Mengram: AI Memory for Founders
Get human-like memory for AI agents with Mengram. For startup founders building AI-powered projects.
183 stars27 forksPythonQuality 8/10Updated 7/24/2026100% free ยท open source Mengram gives AI agents human-like memory, enabling them to learn from experiences, failures, and semantic, episodic, and procedural knowledge.
- โขYou're building an AI-powered chatbot that needs to remember user interactions and adapt to their preferences.
- โขYour AI model requires the ability to learn from failures and adjust its behavior based on experience.
- โขYou want to integrate human-like memory capabilities into your AI project using Python or JavaScript.
- 1Import the Mengram library in your Python script using `import mengram`.
- 2Create a new Mengram instance with `mengram = Mengram()` to start building your AI agent's memory.
- 3Use the `mengram.learn()` method to teach your AI agent new knowledge and experiences, such as `mengram.learn(episodic_memory='user_interactions')`.
- 4Integrate Mengram with other AI frameworks like LangChain, CrewAI, or OpenClaw using their respective SDKs and APIs.
- 5Configure your Mengram instance to use the free API or set up your own server using the Mengram GitHub repository as a reference.
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
Topics
agent-memory
ai-agents
ai-memory
claude-desktop
cognitive-architecture
cohere
cursor-ai
episodic-memory
knowledge-graph
letta-alternative
llm-memory
mcp-server
mem0-alternative
model-context-protocol
multilingual-embeddings
pgvector
procedural-memory
python
rag
semantic-search