codemem is designed to sit inside AI coding-agent workflows, capture useful context automatically, and surface it again when the next session needs it.
OpenCode
OpenCode is a first-class fit. codemem plugs in so capture and retrieval happen alongside the workflow you already use, instead of being pushed into a separate memory ritual. Add the plugin to config, restart OpenCode, and let the plugin manage backend execution automatically.
Claude Code
Claude Code is also a first-class surface. Install the plugin from the marketplace inside Claude Code, then reload plugins if Claude prompts you to. Current builds also support automatic viewer startup and a sidecar runtime path for subscription users who are not configuring a separate API key.
Codex (early beta)
Codex is supported through its own plugin marketplace (codex plugin marketplace add /
codex plugin add codemem@codemem). The plugin captures session activity through Codex hooks into the same
shared pipeline as OpenCode and Claude Code, and automatically injects relevant memories into your prompts at submit
time via the UserPromptSubmit hook — the same automatic-injection model used elsewhere. Bundled MCP tools
add on-demand recall for when you want to search memory explicitly. Support is early beta today: capture is dogfooded
end-to-end, and automatic injection is wired in but still being validated across Codex models.
What the integration model is for
The point is not just to save transcripts. The point is to keep decisions, debugging context, and repo-specific patterns available when a later agent session needs them.
More to come
OpenCode and Claude Code are the stable integrations today, with Codex in early beta. More agent surfaces can follow from the same model.