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

rememori-mcp

v0.3.0

Published

MCP server for rememori — persistent semantic memory for Claude Code and any MCP-capable agent.

Readme

rememori-mcp

Persistent semantic memory for Claude Code — and any MCP-capable agent — backed by rememori.

Your agent remembers across sessions: facts, decisions, preferences. Stored in one local file, searched semantically, never leaves your machine (with a local embedder).

Setup

With Ollama running locally (default):

ollama pull nomic-embed-text
claude mcp add rememori -- npx -y rememori-mcp

That's it. Claude Code now has the full memory toolset — see Tools below.

Configuration

| Variable | Default | Purpose | |---|---|---| | REMEMORI_PATH | ~/.rememori/memory.mem | Where memories live | | REMEMORI_EMBEDDER | ollama | ollama or openai | | OLLAMA_MODEL | nomic-embed-text | Local embedding model | | OLLAMA_URL | http://localhost:11434 | Ollama endpoint | | OPENAI_API_KEY | — | Required for openai | | OPENAI_MODEL | text-embedding-3-small | | | OPENAI_BASE_URL | https://api.openai.com/v1 | Any OpenAI-compatible endpoint | | REMEMORI_MIN_SIMILARITY | 0.5 | Relevance floor: off-topic recalls return nothing instead of noise (0.5 measured for nomic; lower it if recalls come back empty too often) |

Example with an OpenAI-compatible endpoint:

claude mcp add rememori -e REMEMORI_EMBEDDER=openai -e OPENAI_API_KEY=sk-... -- npx -y rememori-mcp

Tools

  • remember(text, tags?, importance?) — store a memory
  • recall(query, limit?, halfLifeDays?, tags?) — semantic search with entity-graph bonus and optional time decay
  • reinforce(id) — mark a memory as actually used: resets its decay clock, hardens its ranking (log-damped)
  • reinforce_from_output(ids, output) — evidence-gated version: only memories verifiably quoted/used in the answer get reinforced (preferred)
  • demote(id) — negative feedback for used-and-wrong memories or contradiction losers
  • collisions(id, threshold?, limit?) — near-duplicates of a memory; the agent judges duplicate vs update vs contradiction, then demotes/forgets the loser
  • get(id) — read one memory with its reinforcement state
  • forget(id) — delete
  • entities(name?, limit?) — explore the memory↔entity graph

License

MIT