memU (NevaMind) alternatives

Lightweight agent memory system that builds a shared, file-like 'memory wiki' across sessions, agents and devices and can extract reusable skills from agent history; also offered as a hosted service (memu.pro). #9 on GitHub agent-memory topic Full memU (NevaMind) record →

  1. 1 Hindsight (Vectorize) Dedicated memory layers

    also in Dedicated memory layers · same storage (vector) · same retrieval (similarity) · also open source · also self-hostable

    OSS ✓ Self-host ✓ Managed ✓ MCP ✓ ★ 45k released 2026-10-21 MIT Compare with memU (NevaMind) →

  2. 2 Aleph Alpha PhariaAI / PhariaCatch Dedicated memory layers

    also in Dedicated memory layers · same storage (file, vector) · same retrieval (similarity) · same memory unit (document) · also self-hostable

    OSS ? Self-host ✓ Managed ✓ MCP ? Compare with memU (NevaMind) →

  3. 3 Supermemory Dedicated memory layers

    also in Dedicated memory layers · same storage (vector) · same retrieval (similarity) · same memory unit (document) · also open source · also self-hostable

    OSS ✓ Self-host ✓ Managed ✓ MCP ✓ ★ 31k released 2026-10-12 MIT Compare with memU (NevaMind) →

  4. 4 Letta / MemGPT Dedicated memory layers

    also in Dedicated memory layers · same storage (vector) · same retrieval (similarity, agentic) · also open source · also self-hostable

    OSS ✓ Self-host ✓ Managed ✓ MCP ✓ ★ 3.7k released 2026-10-29 Apache-2.0 Compare with memU (NevaMind) →

  5. 5 REALM Retrieval-as-memory hybrids ⚠ research-code — research code; not maintained as a product

    same storage (vector) · same retrieval (similarity) · same memory unit (document) · also open source

    OSS ✓ Self-host ? Managed ? MCP ? ★ 1.8k Apache-2.0 Compare with memU (NevaMind) →

  6. 6 AutoGLM (Zhipu AI) Dedicated memory layers

    also in Dedicated memory layers · same storage (file, vector) · same retrieval (similarity) · also open source · also self-hostable

    OSS ✓ Self-host ✓ Managed ✓ MCP ? ★ 26k Apache-2.0 Compare with memU (NevaMind) →

  7. 7 Pieces for Developers (LTM) Dedicated memory layers

    also in Dedicated memory layers · same storage (vector) · same retrieval (similarity) · also self-hostable

    OSS ? Self-host ✓ Managed ✓ MCP ✓ ★ 113 Compare with memU (NevaMind) →

  8. 8 Backboard Dedicated memory layers

    also in Dedicated memory layers · same storage (vector) · same retrieval (similarity) · also self-hostable

    OSS — Self-host ✓ Managed ✓ MCP ? ★ 18 Unlicensed Compare with memU (NevaMind) →

Ranked by shared memory design (storage, retrieval, conflict handling, memory unit), same section and shared must-haves (open source, self-hosting, MCP), with adoption as a tie-breaker. ✓ confirmed · — no · ? not in the catalog yet. Want picks for your own requirements? Use the chooser. Checking a whole project? Check your stack.