MemPalace.Mcp
Model Context Protocol (MCP) server for MemPalace.NET exposing memory operations as MCP tools.
Ask AI about MemPalace.Mcp
Powered by Claude Β· Grounded in docs
I know everything about MemPalace.Mcp. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
MemPalace.NET
A .NET port of MemPalace β local-first AI memory that stores everything verbatim, searches semantically, and organizes knowledge through a wings / rooms / drawers hierarchy. No cloud calls by default, powered by ONNX embeddings.
π― Status: v0.15.1 β Production-ready with advanced E2E testing, comprehensive journey guides, and skill pattern library.
Why MemPalace.NET?
- Local-first by default β ONNX embeddings via ElBruno.LocalEmbeddings (no API keys, no cloud calls)
- Microsoft.Extensions.AI β swap embedders and LLMs with zero lock-in
- Microsoft Agent Framework β each agent gets its own memory diary
- MCP server β expose your palace as Model Context Protocol tools (Claude Desktop, VS Code, etc.)
- Temporal knowledge graph β track entity relationships with validity windows
- SQLite backend β managed BLOB storage, cosine similarity, clear upgrade path to vector stores
Examples & Getting Started
Ready to dive in? Check out our runnable examples:
- π° Simple Memory Agent β Core memory operations with semantic search
- πΈοΈ Semantic Knowledge Graph β Temporal entity relationships
See examples/README.md for detailed walkthroughs and learning paths.
Quick Start
# Install the CLI tool
dotnet tool install -g mempalacenet --version 0.15.1
# Initialize a new palace
mempalacenet init ~/my-palace
# Mine project files
mempalacenet mine ~/my-code --wing work --mode files
# Mine conversation transcripts
mempalacenet mine ~/my-convos --wing personal --mode convos
# Semantic search
mempalacenet search "how do I handle auth errors?"
# Hybrid search with reranking
mempalacenet search "latest React patterns" --hybrid --rerank
# Start MCP server (for Claude Desktop, VS Code, etc.)
mempalacenet mcp --palace ~/my-palace
# Run an agent
mempalacenet agents run scribe --wing research --mode local
Architecture
MemPalace.NET is a modular .NET solution with clear separation of concerns:
| Project | Purpose |
|---|---|
| MemPalace.Core | Domain types, storage interfaces, PalaceRef value object |
| MemPalace.Backends.Sqlite | Default SQLite backend with BLOB vectors + cosine similarity |
| MemPalace.Ai | M.E.AI integration with ONNX (default), Ollama, OpenAI support |
| MemPalace.Mining | Content ingestion: filesystem miner + conversation transcript miner |
| MemPalace.Search | Semantic, keyword, and hybrid search with optional LLM reranking |
| MemPalace.KnowledgeGraph | Temporal entity-relationship graph with validity windows |
| MemPalace.Mcp | Model Context Protocol server (7 tools in v0.1) |
| MemPalace.Agents | Microsoft Agent Framework integration + per-agent diaries |
| MemPalace.Cli | Spectre.Console CLI (mempalacenet command) |
| MemPalace.Benchmarks | LongMemEval / LoCoMo / ConvoMem benchmarks + R@5 testing |
Documentation
Full documentation lives in docs/:
- Architecture β solution layout, component contracts, dependency graph
- Concepts β wings, rooms, drawers, verbatim storage, embedder identity
- Backends β writing custom backends, conformance tests
- AI Integration β embedder selection, reranking, M.E.AI seams
- Mining β ingestion pipeline, custom miners, .gitignore respect
- Search β semantic vs hybrid strategies, RRF fusion, temporal boosting
- Knowledge Graph β temporal triples, pattern queries, invalidation
- MCP Server β tool reference, VS Code / Claude Desktop setup
- Agents β Agent Framework integration, diary management, agent discovery
- CLI β command reference, configuration, examples
- Benchmarks β reproducibility, dataset sources, R@5 parity
- GitHub Copilot Skill β integration guide, pattern library, code generation hints
Building Custom Integrations
Integrating MemPalace.NET into your .NET projects? Start with our developer guides:
- C# Library Developer Guide β Build applications on MemPalace.NET
- Embedder Pluggability Guide β Swap or implement custom embedders
- Skill Integration Deep Dive β Extend the platform with reusable skills
Development
# Clone
git clone https://github.com/elbruno/mempalacenet
cd mempalacenet
# Build
dotnet build src/
# Test (129 tests, all green)
dotnet test src/
# Pack NuGet packages
dotnet pack src/ -c Release
Roadmap
v0.1.0 (current) ships core memory operations, search, MCP server, and agents.
Post-v0.1:
- Upgrade to sqlite-vec or Qdrant for >100K vectors
- BM25 keyword search (currently token overlap)
- LongMemEval R@5 parity validation (target β₯ 91%)
- Conversation context summaries (
mempalace wake-up)
Credits
- Original project: MemPalace (Python)
- Default embedder: ElBruno.LocalEmbeddings (ONNX)
License
MIT β same spirit as the original MemPalace.
π About the Author
Made with β€οΈ by Bruno Capuano (ElBruno)
- π Blog: elbruno.com
- πΊ YouTube: youtube.com/elbruno
- π LinkedIn: linkedin.com/in/elbruno
- π Twitter: twitter.com/elbruno
- ποΈ Podcast: notienenombre.com
Community
We welcome contributions from the community! Here's how to get involved:
- Contributing Guidelines β how to submit pull requests, report issues, and contribute code
- Code of Conduct β our commitment to fostering an open and welcoming environment
- Security Policy β how to report security vulnerabilities responsibly
- Issues β report bugs or request features
- Discussions β ask questions, share ideas, and connect with the community
Got questions? Open a discussion or reach out to @elbruno.
