AgentIndex icon
AgentIndex
daidocs logo
daidocs
★ 53
vs
engrim logo
engrim
★ 299

daidocs vs engrim

daidocs: DaiDocs introduces an open, plain-text file format (.dai) for AI assistant memory, allowing memory to reside as files on your local disk that are readable by any tool or model. It boasts high performance on the LongMemEval-S benchmark, significantly outperforming models without a dedicated memory system while reading substantially fewer tokens.; 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

daidocs logo
daidocsRAG / Knowledge Base · ★ 53

Storing AI assistant conversations as persistent, local files for long-term memory and easy inspection.

Read daidocs full review →
engrim logo
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 →
02

Side-by-Side Comparison

Field
daidocs logodaidocs
engrim logoengrim
Category
RAG / Knowledge Base
Memory & Context
Stars
★ 53
★ 299
License
Apache-2.0
MIT
Install Command
npx daidocs setup
pip install engrim
Updated
2w ago
3w ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
AI Memory, Plain-Text Format, LLM Context Management
Episodic Memory, LLM Context Management, AI Agents
03

Features

daidocs logodaidocs
01Open, plain-text `.dai` file format for AI memory, ensuring data persistence and inspectability.
02Language and model agnostic, readable by any tool (grep, git) and multiple LLMs (Claude, GPT, Gemini).
03Automatic and keyless session saving to local disk, converting conversations into memory files.
04Benchmarked as second on LongMemEval-S, significantly reducing token usage for retrieval (10x fewer tokens).
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

daidocs logodaidocs
↳Storing AI assistant conversations as persistent, local files for long-term memory and easy inspection.
↳Integrating with various LLM agents and frameworks (e.g., LangChain, CrewAI) for enhanced memory recall.
↳Converting existing conversation histories from multiple sources into a unified, searchable memory store.
↳Enabling project-specific context and memory for development workflows within IDEs and CLI tools.
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 daidocs and engrim?
Both daidocs and engrim are in the RAG / Knowledge Base category. daidocs has 53 stars, while engrim has 299 stars.
Which is better, daidocs or engrim?
The best choice depends on your use case. Choose daidocs if Storing AI assistant conversations as persistent, local files for long-term memory and easy inspection., 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 daidocs free or open source?
Yes, daidocs 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 daidocs →Alternatives to engrim →daidocs details →engrim details →