MemPalace vs Supermemory
Two of the top projects in Memory, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
MemPalace
Local verbatim memory store for AI agents with semantic search and MCP
Supermemory
Memory and context engine for AI agents, with user profiles and hybrid search
Verdict
MemPalace ranks higher, 90 to 89. Of the 4 score parts we measure for both, MemPalace leads on 1, Supermemory on 1 and 2 are even.
- AdoptionMemPalace leads by 14 points, 93 to 79.
- FreshnessEven at 100.
- MaintenanceSupermemory leads by 11 points, 94 to 83.
- Agent-readyEven at 70.
Pick MemPalace if you are
Developers giving coding agents persistent, local long-term memory
- Stores original text verbatim; raw mode needs no LLM or API key
- Pluggable backends: Chroma, SQLite exact, Rust exact, Milvus, Qdrant, pgvector
Pick Supermemory if you are
Developers adding long-term memory to agents, apps and AI coding tools
- Hybrid search returns RAG documents and user memories in a single query
- Handles knowledge updates and contradictions, and auto-forgets expired facts
| What we compare | MemPalace | Supermemory |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 93, widely used | 79, popular |
| Freshness | 100, active | 100, active |
| Maintenance | 83, healthy | 94, healthy |
| Agent-ready | 70, partly | 70, partly |
| Facts from GitHub and the README | ||
| Stars | 60.5k | 31.6k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Nov 2026 | Nov 2026 |
| Last release | Nov 2026 | Oct 2026 |
| Language | Python | TypeScript |
| Docker | Yes | No |
| GPU | Optional | Optional |
| arm64 or Apple Silicon | Mentioned | Mentioned |
MemPalace
MemPalace stores conversation history and project files as verbatim text, without summarizing, and retrieves it by semantic search scoped into wings (people, projects), rooms (topics) and drawers (original content). It defaults to ChromaDB with a pluggable backend interface, and exposes 47 MCP tools plus a SQLite temporal knowledge graph. The README reports 96.6% R@5 on LongMemEval in raw mode with no LLM.
Who it is for: Developers giving coding agents persistent, local long-term memory
Strengths
- Stores original text verbatim; raw mode needs no LLM or API key
- Pluggable backends: Chroma, SQLite exact, Rust exact, Milvus, Qdrant, pgvector
- Benchmarks reproducible from the repo with committed per-question results
- Auto-save hooks for Claude Code, Codex CLI and Cursor; 47 MCP tools
Weaknesses
- Native Termux install unsupported; Android needs a Debian PRoot container
- Claude Code sessions expire in 30 days unless auto-save hooks are wired
- First embedding call downloads a model of about 80-300 MB
- GPU optional
- Docker + Compose
- Needs Python 3.10+, ChromaDB (default), Milvus (optional), Qdrant (optional), Postgres pgvector (optional)
- Models: minilm, embeddinggemma, OpenAI-compatible embeddings endpoints
Supermemory
Supermemory extracts facts from conversations, tracks updates and contradictions, expires stale information, and returns a per-user profile plus relevant memories through one API. It also covers RAG, connectors (Google Drive, Gmail, Notion, OneDrive, GitHub) and file extraction. It can be used via the hosted API, an MCP server and editor plugins, or a local server on port 6767.
Who it is for: Developers adding long-term memory to agents, apps and AI coding tools
Strengths
- Hybrid search returns RAG documents and user memories in a single query
- Handles knowledge updates and contradictions, and auto-forgets expired facts
- Local server keeps data in ~/.supermemory and can use Ollama with local embeddings
- Plugins for Claude Code, Cursor, Codex, OpenCode, plus Vercel AI SDK, LangChain, Mastra wrappers
Weaknesses
- Benchmark #1 claims are self-reported in the README, with details on a separate research page
- Hosted MCP server and plugins point at supermemory.ai cloud by default
- Local mode URL ingestion depends on a hosted reader service
- Local-versus-Enterprise feature differences are only documented on a separate page
- GPU optional
- Needs LLM provider (OpenAI, Anthropic, Gemini, Groq, or Ollama), Docker (optional)
- Models: OpenAI, Anthropic, Gemini, Groq, Ollama
- port 6767
More in Memory
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.