1. Conduid
  2. RAG
  3. Nram
MCP server · RAG

Nram

Self-hosted long-term memory substrate for any LLM-using tool. Hybrid vector + lexical recall with MMR reranking, auto-extracted knowledge graph, sleep-style consolidation, per-project tuning, MCP server, REST + OAuth 2.0, embedded React admin UI. SQLite or Postgres + pgvector or Qdrant. Pluggable providers (OpenAI, Anthropic, Gemini, Ollama).

34Low

Scored 4 months ago · breakdown

About Nram

Nram is an MCP server in the RAG category: self-hosted long-term memory substrate for any LLM-using tool. Hybrid vector + lexical recall with MMR reranking, auto-extracted knowledge graph, sleep-style consolidation, per-project tuning, MCP server, REST + OAuth 2.0, embedded React admin UI. SQLite or Postgres + pgvector or Qdrant. Pluggable providers (OpenAI, Anthropic, Gemini, Ollama).

Install

From source
git clone https://github.com/nram-ai/nram

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Nram

Powered by Claude · Grounded in docs

I know everything about Nram. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About Nram

How do I install Nram?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Nram safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Nram still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.