Instinct

io.github.yakuphanyclPublished by GitHub account yakuphanyclv1.0.0Updated Oct 24, 2026

Self-learning memory for AI coding agents with pattern detection and confidence scoring.

VerifiedSTDIODesktop onlyKnowledge & MemoryAI & ML

Overview

AI-generated overview

Self-learning memory for AI coding assistants, with pattern detection and confidence scoring.

What you can do
Gives an AI coding assistant a self-learning memory that it can draw on in later sessions. Per the description, it detects patterns and assigns confidence scores to memory entries so the assistant can judge how much to rely on them. Beyond that, the input lists no tools, instructions or README, so the actual operations and what gets remembered cannot be confirmed.
When to use it
Worth adding when you want a coding assistant to carry learned patterns across sessions and weigh them by confidence. Best suited to developers who use the same assistant over time and want accumulated experience instead of restating preferences each time.
Requirements
Runs as a local process over stdio; requires the PyPI package instinct-mcp and a Python runtime. Desktop only, not executable on the web. No authentication, environment variables or headers are declared.
Before you install
The server stores and accumulates assistant memories, which may include code snippets, project details or conversation content; check where they are kept and how to clear them before installing. The input does not say whether data leaves the machine, and with no tool list the write and delete behaviour cannot be confirmed.

Installation

In SourceWeft

  1. Open Instinct in the dashboard and add it to a workspace.
  2. 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

This repository has no README.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

25% 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

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.