Pinned
Ashpreet Bedi
4,311 posts
Ashpreet Bedi
@ashpreetbedi
00:00- > open source > multimodal > lightning fast > 80 toolkits with 1000s of tools > 23 model providers > 12 vector databases Built from scratch, 16 hours a day, 7 days a week.
- Agents with gpt-4o from scratch 🔥 in 11 minutes we'll build: 🌎 Web Search Agent (2:40) 📈 Finance Agent (3:30) 🫡 Hackernews Agent (5:50) 📊 Data Analysis Agent (8:10) 🗒️ Research Agent (9:35) code: phidata.link/assistants
00:00 - It's here! Our highly requested Agent UI is now OPEN SOURCE 🚀 Over 25000 engineers use our beautiful Agent UI daily — and the #1 ask? Self-hosting. Today, we deliver ✨ Build powerful, multimodal Agents with @AgnoAgi and chat with them using a beautiful UI 🔥 Details below
- It's time! Agno is now Generally Available 🚀 The simplest, fastest, full-featured library for building Agentic Systems is production-ready → 2 years, 2500 PRs, 22K ⭐️ → 1M+ new Agents every week → Built-in Memory, Knowledge, Reasoning & Tools Here's my open source journey
- Lets build `Auto-RAG` where we let the LLM pull the data it needs from different sources. 🔎 The user asks a question. 🤔 LLM decides whether to search its knowledge, memory, internet or make an API call. ✍️ LLM answers with the context. Code: git.new/auto-rag
00:00 - Lets build the `LLM OS` inspired by the great @karpathy Can LLMs be the CPU of a new operating system and solve problems using: 💻 software 1.0 tools 🌎 internet browsing 📕 knowledge retrieval 🤖 communication with other LLMs Code: git.new/llm-os
00:00 - OpenAI, Google, and now Anthropic recommend building Agents exactly like Agno does. So avoid lock-in with @AgnoAgi, which comes with: - 23 model providers - Built-in memory and session storage (out of scope for these libs) - 12+ vectordb integrations (out of scope for these
- Introducing MCP Agents powered by Agno! 🔥 Connect your Agents to 100s of MCP-compatible services. Completely free! 👇 Check out the code below to get started
- 🚀 Introducing the first-ever Agent UI 🚀 This is hands-down my favorite product! Chat with local Agents tailored to my needs. Local memory, storage, knowledge and tools 🔥 ⚡️ Your data, your control 🧠 Compatible with any LLM 🤝 Run multiple agents or a team of agents
00:00 - 🌶️ Hot take: The only way Autonomous Multi-Agent Systems work is by adding Reasoning & Agentic Context. I've tried it all, and here are my learnings👇
00:00 - Fully local RAG with Llama 3 on @ollama & @streamlit Learn how to: 🦙Run Llama 3 using @ollama 📄Add Website & PDFs to a knowledge base 💻Build an AI App using @streamlit 🏬Store chat history in a database @PostgreSQL YT: youtu.be/-8NVHaKKNkM
00:00 - Fully local RAG using @teknium OpenHermes, @ollama and @streamlit . GPT4 level performance at 0% of the cost 🔥 Code: github.com/phidatahq/phid…
00:00
