basicmachines-co/basic-memory vs letta-ai/letta
letta-ai/letta scores higher overall: 77/100 (A-tier) against 71/100 (A-tier). basicmachines-co/basic-memory leads on maintenance, composability; letta-ai/letta leads on reliability, skill leverage, documentation. Scored 2026-07-07, methodology v1.0.
Dimension by dimension
| Dimension | basic-memory | letta |
|---|---|---|
| Reliability | 68 | 74 |
| Skill Leverage | 72 | 78 |
| Documentation | 78 | 82 |
| Maintenance | 90 | 86 |
| Safety / Governance | 64 | 70 |
| Evaluation Readiness | 58 | 74 |
| Composability | 76 | 72 |
| Adoption (capped) | 55 | 82 |
| Overall | 71 · A | 77 · A |
The entries
Local-first agent memory over plain Markdown files with an MCP interface: knowledge persists as human-readable notes the agent reads and…
A platform for stateful agents with self-editing memory, descended from the MemGPT research line: agents manage their own memory blocks…
Frequently asked questions
basicmachines-co/basic-memory or letta-ai/letta?
letta-ai/letta scores higher overall (77 vs 71, methodology v1.0). But they are the same category, so the dimension table below is the real answer.
How is this comparison generated?
Both scorecards come from the same public rubric with evidence notes, scored by the same editorial process. This page presents them side by side; it adds no new judgments beyond the scores themselves.