AgentIndex icon
AgentIndex
cuba-memorys logo
cuba-memorys
★ 30
vs
pensyve logo
pensyve
★ 97

cuba-memorys vs pensyve

cuba-memorys: Cuba-Memorys is a Model Context Protocol (MCP) server that gives AI coding assistants long-term persistent memory. It uses a knowledge graph, neuroscience-inspired algorithms like FSRS-6 adaptive decay, Hebbian learning, and dual-strength memory, along with anti-hallucination grounding. The latest version 2.0.0 is a complete Rust rewrite with 12 tools and sub-millisecond performance.; pensyve: Pensyve is a universal memory runtime for AI agents that eliminates amnesia across sessions. It offers three memory types (episodic, semantic, procedural), 8-signal fusion retrieval, and FSRS-based forgetting curve. Framework-agnostic with SDKs for Python, TypeScript, Go, and integrations with LangChain, CrewAI, AutoGen, plus native plugins for Claude Code, Cursor, and VS Code.

01

TL;DR

cuba-memorys logo
cuba-memorysRAG / Knowledge Base · ★ 30

Persistent learning from project context: store and retrieve entities, observations, and relations

Read cuba-memorys full review →
pensyve logo
pensyveRAG / Knowledge Base · ★ 97

Persist agent knowledge across sessions and avoid repetitive questions

Read pensyve full review →
02

Side-by-Side Comparison

Field
cuba-memorys logocuba-memorys
pensyve logopensyve
Category
RAG / Knowledge Base
RAG / Knowledge Base
Stars
★ 30
★ 97
License
NOASSERTION
NOASSERTION
Install Command
git clone https://github.com/LeandroPG19/cuba-memorys.git && cd cuba-memorys && docker compose up -d && cd rust && cargo build --release
pip install pensyve
Updated
2d ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
ai-memory, ai-tools, anti-hallucination
agent-memory, ai, ai-agents
03

Features

cuba-memorys logocuba-memorys
01Knowledge graph with typed relations and Leiden community detection
02FSRS-6 adaptive spaced repetition and Hebbian/BCM metaplasticity
034-signal entropy-routed RRF fusion search (TF-IDF, pg_trgm, full-text, pgvector HNSW)
04Anti-hallucination verification with graduated confidence scoring
05REM Sleep autonomous consolidation and dual-strength memory model
pensyve logopensyve
01Three memory types: episodic, semantic, procedural
028-signal fusion retrieval (vector, BM25, graph, intent, recency, frequency, confidence, type boost)
03FSRS forgetting curve with reinforcement for natural decay
04Offline-first with SQLite and ONNX embeddings, no cloud required
05Framework-agnostic with SDKs for Python, TypeScript, Go, and MCP
04

Use Cases

cuba-memorys logocuba-memorys
↳Persistent learning from project context: store and retrieve entities, observations, and relations
↳Error memory: record and detect repeated mistakes, preventing re-occurrence
↳Anti-hallucination grounding: verify agent claims against stored knowledge before responding
pensyve logopensyve
↳Persist agent knowledge across sessions and avoid repetitive questions
↳Integrate memory into any AI framework (LangChain, CrewAI, AutoGen) via adapters
↳Enable agents to learn effective strategies through procedural memory
FAQ

FAQ

What is the difference between cuba-memorys and pensyve?
Both cuba-memorys and pensyve are in the RAG / Knowledge Base category. cuba-memorys has 30 stars, while pensyve has 97 stars.
Which is better, cuba-memorys or pensyve?
The best choice depends on your use case. Choose cuba-memorys if Persistent learning from project context: store and retrieve entities, observations, and relations, and pensyve if Persist agent knowledge across sessions and avoid repetitive questions.
Is cuba-memorys free or open source?
Yes, cuba-memorys is open source on GitHub (NOASSERTION).
Is pensyve free or open source?
Yes, pensyve is open source on GitHub (NOASSERTION).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to cuba-memorys →Alternatives to pensyve →cuba-memorys details →pensyve details →