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

Compartment

Active·★ 584·Apache-2.0·Updated 2026-10-20

Compartment provides durable, encrypted, and offline-first memory for AI agents, allowing them to retain decisions and preferences permanently on your local machine. It offers fast hybrid search, robust security features including AEAD encryption, and easy integration with popular AI agents like Claude, Hermes, and OpenClaw without needing cloud accounts or API keys.

Compartment sits in the Memory & Context category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Durable and encrypted agentic memory stored locally.. A representative use case is Providing long-term memory for AI agents to improve performance over time.. The listed license is Apache-2.0. GitHub stars are currently 584. Relevant tags include Agentic Memory, Offline-first.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

© 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
#Agentic Memory#Offline-first#Encrypted Storage#Semantic Search#AI Agents#Data Security#Local LLM Integration
$ Install
$ pip install compartment && compartment init
↗ Visit site★ GitHub
01

Features

01Durable and encrypted agentic memory stored locally.
02100% offline operation with no network, API keys, or cloud accounts.
03Fast hybrid semantic and keyword search with sub-20ms latency.
04Pre-seeded knowledge base with 6,718 curated facts available at install.
05Cryptographic deletion and hash-chained audit logs ensure data security and integrity.
02

Why choose it

+Durable and encrypted agentic memory stored locally.
+100% offline operation with no network, API keys, or cloud accounts.
+Providing long-term memory for AI agents to improve performance over time.
+Supports 8 platforms or runtime environments.
03

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.
04

Compatibility

Python
Runtime
Verified via docs
MacOS
OS
Verified via docs
Windows
OS
Verified via docs
Linux
OS
Verified via docs
Claude
AI Agent
Verified via docs
Hermes
AI Agent
Verified via docs
05

Quick start

1
$ pip install compartment
2
$ compartment init
06

Use cases

↳Providing long-term memory for AI agents to improve performance over time.
↳Enabling AI agents to operate effectively offline with a rich knowledge base.
↳Securely storing sensitive agentic data, decisions, and preferences locally.
↳Sharing a single, encrypted memory vault across multiple AI agents and projects.
↳Automatically preserving full conversation context before agent summarization or compaction.
07

Alternatives

⚡Top VS:
VSmemora★744→VSmnemo-cortex★158→VSmcp-local-memory★60→

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases
VS
montycat-mcp
★28
→
memora logo
memora★ 744
Give your AI agents persistent memory.
VSCompare→
mnemo-cortex logo
mnemo-cortex★ 158
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.
VSCompare→
mcp-local-memory logo
mcp-local-memory★ 60
A lightweight, powerful local memory server for AI agents supporting text, entities, and relations. Enables persistent codebase understanding and user preference management.
VSCompare→
montycat-mcp logo
montycat-mcp★ 28
Shared, persistent memory for AI agents. Self-hosted MCP server with semantic search, vector RAG, and live updates. Works with Claude, Cursor, Codex, and any MCP client.
VSCompare→
geode logo
geode★ 34
Easy, secure access to your Obsidian vault from anywhere, for humans and agents.
VSCompare→
infimium-agent logo
infimium-agent★ 25
Infimium helps agents find the right code, docs, and dependencies — before they edit. Local-first, open-source, MCP-compatible.
VSCompare→
hippo-memory logo
hippo-memory★ 784
Biologically-inspired memory for AI agents. Decay, retrieval strengthening, consolidation. Zero runtime deps, SQLite, MCP. Benchmarked retrieval with an opt-in hosted TypeSafe Jev reranker.
VSCompare→
okf-agent-memory logo
okf-agent-memory★ 827
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.
VSCompare→
See all alternatives →
07
Alternatives
MaxFreedomPollard /
Compartment
↗

Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Logically and mathematically sound storage and retrieval.

584Apache-2.0
Last commit2d 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