Arc runs on your own machine — the client starts it, so there is no endpoint to ping.
Local hub your coding agents sign into: rooms, tasks, decisions, artifacts, memory. Desktop app.
Today is the operative word: we check Arc every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Task queue, decisions and memory for coding agents. Local SQLite, no network. Requires Bun.
Shared memory for coding agents and their teams: docs, epics, tasks and decisions over MCP.
Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.
Mine your local AI coding session logs into a profile your agent loads before every task.
deja-vu: local memory over the session histories of thirty-four coding agents.
Local-first memory for coding agents; stores decisions, bugs, and context across sessions.
Cross-tool decision memory for AI coding agents: search your decision graph, check changes over MCP.
Memory for coding agents: the decisions, the dead ends, and where the last session stopped.
Answers built from our own checks of this server.