GitHub Repository

CogmemAi — Cognitive Memory for Any Ai System. Autonomous robots, self-driving vehicles, defense systems, coding assistants, and more. 91% LoCoMo benchmark — above human performance.

6 starsTypeScript

CogmemAi – Persistent memory and compaction recovery for Claude Code

Name: CogmemAi – Persistent memory and compaction recovery for Claude Code
Availability: InStock
Author: hifriendbot

by hifriendbot·Feb 21, 2026·1 point·2 comments

Visit Project View on HN

AI Analysis

●●SolidSolve My ProblemNiche Gem

Persistent memory for Claude Code with auto-compaction recovery—but relies entirely on external API.

Strengths

•Compaction recovery hooks automatically inject project context post-compression, eliminating re-explaining work.
•Semantic search + AI-powered deduplication prevents memory duplication and conflicting facts.
•Cloud-first design (no local databases) sidesteps RAM leaks from competitors (claude-mem, mcp-memory-service).

Weaknesses

•Entirely cloud-dependent; memory is hostage to service uptime and vendor lock-in.
•Privacy concerns: semantic extraction runs server-side, meaning your conversation content is uploaded to their API.

Similar Projects

Developer Tools●Mid

CogmemAi – Persistent Memory for Claude Code via MCP

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.

Niche GemShip ItSolve My Problem

hifriendbot

203mo ago

Developer Tools●●Solid