hifriendbot/cogmemai-mcp
by Various
CogmemAi — Cognitive Memory for Any Ai System. Autonomous robots, self-driving vehicles, defense systems, coding assistants, and more. 91% LoCoMo benchmark — above human performanc
MCP
hifriendbot/cogmemai-mcp
Added 1 June 2026
Overview
Cogmemai-mcp provides cognitive memory for AI systems via a TypeScript server implementing the Model Context Protocol. It achieves 91% on the LoCoMo benchmark, surpassing human performance, and is designed for autonomous robots, self-driving vehicles, defense systems, and coding assistants.
Best for
Best for
Developers building AI agents that require long-term memory and context retention
Use cases
- Adding persistent memory to coding assistants
- Enabling autonomous robots to recall past experiences
- Improving context retention in defense or vehicle AI systems
How to use
Install
npx cogmemai-mcp setup Tools exposed
save_memoryrecall_memoriesextract_memoriesget_project_contextlist_memoriesupdate_memorydelete_memorybulk_deletebulk_updateget_usageexport_memoriesimport_memoriesingest_documentsave_session_summarylist_tagslink_memoriesget_memory_linksget_memory_versionsget_analyticspromote_memory
Tested with
Claude Desktop, Claude Code, Cursor, Windsurf, Cline, Continue, VS Code, ChatGPT
Notes
Cogmemai-mcp provides cognitive memory for AI systems via a TypeScript server implementing the Model Context Protocol. It achieves 91% on the LoCoMo benchmark, surpassing human performance, and is designed for autonomous robots, self-driving vehicles, defense systems, and coding assistants.
6 stars on GitHub. Last updated 2026-05-31. Licensed MIT.
Use cases
- Adding persistent memory to coding assistants
- Enabling autonomous robots to recall past experiences
- Improving context retention in defense or vehicle AI systems
Pros
- Benchmark performance exceeds human baseline on LoCoMo
- Broad applicability across robotics, defense, and coding
- Built in TypeScript for type safety and broad ecosystem compatibility
Cons
- Very early stage with only 6 stars and limited community adoption
- Narrowly focuses on cognitive memory, not a general AI framework
- Documentation and examples sparse due to small project size
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Benchmark performance exceeds human baseline on LoCoMo
- Broad applicability across robotics, defense, and coding
- Built in TypeScript for type safety and broad ecosystem compatibility
Cons
- Very early stage with only 6 stars and limited community adoption
- Narrowly focuses on cognitive memory, not a general AI framework
- Documentation and examples sparse due to small project size
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Claude Computer Use
Anthropic
Claude takes the mouse and keyboard. A vision-based agent that controls a real desktop, not just a browser.
Claude Code
Anthropic
Anthropic's terminal-native coding agent. Reads your repo, edits files, runs tests, ships PRs.
Cline
Cline
Open-source autonomous coding agent that lives inside VS Code. BYO model key, watch it work.
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.