A side-by-side of two agent memory for building AI agents — live GitHub data, languages, and what each is best at.
Short answer: Letta (MemGPT) leads Letta (MemGPT) vs Zep by community traction (★ 24k vs ★ 4.8k). Pick Letta (MemGPT) for persistent agents; pick Zep for temporal memory.
✓ Live data verified
| Letta (MemGPT) | Zep | |
|---|---|---|
| GitHub stars | ★ 24k | ★ 4.8k |
| Language | Python | Go |
| Category | Agent memory | Agent memory |
| Best for | persistent agents | temporal memory |
| Repository | letta-ai/letta | getzep/zep |
Letta (MemGPT) and Zep are both credible choices. By community traction, Letta (MemGPT) leads (★ 24k). Pick Letta (MemGPT) for persistent agents; pick Zep for temporal memory.
Both are credible agent memory. By community traction Letta (MemGPT) leads (★ 24k). Pick Letta (MemGPT) for persistent agents; pick Zep for temporal memory.
Letta (MemGPT) is Stateful agents with long-term memory and self-editing context, evolved from the MemGPT research.. Zep is Long-term memory store for agents with a temporal knowledge graph of facts and their validity over time..
Letta (MemGPT) has more — ★ 24k vs ★ 4.8k (live counts).
Often yes — many teams combine agent memory. Check each tool's docs for interop; they solve overlapping but not identical problems.
Letta (MemGPT) is primarily Python; Zep is primarily Go.
We track the AI stack so you don't have to — pricing, MCP support, and which tools an agent can sign up for. Free.