The request names 'Working Memory', so the answer is about workingmemory.ai 1: a private memory for small marketing teams that captures decisions with their reasoning and recalls them in Claude, ChatGPT and Gemini, exposed through an MCP server named WorkingMemory. Note its page says new sign-ups are currently closed. Alternatives that give AI agents persistent memory are Agentmemory 8, SmartMemory 9 and Memxus 10.
- 1
Working Memoryworkingmemory.aiwebsite read, tools not yet checked
A private team memory that captures the why behind marketing decisions and recalls it across Claude, ChatGPT and Gemini, with an MCP server named WorkingMemory 1; new sign-ups are currently closed.
official:MCP server · WorkingMemory
- 2
- 3
SmartMemorysmartmemory.aifound in code, not yet checked
Keeps team decisions and their reasons available to every AI agent session, with an MCP server 9.
official:MCP server · Stratum MCPMCP server · Compose MCPMCP server · SmartMemory+1 community tools built for it
for agents: get_working_context · memory_recall · memory_resolve_aliases
- 4
Memxusmemxus.comverified and signed
Builds persistent context from GitHub repos and Notion docs and delivers it to Claude, Cursor and ChatGPT, with an MCP server 10.
official:MCP server · com.memxus/memxus+2 community tools built for it
for agents: remember · get_memory · memory_stats
Sources
- 1Working Memory · one memory, every AIworkingmemory.ai · read 2026-10-29
- 8Agentmemory for AI Coding Agents | Persistent Memory, MCP, and Team Recallagentmemory.space · read 2026-10-29
- 9SmartMemory | The Expertise Layer for AI Agentssmartmemory.ai · read 2026-10-29
- 10Memxus — The AI Context Engine for Developersmemxus.com · read 2026-10-29
For agents: the 10 actions behind this answer
· Working Memory website read, tools not yet checked
One memory, every AI. Working Memory gives small marketing teams a private memory that captures the why behind decisions and recalls it in Claude, ChatGPT, Gemini, and every AI your team works in.
get_working_memory · agent-memory-server found in code, not yet checked
Get working memory for a session.
nemo-rl-session-memory · nemo-rl-session-memory verified and signed
Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for
remember · remember verified and signed
Transforms lessons learned into domain-organized memory instructions (global or workspace). Syntax: `/remember [>domain [scope]] lesson clue` where scope is `global` (default), `user`, `workspace`, or `ws`.
agent-memory-memory-get · Cloudflare API verified and signed
Get a memory
update_row · Supabase (Activepieces) verified and signed
Update Row — Update rows in a table based on filter criteria
install-skills · install-skills verified and signed
Configure and customize skills for your workspace by asking questions and updating skill files with your preferences.
· Agentmemory for AI Coding Agents website read, tools not yet checked
Give Claude Code, Codex, Cursor, OpenAI agents, and MCP workflows governed long-term memory for repos, decisions, procedures, and team handoffs.
get_working_context · smart-memory-mcp found in code, not yet checked
Retrieve a structured surfacing response (CORE-MEMORY-DYNAMICS-1 M1a).
remember · memxus verified and signed
Save important information to long-term memory. Always set collection when the topic is clear: project work → project:<slug>, personal tastes → personal:preferences. Use append_to to extend an existing memory instead of creating duplicates.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.