Skip to main content

EngramDev

Your AI coding tool has amnesia. EngramDev gives it long-term memory.

EngramDev learns your coding patterns and serves them to AI tools like Claude Code and Cursor - so they stop regenerating what they already know.

Install

pip install engramdev

For the full MCP server + CLI, use the Node.js package:

npm install -g engramdev

Quick Start

from engramdev import PatternStore, classify

# Store patterns
store = PatternStore(".")
store.add_pattern({
    "type": "component",
    "name": "UserCard",
    "description": "React user profile card",
    "template": "export default function UserCard({ name }) { ... }",
    "tags": ["react", "component", "card"],
})

# Classify a task
patterns = store.get_all_patterns()
result = classify("Create a React card component", patterns, {"framework": "react"})
print(result["match"])       # "exact", "partial", or "none"
print(result["confidence"])  # 0.0 - 1.0

Full Documentation

See GitHub for full docs, MCP server setup, CLI usage, and plugin system.

License

MIT

Release files for engramdev-ai 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for engramdev-ai 0.1.0
File Size Uploaded
engramdev_ai-0.1.0.tar.gz 5.7 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for engramdev-ai 0.1.0
File Interpreter ABI Platform
engramdev_ai-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 12.1 kB

Release files / engramdev_ai-0.1.0.tar.gz

Download URL engramdev_ai-0.1.0.tar.gz
Size 5.7 kB
Tags Source
SHA-256 checksum
How to use checksums
9d83792ea93b922a352522819b8655aa978d13c645a6d2794aae036207ea3f34
BLAKE2b-256 checksum
How to use checksums
fdfeca9de7caf6ae3b19a87128591a68b80cb0a517e125dd143b543c2a873b6b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.3

Release files / engramdev_ai-0.1.0-py3-none-any.whl

Download URL engramdev_ai-0.1.0-py3-none-any.whl
Size 6.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
8317e302a39d8a274bc19981bc68ea516b37d3bec53e9d4ef5da02017cad05ae
BLAKE2b-256 checksum
How to use checksums
5e5073cf887fd40321db93e24f2ec4870348d5b27501144142cf6095077dae35
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.3

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page