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

@memongo/pi-extension

v2.1.1

Published

Pi coding-agent extension — exposes Memongo's durable, cross-project, MongoDB-backed semantic memory as additive tools alongside pi-hermes-memory.

Readme

@memongo/pi-extension

Memongo durable memory for the Pi coding agent.

Additive — sits alongside pi-hermes-memory (local SQLite FTS5) and exposes Memongo's hybrid vector + full-text + graph retrieval as new tools. Does not replace any existing Pi memory tool.

Tools

| Tool | Purpose | |------|---------| | memongo_search | Semantic / cross-project / cross-session search over durable memory (hybrid vector + text + graph) | | memongo_save | Persist a durable structured fact / decision / preference / instruction to Memongo | | memongo_status | Probe Memongo API health + vector search availability | | /memongo | Slash command — quick status check |

Quick start

1. Run Memongo locally

cd /Users/rom.iluz/Dev/memongo

# Start MongoDB (Atlas Local Preview — includes mongod + mongot + Atlas Search + auto-embed)
docker compose -f docker/docker-compose.yml up -d

# Start the HTTP API
cd apps/api && bun run dev

Get a Voyage AI API key (free tier, al-... prefix) and export it:

export VOYAGE_API_KEY="al-..."

2. Wire into Pi

Add to ~/.pi/agent/settings.json:

{
  "packages": [
    "/Users/rom.iluz/Dev/memongo/packages/pi-extension"
  ]
}

Set env vars (in shell or .envrc):

export MEMONGO_API_URL="http://127.0.0.1:3847"
export MEMONGO_API_KEY="local-dev-secret"
export MEMONGO_AGENT_ID="pi-agent"

3. Reload and verify

/reload
/memongo

You should see Memongo @ http://127.0.0.1:3847 with vector status. Then try:

  • memongo_status — confirms API + vector search are live
  • memongo_search with a query — semantic recall across projects
  • memongo_save — persist a durable fact

Architecture

Pi Agent
  ├── pi-hermes-memory (local FTS5)       ← stays
  ├── pi-observational-memory             ← stays
  └── @memongo/pi-extension (this)        ← additive
        └── @memongo/client → HTTP API (port 3847) → MongoDB (Docker)

Config

| Env var | Default | Purpose | |---------|---------|---------| | MEMONGO_API_URL | http://127.0.0.1:3847 | Memongo HTTP API base URL | | MEMONGO_API_KEY | (none) | Bearer token (optional for local dev) | | MEMONGO_AGENT_ID | pi-agent | Agent identity for scoping | | VOYAGE_API_KEY | (none) | Required for vector/semantic search (Atlas Model API key) |

Graceful degradation

If the Memongo API is down, all three tools return clean error messages instead of crashing. The agent is instructed to fall back to memory_search (local FTS5). Nothing breaks.

License

Apache-2.0