markmhendrickson/neotoma
by Various
Your agents forget. Neotoma makes them remember.
MCP
markmhendrickson/neotoma
Added 1 June 2026
Overview
Neotoma provides memory for AI agents, preventing them from forgetting between interactions. The repository is written in HTML, indicating a simple implementation or demonstration. It solves the problem of context loss in agent workflows.
Best for
Best for
Developers building experimental agents that need basic memory
Use cases
- Adding persistent memory to AI agents
- Preventing agent context loss across conversations
- Storing and recalling agent experiences
How to use
Install
npm install -g neotomaTested with
Cursor, Claude Desktop, Claude Code, Windsurf, Continue, VS Code, ChatGPT
Notes
Neotoma provides memory for AI agents, preventing them from forgetting between interactions. The repository is written in HTML, indicating a simple implementation or demonstration. It solves the problem of context loss in agent workflows.
24 stars on GitHub. Last updated 2026-06-01. Licensed MIT.
Use cases
- Adding persistent memory to AI agents
- Preventing agent context loss across conversations
- Storing and recalling agent experiences
Pros
- Focused on a single clear problem: agent memory
- Simple codebase easy to understand and modify
- Low overhead, suitable for experimentation
Cons
- Very small community with only 24 stars
- Limited documentation and features
- May not be production-ready or actively maintained
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Focused on a single clear problem: agent memory
- Simple codebase easy to understand and modify
- Low overhead, suitable for experimentation
Cons
- Very small community with only 24 stars
- Limited documentation and features
- May not be production-ready or actively maintained
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
upstash/context7
Various
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
topoteretes/cognee
Various
Memory platform for AI Agents in 6 lines of code
vectorize-io/hindsight
Various
Hindsight: Agent Memory That Learns
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.