CogmemAi – Persistent memory and compaction recovery for Claude Code
Persistent memory for Claude Code with auto-compaction recovery—but relies entirely on external API.
CogmemAi — Cognitive Memory for Any Ai System. Autonomous robots, self-driving vehicles, defense systems, coding assistants, and more. 91% LoCoMo benchmark — above human performance.
Runs extraction and search server-side so your local MCP is a tiny HTTP client — no local DBs, no giant RAM leaks, and an easy npx install and .mcp.json or global MCP registration. It exposes clear tools (save_memory, recall_memories, extract_memories, get_project_context) and adds project-scoped + global preferences — a pragmatic fix for Claude Code's tiny flat-file memory. The tradeoff is obvious: usefulness depends on the hosted API (privacy, uptime, cost), and the repo looks early-stage with minimal commits and docs beyond the quickstart.
Developers and teams who use Claude Code and want cross-session persistent memory (AI-assisted engineers, tooling maintainers)
Persistent memory for Claude Code with auto-compaction recovery—but relies entirely on external API.
Local RAG + MCP for Claude with zero external dependencies—elegant constraint execution.
Claude memory without token costs, but requires running five services for one feature.
Claude memory is solved—Pinecone, LLamaIndex, and Continue already do this.
MCP memory standard solves AI context amnesia better than static .claude files.
Local RAG for Claude when Cursor and other editors already handle context.