Transfer a reviewed AI profile through Claude's memory import
A migration tutorial moves a condensed profile from ChatGPT into Claude using the built-in import flow rather than an entire chat archive.
Topic
Source-linked agent workflows tagged Agents.
A migration tutorial moves a condensed profile from ChatGPT into Claude using the built-in import flow rather than an entire chat archive.
AgentMail's Product Hunt page describes per-agent inboxes, incoming-message events, threaded replies, semantic search, and attachment extraction. This lead is an infrastructure recipe rather than a measured customer result.
A parent gives Claude reusable household context and manually saves the changes it notices during everyday conversations.
Ankur Sethi used Claude Code to build Cutlet, steering generated C code with written plans, example-program outputs and memory-safety checks.
A Show HN browser-agent demo takes a CV, scans incoming job information, opens the listings, and extracts matching details into a Google Sheet, illustrating an end-to-end job-research workflow.
A parent created a Claude Project that remembers school routines and travel preferences before planning the year's trips.
Ruben Hassid points Claude Cowork at a folder with about-me, anti-AI style rules, and past issues; Cowork asks clarifying questions, outlines, then drafts the newsletter in his voice.
Jam's creator reports using a named agent to build a campaign dashboard, draft channel-specific content, and operate marketing tasks, with persistent logs and a shared desktop interface for several coding runtimes.
A public Discord showcase introduces Glimpse, a small native webview library and Pi integration for agent status interfaces. The linked README documents bidirectional JSON messages and an optional cursor-following companion.
A NanoClaw user connected their agent to Claude Code with two local inbox files so the agents could exchange server-management requests.
Make's Post-Call Hero case study describes a transcript-driven agent that drafts follow-up email, prepares CRM changes, and can create stakeholder Slack channels, supported by fixed context files and a limited tool set.
A public LiveKit Slack Q&A explains waiting for a participant and checking participant kind before beginning a SIP interaction, with a minimal JobContext example and a link to lifecycle documentation.
A Lobsters introduction points to Cua-Bench, an open-source framework for evaluating computer-use agents across operating-system and UI variations rather than assuming one successful interface generalizes.
A product manager's tutorial walks through a Claude Code project with a lightweight specification, a Google Sheets question source, and browser feedback used to repair the data connection.
Jerry Liu links a worked example by Tuana Celik that classifies incoming email and attachments as invoices or expenses, then routes them through LlamaCloud extraction and LlamaIndex workflows.
An English video walkthrough connects n8n, OpenAI, Gmail, Calendar, and research tools to a personal assistant, demonstrating the construction of an integrated assistant rather than reporting a controlled benchmark.
An English n8n tutorial uses Google Vision OCR for PDF and image invoices, an LLM for structured fields, and Google Sheets for storage, making the OCR-to-extraction sequence explicit.
The template indexes provided learning documents in MongoDB Atlas and uses a Gemini Telegram agent to retrieve relevant passages before answering questions.
A developer's RAG Builder indexes personal notes locally and returns model answers with source attribution.
A public Mastra Discord thread shares a working custom execute wrapper that calls an agent with a Zod structured-output schema and returns the validated object; agent-step visualization remains the author's open question.
The template validates incoming orders, checks local calling hours, and uses a Vapi voice agent to confirm order details while updating status records.
Evan Sunwall's ChatGPT agent researched restaurants, prepared a reservation, paused for personal details, asked before submit, and confirmed a business-lunch booking—successful but slow and shaky.