A
licenseC
qualityC
maintenanceMCP server for sharing source-backed engineering memory across AI coding clients like Cursor and VS Code.
30
1
MIT
Memory-Facade
by morozsm
Provides a curated memory entry point for Hermes agent, enabling automatic bank/tag routing, URL ingestion into linked articles, session-to-documentation set conversion, and consistency tooling (deduplication/rerouting).
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Memory-Facadewhat do we know about the 2026 content baseline?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Memory-Facade
A thin, stateless MCP server that gives every coding agent (Claude Code, Codex, OpenCode, Hermes) one curated entry point to shared memory — automatic bank/tag routing, URL-ingest → linked article, session → documentation set, and consistency tooling (dedupe / reroute).
It orchestrates Hindsight (facts) and LightRAG (corpora). It does not reimplement storage and never creates banks.
See ~/Projects/common-memory/docs/memory-facade-architecture.md for the design
and the 2026-08-18 content baseline.
Run (stdio MCP server)
uv run python -m mf.serverDeployed as an MCP server in the msm-ai-gateway LiteLLM MCP runtime, routed as
/memory-facade/mcp (same pattern as lightrag in config/litellm.yaml).
Related MCP server: memex
Test
env -u PYTHONPATH uv run --extra dev pytest -qNote: on Sergey's host the shell exports a
PYTHONPATHpointing at the Hermes venv. Unset it (env -u PYTHONPATH …) before running here, otherwise the wrong pydantic/pydantic_core gets imported and collection fails.
Maintenance
–Maintainers
–Response time
0dRelease cycle
2Releases (12mo)
Commit activity
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityCmaintenanceCentralized agentic memory and MCP gateway for LLMs, enabling persistent memory recall, validation, and integration with upstream MCP servers.1Apache 2.0
- AlicenseAqualityCmaintenanceA local shared-memory MCP server for Claude, Codex, Hermes, and other MCP-aware agents, providing a durable memory layer with Markdown files and SQLite fact store.6MIT
- Alicense-qualityBmaintenanceA self-hosted server providing shared memory, RAG document search, project maps, and role-based prompts for all AI agents via MCP and REST, enabling persistent context across devices and tools.2MIT
Related MCP Connectors
Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/morozsm/memory-facade'
If you have feedback or need assistance with the MCP directory API, please join our Discord server