
BRICO feature memory
io.github.ScienceWerx-IncPublished by GitHub account ScienceWerx-Incv0.2.0Updated Oct 29, 2026
Find features you built in other projects, see how they fit this one, and reuse them.
The publisher's own server: Memory.fit
Overview
BRICO feature memory lets a coding agent find features you built in other projects, judge how well they fit the current one, and reuse them.
- What you can do
- Search your indexed projects for features you have already built
- Compare a found feature against the project you are working in and rate how well it fits
- Reuse or wire an existing feature into the current codebase through the coding agent
- Index a local project directory so its features become searchable memory
- When to use it
- Useful when you work across several codebases and want your coding agent to reuse code you already wrote instead of rebuilding it, or to check whether an existing feature fits a new project.
- Requirements
- Runs locally over stdio via the npm package bricowerx (Node.js, typically through npx). Needs a BRICO Builder invite token, supplied as the BRICO_TOKEN environment variable or stored by running the brico login command. Projects must be indexed first with the brico index command.
Installation
In SourceWeft
- Open BRICO feature memory in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
BRICO releases
Release binaries for BRICO: your feature memory. BRICO finds the features you've built in your other projects, tells you how well each fits the project you're in, and lets your coding agent wire it in.
This repository holds release downloads only. Docs: https://www.bricowerx.com
Install
Use it in your coding agent (MCP)
Cursor, in ~/.cursor/mcp.json:
Every release includes SHA256SUMS.txt; the installers verify downloads against it.
MCP registry
server.json is the server's MCP registry entry, io.github.ScienceWerx-Inc/brico. After each npm release, copy it from the source repository and run Actions → MCP registry → Run workflow.
Source: README.md at commit 7a124c5
Tools
0Version history
1- v0.2.0LatestOct 29, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Memory integrations

Memory.fit
fit.memoryOfficial publisher
Hosted Memory.fit server that lets an AI read your training, sleep, recovery and nutrition data and write back weekly plans, targets and meal plans.
pg.ddx.io: the PostgreSQL community's memory
io.ddx.pgOfficial publisher
pg.ddx.io: the PostgreSQL community's memory's hosted MCP server, published by pg.ddx.io; no sign-in required; Streamable HTTP; 29 tools.
var.gg Naming Memory
gg.varOfficial publisher
Remote MCP server that suggests and searches code identifier names from domain concepts in Korean, Japanese, Chinese, Vietnamese and English, and exposes ERD…

Counterparts
ai.counterparts
Local-first long-term memory for Claude Code and Claude Desktop: the assistant writes notes about you and your projects and recalls them in later sessions.

LAHZE - Persian AI Memory Platform
Published by GitHub account pedramgholizadeh
LAHZE - Persian AI Memory Platform's hosted MCP server; no sign-in required; Streamable HTTP; 13 tools.