AgentIndex icon
AgentIndex
mengram logo
mengram
★ 204
vs
engrim logo
engrim
★ 300

mengram vs engrim

mengram: Mengram is an AI memory layer that enables agents to remember facts, events, and workflows, with procedures automatically improving from failures. It uniquely stores semantic, episodic, and procedural memory, offering experience-driven evolution for AI agents.; engrim: Engrim is a universal, local-first SQLite memory engine specifically engineered for autonomous AI coding agents, designed to solve the '200,000-token context window trap'. It provides high-precision, curated episodic working memory, allowing developers to switch between various models and environments on the same codebase without losing architectural decisions or project state.

01

TL;DR

mengram logo
mengramMemory & Context · ★ 204

Building intelligent AI agents that learn and adapt from real-world outcomes.

Read mengram full review →
engrim logo
engrimMemory & Context · ★ 300

Maintaining Project Context Across Agent Sessions: Developers can use Engrim to prevent LLMs from losing architectural decisions, user constraints, or project state when chat sessions are cleared or models are switched.

Read engrim full review →
02

Side-by-Side Comparison

Field
mengram logomengram
engrim logoengrim
Category
Memory & Context
Memory & Context
Stars
★ 204
★ 300
License
Apache-2.0
MIT
Install Command
pip install mengram-ai
pip install engrim
Updated
2d ago
1mo ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
AI Agents, Memory Layer, Procedural Memory
Episodic Memory, LLM Context Management, AI Agents
03

Features

mengram logomengram
01Stores Semantic, Episodic, and Procedural Memory types.
02Experience-Driven Evolution: Procedures automatically improve when they fail.
03Cognitive Profile generation for personalized LLM system prompts.
04Multi-User Isolation: Separate memory spaces for individual users in multi-tenant applications.
05Import existing data from ChatGPT, Obsidian, or text files to avoid cold-start problems.
engrim logoengrim
01Precision Working Memory: Replaces raw transcript replay with ~4,000 characters of high-precision, curated episodic memory, injected at boot with zero attention dilution.
02Cross-Model/Agent Compatibility: Provides a universal substrate for memory, allowing decisions made in one agent (e.g., Claude Code) to be visible and usable in others (e.g., Antigravity, Cursor).
03Local-First & Private Storage: Stores all memories locally in a SQLite file (~/.engrim/memory.db) with WAL mode and POSIX 0600 permissions, ensuring 100% privacy with no cloud sync or telemetry.
04Self-Healing Diagnostics: The `engrim doctor --fix` command verifies all hooks and installs portable PATH fallbacks, ensuring reliable operation across machines and OSes without silent failures.
05Hybrid Retrieval & Minder: Employs a hybrid lexical (BM25) and vector (model2vec) search for efficient and relevant memory recall in approximately 30ms.
04

Use Cases

mengram logomengram
↳Building intelligent AI agents that learn and adapt from real-world outcomes.
↳Enhancing DevOps agents by enabling procedures to evolve from deployment failures.
↳Creating personalized customer support agents that remember returning customers and their history.
↳Personalizing LLM interactions and responses using a dynamically generated cognitive profile.
↳Developing multi-tenant applications where each user requires an isolated and persistent memory space.
engrim logoengrim
↳Maintaining Project Context Across Agent Sessions: Developers can use Engrim to prevent LLMs from losing architectural decisions, user constraints, or project state when chat sessions are cleared or models are switched.
↳Collaborative Multi-Agent Development: Enabling multiple AI coding agents (e.g., Antigravity, Claude Code, Cursor) to work on the same codebase and share a consistent, evolving memory store.
↳Continue-As-Clear Workflow: Allows users to clear their agent's context window at any time, with Engrim automatically re-injecting the active memory pack for seamless continuation without memory loss.
↳Auditing Agent Provenance: Tracking which agent made specific architectural decisions or added facts to the project's memory, enhancing transparency in multi-agent environments.
FAQ

FAQ

What is the difference between mengram and engrim?
Both mengram and engrim are in the Memory & Context category. mengram has 204 stars, while engrim has 300 stars.
Which is better, mengram or engrim?
The best choice depends on your use case. Choose mengram if Building intelligent AI agents that learn and adapt from real-world outcomes., and engrim if Maintaining Project Context Across Agent Sessions: Developers can use Engrim to prevent LLMs from losing architectural decisions, user constraints, or project state when chat sessions are cleared or models are switched..
Is mengram free or open source?
Yes, mengram is open source on GitHub (Apache-2.0).
Is engrim free or open source?
Yes, engrim 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 mengram →Alternatives to engrim →mengram details →engrim details →