zensation-ai/zenbrain
by Various
Agent memory for LLM agents: 7 neuroscience-inspired layers (working, episodic, semantic, procedural) with FSRS spaced repetition and memory consolidation. Zero-dependency TypeScri
MCP
zensation-ai/zenbrain
Added 21 Sept 2026
Overview
Agent memory library for LLM agents that organizes memory across seven layers inspired by neuroscience, including working, episodic, semantic, and procedural memory. Uses FSRS spaced repetition and memory consolidation to prioritize recall. Implemented as a zero-dependency TypeScript library with an MCP server and Vercel AI SDK middleware. Reports 9/9 answer-quality wins on LongMemEval-500.
Best for
Best for
Developers building experimental LLM agents that need structured, long-term memory.
Use cases
- Give a long-running agent persistent, tiered memory across sessions
- Add spaced-repetition recall to an LLM app via MCP or Vercel AI SDK middleware
- Benchmark agent memory quality against LongMemEval-500
How to use
Install
npx tsx examples/basic-chatbot.tsTested with
Claude Desktop, Claude Code, Cursor
Notes
Agent memory library for LLM agents that organizes memory across seven layers inspired by neuroscience, including working, episodic, semantic, and procedural memory. Uses FSRS spaced repetition and memory consolidation to prioritize recall. Implemented as a zero-dependency TypeScript library with an MCP server and Vercel AI SDK middleware. Reports 9/9 answer-quality wins on LongMemEval-500.
24 stars on GitHub. Last updated 2026-09-21. Licensed Apache-2.0.
Use cases
- Give a long-running agent persistent, tiered memory across sessions
- Add spaced-repetition recall to an LLM app via MCP or Vercel AI SDK middleware
- Benchmark agent memory quality against LongMemEval-500
Pros
- Zero-dependency TypeScript, works without heavy runtime setup
- Integrates as MCP server or Vercel AI SDK middleware
- Strong reported benchmark results (9/9 on LongMemEval-500)
Cons
- Very few GitHub stars (24), so community and production track record are thin
- Vendor listed as ‘Various’, so support and maintenance are unclear
- Neuroscience-inspired layer design may be over-engineered for simple use cases
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Zero-dependency TypeScript, works without heavy runtime setup
- Integrates as MCP server or Vercel AI SDK middleware
- Strong reported benchmark results (9/9 on LongMemEval-500)
Cons
- Very few GitHub stars (24), so community and production track record are thin
- Vendor listed as 'Various', so support and maintenance are unclear
- Neuroscience-inspired layer design may be over-engineered for simple use cases
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
AutoGPT
Community
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Crewai
Community
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
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.