Connect your AI tools

chat-recall init does this for you. Manual equivalent in ~/.mcp.json:

{
  "mcpServers": {
    "chat-recall": {
      "command": "chat-recall-mcp"
    }
  }
}

chat-recall-mcp is a relay, not the server. It finds the background daemon for your tool profile, starts one if there is none, and passes bytes to it. Every session on a machine therefore shares one loaded engine instead of carrying its own: a session costs about 50 MB rather than 87 MB, against a single shared daemon, and background sync runs in one process instead of racing a lock in all of them. The daemon exits 15 minutes after the last session closes.

Two knobs, both optional:

CHAT_RECALL_NO_DAEMON=1          # load the whole server in each session instead
CHAT_RECALL_DAEMON_IDLE_SECS=0   # keep the daemon resident (default 900)

If the daemon cannot be reached for any reason, the session loads the server itself and works exactly as it did before — slower, never broken.

chat-recall init installs the Claude Code hooks in every profile's settings.json. If you added only the MCP server, from a marketplace button or by hand, the MCP server installs them when it starts. You run nothing else.

To choose which hooks run, or to remove them:

chat-recall install-hooks --no-resume-hint  # without the resume warning
chat-recall install-hooks --no-messages     # without messages between sessions
chat-recall install-hooks --uninstall       # remove ours; third-party hooks stay

After --uninstall the MCP server does not put them back.

Hook	When it fires	What it does
SessionStart	New session (startup / clear)	Injects the project-scoped wake-up bundle
UserPromptSubmit	When you type a prompt	Searches past sessions; if a similar one exists, injects "you've worked on this before" into the agent's context
Stop	After every assistant turn	Auto-saves topics, decisions, and tools to ~/.chat-recall/memory/
PreCompact	Before Claude Code compacts context	Emergency save so nothing is lost to compaction
SessionEnd	When the session closes	Escalates the session's learnings in the background, so nothing is delayed
SessionStart, UserPromptSubmit, Stop, SessionEnd	Each turn	Messages between sessions: tells the session its id, delivers what waits for it, reports its state
SessionStart, UserPromptSubmit, Stop (background)	Until a message arrives	Waits for a message from another session and wakes this one, also when it is idle

The other AI tools get the message hook too, so their sessions can send and receive messages. The installer writes it only for a tool that is installed:

Tool	Where	When a message arrives in the session
Codex	~/.codex/hooks.json	At the next prompt. Approve the hook once with /hooks in Codex.
Antigravity	~/.gemini/config/hooks.json	At the next prompt
Cursor	~/.cursor/hooks.json	When the agent stops, as a follow-up prompt
opencode	~/.config/opencode/plugins/chat-recall-messages.js	Within a few seconds, also when the session is idle
pi	~/.pi/agent/extensions/chat-recall-messages.js	Within a few seconds, also when the session is idle

Claude Code, opencode and pi wake an idle session. In Codex, Antigravity and Cursor, an idle session reads its messages when its user types next. chat-recall doctor shows the hook of each tool.