agentmem
Persistent memory for Claude Desktop, Cursor, and similar coding agents that treats every stored fact as having a trust level. Memories move through a lifecycle from hypothesis to active to validated, and you can deprecate or supersede them when they're outdated. It detects conflicts between contradictory rules, flags stale entries based on age or source file drift, and scores overall memory health. The MCP server exposes 13 tools for CRUD, search, recall with token budgeting, promotion, and conflict detection. Think of it as version control for what your agent believes is true, so it stops retrieving rules you stopped following three months ago.
- GitHub stars
- 2
- tools
- 13
- transport
- STDIO
- last updated
- Apr 17, 2026
Tools
13 toolsPublic tool metadata for what this MCP can expose to an agent.
add_memory
No parameter schema in public metadata yet.
search_memory
No parameter schema in public metadata yet.
recall_memory
No parameter schema in public metadata yet.
update_memory
No parameter schema in public metadata yet.
delete_memory
No parameter schema in public metadata yet.
list_memories
No parameter schema in public metadata yet.
save_session
No parameter schema in public metadata yet.
load_session
No parameter schema in public metadata yet.
promote_memory
No parameter schema in public metadata yet.
deprecate_memory
No parameter schema in public metadata yet.
supersede_memory
No parameter schema in public metadata yet.
memory_health
No parameter schema in public metadata yet.
memory_conflicts
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
agentmem
Shared memory for Claude Code, Cursor, and Codex that knows what's still true. Save sessions, catch stale and conflicting rules, and stop your agent from repeating old mistakes.
The Problem
Your AI coding assistant forgets everything between sessions. It repeats old mistakes. It can't tell current rules from outdated ones. Context compresses and recovery is painful.
Most memory tools solve storage. agentmem solves trust.
Get Started (Claude Code / Cursor / Codex)
pip install quilmem[mcp]
agentmem init --tool claude --project myapp
That's it. Restart your editor. Your agent now has 13 memory tools. Run memory_health to confirm.
Details
- Repository
- github.com/thezenmonster/agentmem
- Website
- thezenmonster.github.io/agentmem
- Category
- AI & LLM Tools
- Package
quilmem- Transport
- STDIO
- Registry
- MCP registry, active
More from thezenmonster
Related AI & LLM Tools MCP servers
View all
Mcp Thinkgatetjp2021/mcp-thinkgateAuto-classifies prompt complexity and routes to the right Claude thinking mode. No API key needed.2stars
Pseudonym Mcpwoladi/pseudonym-mcpLocally pseudonymizes sensitive text before cloud LLM work and restores the tokens afterward.2stars
Pop Pay100xpercent/pop-payRuntime security for AI agent commerce. CLI + MCP server blocks hallucinated purchases.1stars
Forgevoxellinc/forge-mcpMCP server for Forge, Voxell's embedding API. Voxell's Ingot-8B-R3 ranks #1 for English on MTEB.1stars
Amberambermem/amberLong-term memory for AI assistants: permanent, portable across clients, searchable and exportable.1stars
Queryshieldbch1212/queryshieldSecure SQL proxy for AI agents — NL→SQL, AST safety, per-agent RLS, audit log.1stars