workflowstacks
mcp-server

mengram: Human‑like Memory for Your AI Agents

Equip your AI agents with semantic, episodic and procedural memory that learns from failures. Ideal for founders building intelligent, context‑aware applications.

From the repo · “Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain, CrewAI & OpenClaw integrations.”

204 stars35 forksPythonGuide quality 9/10 · reviewed Oct 22Updated 9/16/2026100% free · open source
What it does

Mengram gives AI agents human-like memory, enabling them to learn from experiences, failures, and semantic, episodic, and procedural knowledge.

When to use it
  • •You're building an AI-powered chatbot that needs to remember user interactions and adapt to their preferences.
  • •Your AI model requires the ability to learn from failures and adjust its behavior based on experience.
  • •You want to integrate human-like memory capabilities into your AI project using Python or JavaScript.
Ready-to-paste prompt
mengram.learn(episodic_memory='user_purchases', semantic_memory='product_recommendations', procedural_memory='order_fulfillment')
Heads up: Before using Mengram, ensure you have Python 3.7 or later installed, as the library is not compatible with earlier Python versions.
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/mengram && curl -fsSL https://workflowstacks.com/api/skills/mengram/claude-skill -o ~/.claude/skills/mengram/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How mengram: Human‑like Memory for Your AI Agents works
Codeflow
Free to inspect

Mengram: Human‑like Memory for Your AI Agents is a large Python project (~48k lines across 151 code files, plus 57 test files). You install it into your AI tool with one command; there is nothing to run yourself. Last commit a month ago, Apache-2.0 license, has a test suite.

Size
Large codebase
~48k lines · 151 code files · ~7 h to skim
Setup
Install as a skill / plugin
Add it to Claude Code (or your AI tool) with one command — 2 skills inside. Nothing to run yourself.
Runs on
Inside your AI tool
Helper scripts use Python · Docker
Python 72%HTML 22%JavaScript 2%TypeScript 2%Shell 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    cli.py
    Where the program starts running
  3. 3
    examples/README.md
    A worked example — copy this to get going
What's in each folder
integrations/Sub-packages / plugins23 files
api/Backend / API5 files
examples/Examples you can copy22 files
cloud/Folder69 files
vscode-mengram/Folder20 files
engine/Folder17 files
sdk/SDKs / client libraries16 files
experiments/Research & notebooks14 files
READMEHas testsDocumentedDocker readyExamples includedApache-2.0 licenseUpdated 1 mo ago
Quick Actions
Details
Creator
alibaizhanov
Language
Python
Category
mcp-server
Published
2/10/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/mengram.svg)](https://workflowstacks.com/skills/mengram?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

Memory (knowledge graph) MCP config

Persistent memory across chats via a local knowledge graph.

MCP config

GitHub MCP config

Search repos, read code, open issues and PRs from Claude.

MCP config

Brave Search MCP config

Give Claude live web search via the Brave Search API.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 368,155
Rea: Reverse Engineer Apps
Inspect apps down to binary level with Rea. For founders needing code clarity.
mcp-server★ 156,480
open-webui: Self‑hosted AI Chat UI for Faster LLM Integration
Launch a sleek, web‑based AI interface that works with Ollama, OpenAI API, and more—ideal for founders needing a quick, customizable LLM front‑end. 153k+ GitHub stars.
mcp-server★ 133,178
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
mcp-server★ 107,521
gemini-cli: Supercharge Your Terminal with Gemini AI
Leverage the Gemini AI directly from your command line to accelerate decision‑making and prototyping. Ideal for tech founders who need instant, code‑native insights.
mcp-server★ 214
nosia: Self‑hosted AI RAG & MCP platform for founders
Deploy a unified AI retrieval‑augmented generation and MCP stack on your own servers—ideal for startups needing secure, customizable data pipelines.
mcp-server★ 105
apra-fleet: Automate coding
Get AI agents that write and review code for your startup. For founders needing automation.