1. Conduid
  2. Developer Tools
  3. io.github.ezumba/vanguard-memory-node
MCP server · Developer Tools

io.github.ezumba/vanguard-memory-node

by · github.com/ezumba/vanguard-memory-node

Local deterministic BM25 memory for AI agents. Offline-first, no API key, SHA-256 shards, stdio.

Unclaimed devtools
InstallView source
37Low

Scored a month ago · breakdown

About io.github.ezumba/vanguard-memory-node

io.github.ezumba/vanguard-memory-node is an MCP server published by ezumba in the Developer Tools category: local deterministic BM25 memory for AI agents. Offline-first, no API key, SHA-256 shards, stdio.

Recent commit activity is the strongest signal that reported issues will get attention.

Install

Claude Code
claude mcp add io-github-ezumba-vanguard-memory-node -- npx -y @lnes/vanguard-memory-node
npx
npx -y @lnes/vanguard-memory-node

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.

Tools (11)

vmn_deleteDelete a memory object from the local vault by its SHA-256 root hash. This is permanent.

Parameters not published.

vmn_index_statusReturn the current status of the BM25 inverted index. Indicates if a rebuild is needed.

Parameters not published.

vmn_ingestIngest text into the local Vanguard Memory Vault. Returns a SHA-256 shard hash.

Parameters not published.

vmn_ingest_fileIngest new content from a file into the vault, tracking progress with a cursor so only new lines are ingested on each call. Safe to call repeatedly — only the delta since the last call is stored.

Parameters not published.

vmn_inspectInspect the catalog metadata for a specific memory shard by its SHA-256 root hash.

Parameters not published.

vmn_listList all memory objects in the local vault. Optionally filter by namespace.

Parameters not published.

vmn_rebuild_indexRebuild the BM25 inverted index from existing vault objects. Safe to run at any time — objects are never modified.

Parameters not published.

vmn_recallRecall evidence from a local Vanguard Memory shard using deterministic xLMP lexical search.

Parameters not published.

vmn_searchSearch across all memory objects in the vault by keyword query. Returns candidate roots. Use vmn_recall with a specific root to retrieve full evidence.

Parameters not published.

vmn_statsReturn statistics about the local Vanguard Memory Vault.

Parameters not published.

vmn_sync_vaultSync a local memory object to the ExergyNet LNES-17 vault. Requires EXERGYNET_API_KEY env var.

Parameters not published.

Ask AI

✦

Ask AI about io.github.ezumba/vanguard-memory-node

Powered by Claude · Grounded in docs

I know everything about io.github.ezumba/vanguard-memory-node. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About io.github.ezumba/vanguard-memory-node

How do I install io.github.ezumba/vanguard-memory-node?

Run claude mcp add io-github-ezumba-vanguard-memory-node -- npx -y @lnes/vanguard-memory-node, then add the server to your MCP client's configuration.

Is io.github.ezumba/vanguard-memory-node safe to use with an AI agent?

Its trust score is 37 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 io.github.ezumba/vanguard-memory-node still maintained?

Yes — the last commit was a month ago. The repository has 0 stars and 0 forks.