The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
AI Agents & RAG Chatbots with Persistent Memory
I design and build intelligent AI agents and chatbots that maintain conversation context, retrieve reliable information, and interact with external tools and APIs.
Core Capabilities
🔹 Persistent conversation and long-term memory
🔹 RAG-powered answers with reduced hallucinations
🔹 Tool calling, APIs, web search, and file retrieval
🔹 Multi-agent and multi-step workflows
🔹 Integration with OpenAI, Claude, Gemini, and open-source LLMs
🔹 Vector databases including pgvector, Pinecone, Weaviate, FAISS, and ChromaDB
Technologies
LangGraph, LangChain, Agno, PydanticAI, Haystack, FastAPI, OpenAI, Claude, Gemini, Hugging Face, PostgreSQL, pgvector, Pinecone, and Weaviate
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
Another late night. Building a quant trading system an agentic model where different AI agents handle research, testing and risk, and none of them is allowed to place a trade on its own.
The hardest part so far? Being honest when the results say "not yet." Most strategies I've tested failed once real costs were included. That's exactly what testing is for.
Keeping The Psychology of Money and The Diary of a CEO close while I figure it out. What are you reading these days?
Curious how you’ve separated the agents from execution. When you say none can place a trade on its own, is that enforced through a separate execution service with fixed risk checks, human approval or both? I’d love to understand where the agent's decision-making ends and the hard rules take over.
Built this AI agent to find, organize, and manage leads through Gmail, helping automate lead handling and outreach.
n8n is absolute gold for orchestrating lead pipelines like this! Connecting Gmail parsing with LLM qualification saves teams dozens of hours weekly. As someone who builds custom agentic lead automation workflows, seeing clean visual architectures like this is super satisfying. Top-tier build, Talha!.
I built The Quiet Chair, a booking experience for a fictional single-chair hair studio in Baner, Pune, run by a solo stylist named Mira.
Mira’s problem is simple: every booking message interrupts an appointment. Checking availability, confirming times, and handling changes take attention away from the customer in her chair.
The app lets customers choose a service, see available times, and receive an immediate booking confirmation. Availability accounts for opening hours, lunch breaks, existing appointments, and cleanup time. Customers can request a quiet appointment and use a secure link to reschedule or cancel, with online changes closing four hours before their appointment.
Mira has a protected owner workspace to view her daily agenda, check customer preferences, manage appointments, and block personal time.
I built it to turn “Can I book with you?” into “You’re booked” without needing a reply from the owner—and to make later changes just as straightforward. The result is fewer messages, fewer manual calendar checks, and more time for Mira to focus on her clients. @Lovable
