
@Alessandro Frau Are we going to see a fix for the secrets bug? In this latest release I still see §§secret(API_KEY_OTHER) in my agents context. This is very problematic when trying to copy instructions or trying to diagnose bugs / track down precise locations. I run everything locally! I don't need these guardrails. Would be nice if there was an option in the settings to turn off secrets masking completely! It is unnecessary in my case. Everything is offline and local.
What an Agent!
I just want to say thank you to the team that's been designing and growing A0! Over the past couple of months the utility of the Agent and it's ability to perform long-run tasks has improved significantly! It's been a phenomenal aid to both my personal and professional life. Thanks all and keep up the great work!
1 like • 28d
Yes, AgentZero certainly has come a long way. The stability and all the added features to the user interface: Project organizing, chat renaming, the stop button, the plugin system, the task scheduling, and more - these have all made it very pleasant to work with. Perfect for local LLMs too. It seems the latest AgentZero is quite happy working with my local LLM setup.
Do You Quiz Your LLMs???
You should be testing your LLM to see which one works best for your needs and gives the BEST results! I run local LLMs always and it is important to test their intelligence before you start running them. But I would say every LLM you use - even the frontier models should be put to the test before you start working with them. See my results with my local models in the pictures. It past the tests. Granted the two that it got wrong - it may have got them correct with a better context. This is why a good prompt matters! Especially when working with AgentZero. Test how smart your LLM is here: https://www.llm-quiz.com/quiz
Do You Quiz Your LLMs???
0 likes • 29d
I will be discussing this in detail and sharing videos, join us over at: https://www.skool.com/local-llm-wizardry-5423 to learn more, it's free.
Proof You CAN Run Local LLMs
I see people on here all the time saying that you cannot run AgentZero with Local LLMs. People think that somehow this is impossible - or that you have to sacrifice intelligence - NOT TRUE. I have been running strictly offline local LLMs since day 1 with AgentZero, I pay ZERO api fees! What makes this possible is is having a good engine to prefill the prompt and a good LLM server. Do not use Ollama, do not use vLLM and although I do like it - do not use LM Studio. You need to run a model server with what is called model streaming - this is how you can get around size limitations on your VRAM. I am getting crazy fast speeds with big & intelligent models now, because I take all this a step further and use speed projection, MTP, and the right Quant-size! All of these matter to get quality intelligent output WITH speed. Stop belly-aching that you can't run local LLMs with AgentZero, you can!
Proof You CAN Run Local LLMs
0 likes • Oct 17
See my other post, but to reiterate: Strata with 1 model (Qwen3.8-flash-next from ISTA-DASLab)
0 likes • 29d
Anyone interested, you can get the details in my new group: https://www.skool.com/local-llm-wizardry-5423
Best local models
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.
0 likes • Oct 18
@Joshua Cunningham Times have changed... local models are capable now. Have you tried using the Strata engine with AgentZero?
0 likes • Oct 18
@Lolichelis Ia Have you seen the new Strata engine? I am getting great results using it with my AgentZero setup and I also have a 3090. I get up to 120 tokens per second with quality output.
1-10 of 45
Daniel ITwizard
3
7 points to level up
@daniel-p-4970
Certified IT professional and Linux user. Investigative researcher.

Active 12h ago
Joined Mar 2, 2026
USA
Powered by