YourMemory
Active·★ 231·NOASSERTION·Updated 2026-05-29
★ Trending★ Memory & Context
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
YourMemory is an MCP-compatible memory server for AI agents that mimics human memory with biological decay. Important facts persist, outdated ones fade, and a graph layer keeps related memories alive. It achieves 59% Recall@5 on the LoCoMo-10 benchmark and can be installed with just two commands.
#ai-agents#claude#ebbinghaus#llm-memory#mcp#mcp-servers#memory#model-context-protocol
01
Features
01Biological decay mimicking human memory
02Hybrid BM25 + vector + knowledge graph retrieval pipeline
03Chain-aware pruning that protects related memory clusters
04Multi-agent shared and private memory with access control
05Zero infrastructure setup using DuckDB
02
Compatibility
Claude Code
Claude Code
Verified via docs
Claude Desktop
Claude Desktop
Verified via docs
Cline
Cline
Verified via docs
Cursor
Cursor
Verified via docs
Windsurf
Windsurf
Verified via docs
Continue
Continue
Verified via docs
03
Quick start
1
$ pip install yourmemory
2
$ yourmemory-setup
04
Use cases
↳Providing persistent memory for AI coding assistants like Claude and Cline
↳Enabling multi-agent collaboration with shared and private memory
↳Remembering user preferences and project context across sessions
05
Alternatives
letta★ 23.0k
Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.
DesktopCommanderMCP★ 6.1k
This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities
FunASR★ 16.6k
Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.
Auto-claude-code-research-in-sleep★ 11.0k
ARIS ⚔️ (Auto-Research-In-Sleep) — Claude Code skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation via Codex MCP
Related searches
Comments
Log in to leave a comment
- RRiver JohnsonMay 17, 2026
The forgetting curve model prioritizes recently reinforced memories correctly.
- OOaklyn WhiteMay 9, 2026
Ebbinghaus forgetting curve applied to AI memory is a principled approach to retention.
- FFinley ZhangMar 12, 2026
+16pp better recall with decay-aware memory is a meaningful improvement.
- CCorey ThompsonMar 7, 2026
Good for AI agents where memory quality matters over extended use.