AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Memory & Context/
engrim
engrim logo

engrim

Active·★ 305·MIT·Updated 2026-09-26

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.

Basic information · No in-depth review published yet. Features and usage information are compiled from public project materials; check the official documentation before choosing.

#Episodic Memory#LLM Context Management#AI Agents#SQLite Database
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides
#Cross-Model Compatibility
#Local-First
#Dev Tooling
#Software Development
$ Install
$ pip install engrim
↗ Visit site★ GitHub
01

Features

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.
02

Compatibility

Python
Runtime
Verified via docs
SQLite
Database
Verified via docs
Google Antigravity
Agent Environment
Verified via docs
Claude Code
Agent Environment
Verified via docs
Cursor / Windsurf
Agent Environment
Verified via docs
Codex CLI
Agent Environment
Verified via docs
03

Quick start

1
$ pip install engrim
04

Use cases

↳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.
05

Alternatives

mcp-local-memory logo
mcp-local-memory★ 62
A lightweight, powerful local memory server for AI agents supporting text, entities, and relations. Enables persistent codebase understanding and user preference management.
Headroom logo
Headroom★ 79.6k
Local context compression for tool outputs, logs and structured data, with Python, proxy and MCP integration paths.
daidocs logo
daidocs★ 55

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cursor, local models and grep (all LLM models work). MCP server + hooks for Claude Code, Claude Desktop, Cursor, Windsurf, Codex. 83% LongMemEval-S (GPT-4o), 92% (Claude Fable 5), 10x fewer tokens.
mnemo-cortex logo
mnemo-cortex★ 160
Open-source cognitive coprocessor with active memory for AI agents — persistent recall, semantic search, overnight dreaming, verified facts, encrypted USB sync. MCP server; works with Claude, ChatGPT, and any local LLM. Built by one maker and his agents.
MemWhale logo
MemWhale★ 145
Persistent, local memory for developers and their coding agents. Records commands, output, errors, and the fixes that worked into SQLite and serves them over MCP.
remem logo
remem★ 33
Local-first persistent memory for Claude Code & Codex CLI - Rust CLI, hooks, MCP server, SQLite/SQLCipher, auditable recall for long-running coding work.
okf-agent-memory logo
okf-agent-memory★ 866
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
projectmem logo
projectmem★ 881
Local-first AI coding memory for AI agents. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.
timgordontg /
engrim
↗

The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antigravity, Claude Code, Cursor, Codex CLI, and OpenCode. Zero cloud lock-in.

305MIT
Last commit1mo ago
StatusActive
CategoryMemory & Context
Links
Documentation↗Discussion↗Issues↗Releases↗
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