I forked Andrej Karpathy's LLM Council and added a Modern UI & Settings Page, multi-AI API support, web search provi
Hey everyone!
I recently spent a couple of weekends improving Karpathy's excellent LLM Council Open Source Project.
The [original project](https://github.com/karpathy/llm-council) was brilliant but lacked usability and flexibility imho.
**What I added:**
* Web search integration (DuckDuckGo, Tavily, Brave, Jina AI)
* Clean Modern UI with a settings page to support:
* Support for multiple API providers (OpenRouter, Anthropic, OpenAI, Google, etc.)
* Customizable system prompts and temperature controls (the custom prompts open up tons of use cases beyond a "council")
* Export & Import of councils, prompts, and settings (for backup and even sharing)
* Control the council size (from 1 to 8 - original only supported 3)
* Full Ollama support for local models
* "I'm Feeling Lucky" random model selector
* Filter only Free models on OpenRouter (although Rate Limits can be an issue)
* Control the Process, from a simple asking multiple models a question in parallel (Chat Only), Chat & peer rating where models rate the responses of other models, and Full end-to-end deliberation where the Chairman model makes the final decision on the best answer
You can compare up to 8 models simul
Looking at this, this reads stronger on paper than in practice That part stands out. That’s the impression it gives me.
To be fair, the main issue seems to be how this is handled and that tension shows up immediately That’s the key detail here. Curious how this plays out.
Reaction: It's been 7 years , yes 7 whole years
this reads stronger on paper than in practice Let’s see what happens next.
Bluntly speaking, this solves one problem while creating another That’s what changes the context. Curious how this plays out. At least from my perspective.
From a practical angle, this depends heavily on what happens next and that’s why this won’t land the same for everyone
Looking at this, this feels more about execution than intent and that’s what people are responding to Time will tell. That’s just my read on it.
this feels rushed rather than thought through and that tension shows up immediately Interested to see the follow-up.
Bluntly speaking, this feels rushed rather than thought through which is why this is getting picked apart That’s the impression it gives me.
Reaction: me_irl
the intention might be solid, the rollout less so That’s just how it reads to me. At least from my perspective.
From my side, there’s a lot said here but not much clarified Feels like there’s more coming here.
Bluntly speaking, the idea isn’t bad, but the delivery is doing damage and that’s why opinions are all over the place
Reaction: Me_irl
Trying to be fair, the follow-through is what will decide this That’s what changes the context. Could be wrong, but that’s how it comes across.
Reaction: I believed in karma too
From a practical angle, the signal is clear, the strategy less so which explains why reactions are split We’ll see how people react over time. That’s the impression it gives me.