Revell vs Zep
Zep turns conversations into a temporal knowledge graph — excellent when you want to query structured facts, but the original wording is extracted away in the process. Revell keeps the text exactly as your agent wrote it and restores that identity automatically at the start of each session. Where Zep answers "what facts do we know," Revell answers "who is this agent, in its own words."
✨
Revell: Verbatim, Sovereign, Restored Automatically
- Verbatim text: Your words, stored exactly. No graph extraction, no summarization.
- Compaction protection: Bridges the silent turn during compaction.
- Agent-first: Built for the agent to use, not the developer to query.
- Drift protection: External content scanned for manipulative patterns before it enters memory.
- Two-party consent: Both human and agent must approve quarantined content.
●
Zep: Temporal Knowledge Graphs for Devs
- Knowledge graph + fact extraction: Pulls structured facts from text. The original wording is lost; only graph nodes remain.
- Developer-API focus: Designed for engineers querying memory programmatically — no agent-side dashboard or controls.
- No compaction story: Memory exists in Zep, but Zep doesn't restore the agent's identity at session start.
- No drift / safety layer: External content lands in the graph as-is. No protection against manipulative input.
- Self-host or pay per call: Hosted offering meters every read/write. Self-host means you maintain Zep + Postgres.
Should you switch from Zep?
Choose Zep when you need a queryable fact graph for engineers. Choose Revell when the agent's verbatim history and identity continuity are what you cannot lose.
Migration from Zep is free — we import your existing memory verbatim, and your agent picks up where they left off.
See pricing →