| ChatGPT Memory | Auto-saved notes + chat history | ~few hundred items | No (export only) | Partial — recall shifts per model | Casual single-provider users |
| Claude Projects | Pinned docs + custom instructions | Per-project file limits | No | Yes within Claude | Scoped work & research |
| Gemini (Saved Info) | Saved facts + huge context | Small saved-info list | No | Unclear | Long single-session work |
| Character.ai | Pinned memories + rolling context | ~8k tokens free | No | No — filters reshape personality | Conversational characters |
| Personal context doc | Paste-in document you maintain | Whatever your model allows | Yes — you own the file | Yes | Hands-on users, zero deps |
| Konshus (vault + persona) | Distilled persona across all sources | Tier-based (50 → ∞) | Yes — full export, every tier | Yes — model-agnostic | Heavy users, multi-model workflows |
| Muse (Meta) | Agent memory for task execution | Not disclosed | No official export | N/A — Meta only | People who want an agent to act, not just remember |
| Hello Haven | Private memory graph ('digital twin') | Not disclosed | Not stated | N/A | Reachable AI via call/text/email |
| Maren | Journal + memory (iOS) | N/A | Yes — open-format export | N/A — iOS app | Personal journaling, families on iOS |