AgentIndex icon
AgentIndex
engram-memory logo
engram-memory
★ 38
vs
Perenna logo
Perenna
★ 61

engram-memory vs Perenna

engram-memory: Engram Memory provides AI agents with persistent, self-hosted memory, eliminating session-end forgetfulness and API costs. It features a three-tiered recall engine for efficient storage, search, and retrieval of semantic embeddings on your own hardware.; Perenna: Perenna provides a lightweight, Git-backed permanent memory solution for various AI agents, enabling them to share durable memories without vendor lock-in. It stores human-readable Markdown in a Git repository and uses a local Vexor index for retrieval, ensuring memory persistence across different agents and machines.

01

TL;DR

engram-memory logo
engram-memoryMemory & Context · ★ 38

Providing long-term memory for AI agents (e.g., Claude Code, Cursor) to remember codebase details, user preferences, and architectural decisions across sessions.

Read engram-memory full review →
Perenna logo
PerennaMemory & Context · ★ 61

Sharing durable memories across different AI agents like Claude Code, Codex, ChatGPT, and Cursor.

Read Perenna full review →
02

Side-by-Side Comparison

Field
engram-memory logoengram-memory
Perenna logoPerenna
Category
Memory & Context
Memory & Context
Stars
★ 38
★ 61
License
NOASSERTION
MIT
Install Command
docker run -d --name engram-memory --restart unless-stopped -p 6333:6333 -p 11435:11435 -p 8585:8585 -v engram_data:/data engrammemory/engram-memory:latest
uv tool install perenna
Updated
4mo ago
1mo ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
AI Agent Memory, Self-hosted, Vector Database
AI Memory, Agent Tooling, Git-backed Storage
03

Features

engram-memory logoengram-memory
01Three-tiered recall engine (Hot-Tier Cache, Multi-Head Hash Index, Hybrid Vector Search) for fast and efficient memory retrieval.
02Persistent memory management with semantic embedding (store, search, recall, forget, consolidate) for AI agents.
03Local-first operation with self-hosted components (Qdrant, FastEmbed, MCP server) for data privacy and zero API costs.
04Kuzu-backed entity graph for tracking entities, co-retrieval patterns, and spreading activation.
05Advanced memory capabilities including conflict detection, temporal queries, and an "answer from memory" function.
06Hive Memory for multi-device sharing, enabling shared memory pools across different agents and devices.
Perenna logoPerenna
01Git-backed permanent memory storage in human-readable Markdown.
02Local Vexor retrieval index that can always be rebuilt from Git.
03Support for various AI agents and MCP clients to share memory.
04Self-hosted with no account or proprietary cloud lock-in.
05Cross-process locking for multiple local agent processes.
04

Use Cases

engram-memory logoengram-memory
↳Providing long-term memory for AI agents (e.g., Claude Code, Cursor) to remember codebase details, user preferences, and architectural decisions across sessions.
↳Enabling multi-agent systems to share a common knowledge base and collaborate effectively through shared memory pools (Hive Memory).
↳Answering complex questions by synthesizing information from an agent's stored memories, both locally and optionally with cloud enhancement.
↳Auditing an agent's knowledge at specific points in time or over date ranges using temporal queries for incident analysis or historical context.
↳Storing and retrieving user preferences, facts, decisions, goals, and insights efficiently and semantically for personalized agent interactions.
Perenna logoPerenna
↳Sharing durable memories across different AI agents like Claude Code, Codex, ChatGPT, and Cursor.
↳Self-hosting a private and controllable AI agent memory service.
↳Inspecting, editing, versioning, and backing up AI agent memories.
↳Ensuring AI agent memory persistence when switching between agents or machines.
FAQ

FAQ

What is the difference between engram-memory and Perenna?
Both engram-memory and Perenna are in the Memory & Context category. engram-memory has 38 stars, while Perenna has 61 stars.
Which is better, engram-memory or Perenna?
The best choice depends on your use case. Choose engram-memory if Providing long-term memory for AI agents (e.g., Claude Code, Cursor) to remember codebase details, user preferences, and architectural decisions across sessions., and Perenna if Sharing durable memories across different AI agents like Claude Code, Codex, ChatGPT, and Cursor..
Is engram-memory free or open source?
Yes, engram-memory is open source on GitHub (NOASSERTION).
Is Perenna free or open source?
Yes, Perenna is open source on GitHub (MIT).
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 engram-memory →Alternatives to Perenna →engram-memory details →Perenna details →