116,000 Stars vs. One Binary: claude-mem and palace-rs, Fact by Fact
claude-mem is the most popular memory plugin for AI coding agents. At the time of writing it has 116,434 GitHub stars . palace-rs does the same job. It has 10 . Stars tell you what people clicked. They don't tell you what you have to install, what runs in the background, who writes your memories, or whether anyone measured if the thing finds the right memory. So I went through both projects' own…
claude-mem, a memory plugin for AI coding agents, is currently the most popular with 116,434 GitHub stars. It uses multiple runtimes, a Python package manager for vector search, a local HTTP service, and an LLM to write memories based on agent activity. Palace-rs, on the other hand, offers a simpler alternative with just one binary, one SQLite file, and no LLM or cloud services.
It stores memories verbatim, without any model summaries, and runs on the CPU through ONNX Runtime. Palace-rs also has a temporal knowledge graph and does not depend on the agent remembering to search for information. Privacy-wise, claude-mem collects anonymous usage data by default, while palace-rs does not collect any telemetry.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
