How to Build a Chatbot That Remembers Users with Supermemory
Most chatbots reset every session. Wiring Supermemory into your chat loop lets the bot recall past preferences and facts. Here is the read-write pattern, with…
Category: Blog
How to Add Persistent Memory to Your App with Supermemory
Supermemory is a memory API that stores and recalls user context across sessions. Here is how to create a namespace, add memories, and retrieve them,…
How to Give an AI Agent Long-Term Memory with Graphiti
A chat agent forgets everything between sessions. Graphiti stores facts as a time-stamped graph so the agent remembers what changed and when. Here is how…
How to Build a Temporal Knowledge Graph with Graphiti
Graphiti builds knowledge graphs that track how facts change over time, so your AI agent knows what is still true. Here is how to install…
How to Scrape Structured Data with Stagehand Extract
Selector-based scrapers break on every redesign. Stagehand's extract() turns a page into typed JSON from a schema. Here is how to build a resilient scraper…
How to Automate Browser Tasks with Stagehand and Playwright
Stagehand adds AI actions to Playwright so you can call page.act('click login') instead of hunting selectors. Here is how to install it, write an extract…
How to Fine-Tune an Open LLM on Together AI
Fine-tuning an open model used to mean renting GPUs for days. Together AI turns it into a job you upload and monitor. Here is the…
How to Run Open-Source LLMs with Together AI
Together AI hosts 100+ open-source models behind an OpenAI-compatible API. Here is how to get a key, call Llama or Qwen, and keep the bill…
How to Run Batch GPU Inference on Modal Without a Server
Processing thousands of items through a model does not need an always-on GPU box. Modal parallelizes the work across containers and charges only for the…
How to Deploy a Python Function to the Cloud with Modal
Modal runs Python functions in the cloud without a Dockerfile or Kubernetes. Here is how to install the client, run a function remotely, add a…
How to Track LLM Costs Across Providers with LiteLLM
One team, five providers, one mystery invoice. LiteLLM's virtual keys, budgets and logging turn scattered LLM spend into a number you can actually control. Here…
How to Set Up LiteLLM Proxy for 100+ LLM APIs
LiteLLM is an open-source proxy that puts one OpenAI-compatible API in front of 100+ models. Here is how to install it, add keys, and call…