AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Memory & Context/
agent-skill-memories-off
agent-skill-memories-off logo

agent-skill-memories-off

Active·★ 48·Apache-2.0·Updated 2026-05-28

memories-off provides a minimalist, structured local knowledge management solution that endows agents with long-term memory. It uses standardized Markdown entities and Git-driven workflows to maintain an auditable, rollbackable knowledge base. The project is designed for personal or small project use, with a focus on portability, readability, and flexibility.

#agent-skills#cli#llm#mcp#mcp-server#mcp-servers#memory-management#personal-assistant
$ Install
$ cd memories-off-skill && python3 scripts/install.py
↗ Visit site★ GitHub
01

Features

01Lightweight and local-first, no dependency on cloud services
02Structured knowledge via LLM-extracted entities, relations, and observations
03Flexible search by entity name, type, or observation keywords
04Human-readable data with simple backup functionality
02

Compatibility

Python
Runtime
Verified via docs
Cross-platform
OS
Verified via docs
03

Quick start

1
$ cd memories-off-skill
2
$ python3 scripts/install.py
04

Use cases

↳Personal knowledge management: extract key points from documents and conversations, build a personal knowledge graph
↳Personalized content generation: leverage the knowledge graph to generate style-consistent communications or documents
↳Project knowledge base: small teams can use it to accumulate project-level knowledge and optimize agent services
05

Alternatives

⚡Top VS:
VSllm-wiki-kit★61→VShmem★24→VSAgentRecall-MCP★371→VSits-over-9k★0→
llm-wiki-kit logo
llm-wiki-kit★ 61
Stop re-explaining your research to your AI agent. Persistent, LLM-maintained wikis that compound over time. Drop PDFs, URLs, YouTube — your agent remembers forever. Based on Karpathy's LLM Wiki pattern.
VSCompare→
hmem logo
hmem★ 24
Humanlike persistent memory for AI agents — MCP server with 5-level lazy-loaded SQLite memory. Works with Claude Code, Gemini CLI, Cursor, Windsurf, OpenCode.
VSCompare→
AgentRecall-MCP logo
AgentRecall-MCP★ 371
Persistent, correction-driven memory for AI agents. Cross-session, cross-platform (Claude Code, Codex, Gemini — any MCP client). Learns from mistakes, compresses context to save tokens, consolidates knowledge overnight. npm: agent-recall-mcp
VSCompare→
its-over-9k logo
its-over-9k★ 0
Persistent memory and agent lifecycle for Claude Code — because sessions shouldn't start from zero.
VSCompare→
ogham-mcp logo
ogham-mcp★ 116
Shared memory MCP server — persistent, searchable, cross-client Claude, Opencode
VSCompare→
neurostack logo
neurostack★ 47
Your second brain, starting today. CLI + MCP server that helps you build, maintain, and search a knowledge vault that gets better every day. Works with any AI provider. Local-first, zero-prereq install.
VSCompare→
shellguard logo
shellguard★ 24
MCP server that gives LLM agents read-only shell access over SSH
VSCompare→
drift logo
drift★ 791
Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
cafe3310 /
agent-skill-memories-off
↗

把这些记住,帮我早点下班

48Apache-2.0
Last commit4mo 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
© 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.