npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@soa-harness/memory-mcp-mem0

v1.3.3

Published

mem0-backed Memory MCP implementing the SOA-Harness §8.1 6-tool protocol. Qdrant vector store + OpenAI or local Ollama LLM/embedder.

Readme

@soa-harness/memory-mcp-mem0

mem0-backed Memory MCP implementing the SOA-Harness §8.1 six-tool protocol. Qdrant vector store + OpenAI or local Ollama for LLM/embeddings. Passes the SV-MEM-01/02/07/08 + STATE-01/02 conformance probes against a real Runner.

Install

npm install @soa-harness/memory-mcp-mem0

Run

The package needs a running Qdrant instance (default :6333) and an LLM + embedder provider. Ollama is the zero-egress default; OpenAI is supported via OPENAI_API_KEY.

Quickest path (docker-compose, Ollama-on-host)

docker compose -f node_modules/@soa-harness/memory-mcp-mem0/docker-compose.yml up -d
ollama pull llama3.1
ollama pull nomic-embed-text
npx soa-memory-mcp-mem0

Env surface

| Var | Default | Meaning | |---|---|---| | PORT | 8006 | HTTP port | | HOST | 127.0.0.1 | bind host (loopback-only by default) | | OLLAMA_URL | http://localhost:11434 | Ollama endpoint | | QDRANT_URL | http://localhost:6333 | Qdrant endpoint | | SOA_MEMORY_MCP_MEM0_PROVIDER | ollama | ollama or openai | | OPENAI_API_KEY | — | required when SOA_MEMORY_MCP_MEM0_PROVIDER=openai | | SOA_MEMORY_MCP_MEM0_COLLECTION | soa_mem0_notes | Qdrant collection name | | SOA_MEMORY_MCP_MEM0_TIMEOUT_AFTER_N_CALLS | — | fault-injection; after N successful calls, hang forever | | SOA_MEMORY_MCP_MEM0_RETURN_ERROR | — | fault-injection; named tool returns {error:"mock-error"} | | SOA_MEMORY_MCP_MEM0_SEED | — | optional corpus seed path |

Endpoints (§8.1 six tools)

POST /search_memories          { query, limit?, sharing_scope? }            → { hits }
POST /search_memories_by_time  { start, end, limit? }                       → { hits, truncated }
POST /add_memory_note          { summary, data_class, session_id, note_id?, tags?, importance? } → { note_id, created_at }
POST /read_memory_note         { id }                                       → { id, note, tags, importance, created_at, graph_edges } | { error:"MemoryNotFound", id }
POST /consolidate_memories     { consolidation_threshold? }                 → { consolidated_count, pending_count }
POST /delete_memory_note       { id, reason? }                              → { deleted, tombstone_id, deleted_at } (idempotent on id)
GET  /health                                                                → { status:"alive" }

Sensitive-personal filter (§10.7.2 + §8.1 L-58)

Requests with data_class="sensitive-personal" are rejected before any bytes reach the mem0 LLM call and return {error:"MemoryDeletionForbidden", reason:"sensitive-class-forbidden"}. This prevents sensitive-personal inputs from being embedded, summarized, or indexed by the downstream LLM.

Wire compatibility

Wire shapes match @soa-harness/[email protected] byte-for-byte. A Runner configured with SOA_RUNNER_MEMORY_MCP_ENDPOINT pointing at either backend accepts traffic identically.