Real AI agent use cases, with sources and setup prompts
Project memory, graph stores and local vaults builders open-sourced for agents. 13 matching use cases below, each with a public source.
Looking for something else? Search all 348 use cases or .
Built Breadcrumb to record screen, meetings and AI decisions locally, then expose 30+ MCP tools to Claude Code, Codex and Cursor.
Built JevBench, a reproducible benchmark for typed decision models used around agent memory and tooling.
Built Cairn Remembers, an MCP server over a local SQLite vault so Claude Code or Codex can read and write owned memory with no cloud account.
Built Mnemo, a local-first AI memory layer for any LLM using Rust, SQLite and petgraph.
Built an AI memory system with biological-style decay and reported about 52% recall in their setup.
Open-sourced a memory layer so any AI agent can keep long-term context the way Claude.ai and ChatGPT do.
Used LLMs to extract structured data from Le Fooding reviews and mapped the French chef and restaurant network.
Built a free, open-source app with Claude Code that shows CPU and memory in the Mac notch.
Created multiple independent Grok Bot workers, each with its own role, memory, rules and access, and let them hand work to each other.
Shipped recall-mcp so each Claude Code session is distilled into entities and decisions in Postgres + pgvector for the next run.
Built Recall, local project memory for Claude Code so context survives across sessions.
Built MemorySync so apps can give agents lasting user memory without building storage from scratch.
Built NanoMuse, an open-source personal agent with a stable name and memory across phone and computer.
Five real AI use cases with setups, every morning. Free.
The Daily 5 will arrive in your inbox each morning. Unsubscribe any time.
Send the public link (post, video, repo or write-up). We credit you and link back.