akitaonrails/ai-memory
ai-memory gives coding CLIs a shared, Git-backed memory and bounded handoffs, so work can move between agents without treating stale recollections as current code truth.
ai-memory captures sanitized lifecycle observations, compiles them into a **Git-versioned Markdown wiki**, and injects bounded handoffs into later sessions. Managed workstreams can continue across **Claude Code, Codex, OpenCode, Pi**, and other supported harnesses.
Use it for decisions, failed attempts, procedures, and cross-agent handoffs while keeping the checkout, tests, and runtime as operational truth. Per-repository exclusions can prevent recognized file-tool events from entering the spool or server.
ai-memory captures sanitized lifecycle observations, compiles them into a **Git-versioned Markdown wiki**, and injects bounded handoffs into later sessions. Managed workstreams can continue across **Claude Code, Codex, OpenCode, Pi**, and other supported harnesses. Use it for decisions, failed attempts, procedures, and cross-agent handoffs while keeping the checkout, tests, and runtime as operational truth. Per-repository exclusions can prevent recognized file-tool events from entering the spool or server. Client support varies: some integrations lack lifecycle hooks or automatic handoff injection, and several require **finalize-session** for a true closing summary. Per-user slots isolate injected context, not project-wide reads or searches.
This makes cross-agent continuity a concrete, lightweight repository practice: sanitized lifecycle observations become inspectable Git history and bounded handoffs while code and tests remain authoritative. It supports the broader shared-context direction but narrows it with uneven client hooks, explicit finalization requirements, and user-slot isolation that does not restrict project-wide reading or search.