MemOS vs MemPalace

MemOS

Agents

MemPalace

Agents

Tagline

MemOS

—

MemPalace

Open-source, local-first AI memory system for LLM agents

Pricing

MemOS

Freemium· Free tier

MemPalace

Free· Free and open-source under the MIT license. No paid tiers; self-hosted with zero API costs once installed.

Free trial

MemOS

Yes

MemPalace

Not listed

API

MemOS

Yes

MemPalace

Yes

Platforms

MemOS

windowsmacoslinux

MemPalace

—

Open source

MemOS

Yes · Apache-2.0

MemPalace

Yes

GitHub stars

MemOS

12,162

checked 2026-10-29

MemPalace

—

Last GitHub push

MemOS

2026-10-29

MemPalace

—

First commit

MemOS

2025-07

MemPalace

—

Hacker News stories

MemOS

0

checked 2026-10-16

MemPalace

0

checked 2026-10-16

Earliest Wayback capture

MemOS

2025-07-07

earliest archived capture of the site, not a launch date

MemPalace

2026-04-14

earliest archived capture of the site, not a launch date

Company

MemOS

MemTensor

MemPalace

—

Model used

MemOS

Multi-model

MemPalace

Embedding backends: embedding-gemma-300m (multilingual) or all-MiniLM-L6-v2 (English). No LLM required for retrieval.

Best for

MemOS

—

MemPalace

Engineers and AI researchers building agents that need persistent, high-fidelity memory without cloud dependencies or per-token API costs, especially teams already using MCP-compatible clients like Claude Code, Cursor, or Codex CLI.

Not for

MemOS

—

MemPalace

Non-technical users who want a plug-and-play hosted chat-memory service, or teams that need a managed cloud SLA rather than a self-hosted Python package.

Editorial score

MemOS

6.9 / 10

MemPalace

—

Use cases

MemOS

AI assistants with consistent, context-rich conversationsCustomer support that recalls past tickets and user historyPersonalized agents that adapt to individual preferencesMulti-agent collaboration with shared or isolated memoryIntelligent application ecosystems

MemPalace

Persistent memory for Claude Code and Cursor sessionsPer-agent memory isolation in multi-agent systemsMCP-exposed knowledge store for custom LLM toolsLocal RAG over long conversation historiesTemporal knowledge graph for entity-relationship trackingPrivacy-sensitive conversation logging without cloud APIsCodex CLI auto-save memory hooksResearch assistant diaries with scoped retrieval

Pros

MemOS

• Open-source core available under the Apache 2.0 License.
• Structured memory architecture with dynamic retrieval and updates.
• Cross-model and cross-device memory sharing via MIP.
• Flexible deployment options including public cloud, private cloud, on-premises, and hybrid.
• Scalable memory infrastructure designed for high availability.

MemPalace

• Local-first: nothing leaves your machine unless you opt in, so no API bills or data-egress questions
• Verbatim storage avoids the fidelity loss common in summarization-based memory systems
• Structured wings/rooms/drawers layout enables scoped search rather than flat semantic lookup
• MCP server ships 36 tools and integrates with Claude Code, Codex CLI, and Cursor out of the box
• Pluggable vector backends (ChromaDB, SQLite, Milvus, Qdrant, pgvector) fit into most existing stacks
• Temporal knowledge graph with validity windows handles facts that change over time
• Strong reported benchmark: 96.6% R@5 raw on LongMemEval without any API calls

Cons

MemOS

—

MemPalace

• Requires a local Python 3.9+ toolchain to install cleanly (Docker mitigates this but adds its own overhead)
• Verbatim-only storage means no automatic compaction; long-running palaces will grow on disk
• Self-hosted only — no managed cloud option for teams that don't want to run infrastructure
• Small project with a narrow contributor base; support is community-driven via GitHub issues
• Non-technical users will find the MCP/CLI-first UX unfamiliar compared to hosted chat memory products

Website

MemOS

memos.openmem.net

MemPalace

mempalaceofficial.com

Editorial score: rule-based, 0–10, from AI-assisted profile inputs (see /methodology) — not a user rating; “—” means unscored. “Not listed” means we have no record of it, not that it is absent. GitHub figures and prices carry the date they were checked or captured; prices are shown as published, unconverted.