projectmem

★ 868

engrim

★ 299

projectmem vs engrim

Q: Which is better, projectmem or engrim?

By GitHub stars, projectmem has more community adoption, but the best choice depends on your specific use case.

projectmem: projectmem is an open-source, local-first memory and judgment layer for AI coding agents, designed to capture persistent records of project development, including issues, attempts, fixes, and decisions. It aims to make AI experienced, preventing repetition of past failures and significantly reducing token usage by providing distilled context.; 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.

TL;DR

projectmemMemory & Context · ★ 868

Preventing AI agents from repeating past debugging attempts or failed architectural approaches.

Read projectmem full review →

engrimMemory & Context · ★ 299

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 →

Side-by-Side Comparison

Field

projectmem

engrim

Features

projectmem

01Pre-Commit Warnings: Warns developers before committing if they're repeating failed approaches, modifying high-churn files, or touching unresolved issues.

02Local-First and 100% Private: All memory and data reside locally in a `.projectmem/` directory with no cloud, accounts, or telemetry.

03Global Dashboard: Provides a unified view of all `pjm init`-ed projects, showing grades, issues, savings, and a 'needs attention' list, aggregated at read-time.

04Code Structure + Judgment: Overlays failure heat from the event log directly onto the codebase's import graph, highlighting files with repeated failed attempts.

05Smart Context Injection & Token Efficiency: Distills raw event logs into compact, AI-readable summaries and provides token-budgeted memory blocks, significantly reducing token cost.

engrim

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.

Use Cases

projectmem

↳Preventing AI agents from repeating past debugging attempts or failed architectural approaches.

↳Improving AI agent efficiency and reducing token costs by providing distilled, context-aware project memory instead of re-reading raw files.

↳Visualizing project development history, including issues, fixes, and decisions, to understand codebase evolution and identify problem areas.

↳Onboarding new developers or bringing AI agents up to speed on a project quickly by injecting pre-existing project knowledge and decisions.

↳Providing a persistent, auditable record of AI agent interactions and learning within a project.

engrim

↳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.

Best For

projectmem

Hidden Gem

engrim

—

FAQ

What is the difference between projectmem and engrim?

Both projectmem and engrim are in the Memory & Context category. projectmem has 868 stars, while engrim has 299 stars.

Which is better, projectmem or engrim?

The best choice depends on your use case. Choose projectmem if Preventing AI agents from repeating past debugging attempts or failed architectural approaches., 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 projectmem free or open source?

Yes, projectmem is open source on GitHub (MIT).

Is engrim free or open source?

Yes, engrim is open source on GitHub (MIT).

Cloud Infrastructure

Deploy on DigitalOcean

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

Claim $200 Free Credit

→

Alternatives to projectmem →Alternatives to engrim →projectmem details →engrim details →

TL;DR

Side-by-Side Comparison

Features

Use Cases

Best For

FAQ

Deploy on DigitalOcean

Related