zenbrain
Agent memory for LLM agents: 7 neuroscience-inspired layers (working, episodic, semantic, procedural) with FSRS spaced repetition and memory consolidation. Zero-dependency TypeScript library, Model Context Protocol (MCP) server, Vercel AI SDK middleware. Wins 9/9 answer-quality comparisons on LongMemEval-500 (3 judges, Bonferroni).
面向 LLM 智能体的智能体记忆：7 个受神经科学启发的层次（工作、情景、语义、程序）以及 FSRS 间隔重复与记忆整合。零依赖 TypeScript 库、Model Context Protocol（MCP）服务器、Vercel AI SDK 中间件。在 LongMemEval-500 上取得 9/9 答案质量对比全胜（3 位评审，Bonferroni 校正）。
How to install
npx -y zenbrain Recommendation signals
Meta
- License
- Apache-2.0
- Language
- TypeScript
- GitHub stars
- 24
- mo. downloads
- –
- Last push
- 2026-09-21
- Created
- 2026-03-23
Basic safety check
- Findings
- None
- Sources
- curated:punkpeye/awesome-mcp-servers
- Topics
- agent-memory, ai-memory, cognitive-architecture, ebbinghaus, episodic-memory, forgetting-curve, fsrs, hebbian-learning, llm-memory, long-term-memory, longmemeval, memory-consolidation, memory-layer, neuroscience, procedural-memory, semantic-memory, spaced-repetition, stateful-agents, working-memory, zero-dependencies
Related plugins
dsh-mnemon
omdsh-dev/dsh-mnemon
Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.
memsearch
zilliztech/memsearch
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
dsh-mnemon
dsh-external/dsh-mnemon
Composable, view-based memory for DeepSeek Harness. Pluggable sources and strategies, with three-tier memory out of the box.
markdownify-mcp
zcaceres/markdownify-mcp
A Model Context Protocol server for converting almost anything to Markdown