Hello Agent Zero Community. This thread is for discussion on local models for Agent Zero. If you are interested and new to that topic, watch the brief beginner videos in preparation for the Local Models for Agent Zero classroom session: https://www.skool.com/agent-zero/classroom/c8000b5f After the live classroom session or if you caught the recording, we would love to hear more about what you are doing with local models. Are you running an enormously big model? Do you have separate local Chat and Utility models? What context sizes are you reaching? We want to hear it all.

Hello to everyone. I am brand new to A0. I have some computer Knowledge and was enrolled in Brainstation to pursue a Certified Ethical Hacking and CyberSecurity Analyst certification. Passed the admissions and 1 week before starting (after spending a minimum of 4-6 hours a day/night) going through EC - Council, Occupy The Web, TCM Security, and Udemy, I realized that I cannot sit in an office all day. I am a Tradesman, A Welder/Fitter and will always need to be building and shaping steel. Sorry for the long-winded intro, which has nothing to do with openrouter 😂 might make it easier to help with responses. I have almost zero knowledge of coding (AI may or may not have assisted with my admissions test lol. OK. My issue is that I finally got Agent Zero hacking up and running (I am looking at bug bounties as a side income) and am using open-source router models. Made 1 request saying hello, got a response, made a second input, and red flags everywhere (1st img), so I went and added $10, made another input. Got a response did it a second time got a response and than..... (2nd .img) i than asked if it had access to Kali and recieved this (3rd .img) I am adding screenshots of the models i am using here as well (4,5,6 .img) I Can tell that the absolutlely amazing creator behind A0 isnt a hugwe fan of runniong locally to utilize A0 it has to be better than getting denied every second request. Oh, and my setup is an HP Z440 Workstation with 14 cores threaded to 28, 64 GB ram, Nvidia GeForce RTX 3060 with 12 GB GPU

We're cooking something special for the Agent Zero website, with a fresh new look that better reflects what our framework has become. We're emphasizing what makes Agent Zero special: complete control over your AI agents, from single tasks to fully automated workflows, with the freedom to use any LLM provider or local model, and the option to access true private and uncensored AI models through Venice AI. This is still a work in progress, and we'd love to hear your thoughts! What would you like to see on the new site? Drop your feedback below 👇 As always, Agent Zero remains free and open-source. We're building this together!

Hi, I am trialing GLM 4.6 on Venice beta and normally it was working better than anything else yesterday, but today it seems to be caught in a loop of some sort when I ask it to summarize the community call. See attached video. Anyone have any hacks or workaround for this situation? Thanks a lot! :D A0: Message misformat, no valid tool request found. network_intelligence A0: Generating... minimize expand You have sent the same message again. You have to do something else! network_intelligence A0: Generating... minimize expand You have sent the same message again. You have to do something else!

Hi everyone! I am a cybersecurity professional and have been messing around with using Agent Zero as an automated penetration testing agent since Agent Zero was merged with the hacking edition. I am testing against the intentionally vulnerable OWASP Juice Shop web application which is also running in docker). After learning docker concepts, then Agent Zero concepts, I was able to push Agent Zero pretty far in solving Juice Shop challenges. However, the sequential nature of Juice Shop challenge solving was taking a long time and thus I started looking into using subordinate agents for each challenge (with custom profiles for each, pentestmanager, reconspecialist, pentester). Alas, Agent Zero is not architected to support simultaneous agent swarms at this point. I then pivoted to a custom single agent using the Task Scheduler to create simultaneously executing tasks (using TaskType.AD_HOC, and then run_task with dedicated_context=true) and this appears to be working well so far. I also went to through the journey of attempting to use local LLMs via LM Studio before finally listening to folks here and instead using free LLMs on OpenRouter (currently using Chimera). I still hold hope that I can self-host a ridiculously large opensource LLM, in a private cloud if needed. Abliterated LLMs are particularly useful for ethical hacking and local LLMs are useful for sandboxing cyberlab activities when commercial LLM decline actions. However, there does not appear to be an Agent Zero setting (evironment variable or setting dialog) to adjust LLM timeout value, and slow LLM responses invariably lead to timeout errors. It would be fun to develop the solution to the point where it can target any cyber range system (e.g. infrastructure, edge device) and the agent follows industry penetration testing framework stages and actions from PTES (Penetration Testing Execution Standard), NIST SP 800-115, and OSSTMM, etc.