https://www.gibsonai.com/use-cases/customer-support
Hi,I am Bobur, a Software Engineer. We built an open-source customer support AI agent that can remember past conversations.Most chatbots treat every message like it’s the first one. This one keeps context over time, remembering what the user said earlier, what issues they faced, and what pages they visited.It can be added to any website with a small widget. The goal is to make support more...
I also see Verdent has a desktop option. In which cases do you recommend using it versus the VS Code extension?
Do you have a benchmark of how many tokens Verdent agents can save for complex asks? For example, I stopped using Cline because it consumes quite a lot of tokens for bigger projects just to analyze and provide context.
I think Verdent provides good planning, where prompts can be structured and I can review, accept, or adjust this plan before any code changes are made.
The only thing I do not like about Verdent does not offer a free plan. It's worth it as a paid tool but it would be great to have free credits to get started. For example, you can use the Cline or Copilot free version or you can bring your own model.
Mintlify Pro costs 250 USD per month. We wanted something similar (AI assistant and nice UI), but fully customizable and cheap. So we built GibsonAI docs in 1 day for about 50 USD.How we did it:Used Lovable for UI components + rendering MDX beautifully (Markdown stored in GitHub).Built an AI Agent for docs using Agno + Memori → personalized Q&A and “smart educator.”Stored embeddings in...
I see you have also integration with LangChain, Agno, CrewAI. I have been using Mem0. But I like how Memori simplifies the developer experience.
Memori engin uses multiple agents to automatically identify and promote your most important long-term memories into short-term memory — so your AI can respond faster and with better context.
Let me know if you tested with AI Agent or the assistant with function calls?
https://github.com/GibsonAI/memori
Hi Everyone,I’ve been working on an open-source project called Memori — it’s a memory layer for AI agents.Memori is designed to give agents a persistent memory layer that supports both:Short-term “conscious” memory (like working memory in humans)Long-term retrieval using SQL full-text search (not vector stores)It’s built around a multi-agent architecture (memory agent, conscious agent,...