AgentRecall vs Instinct

Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.

Compare
A
AgentRecall
Goldentrii
🧠 Knowledge & Memory
I
Instinct
yakuphanycl
🧠 Knowledge & Memory
SummaryPersistent, compounding memory for AI agents across sessions. Uses the Intelligent Distance Protocol to surface the most contextually relevant past memories. Five tools: sessionstart, remember, recall, check, sessionend. npx agent-recall-mcpSelf-learning memory for AI coding agents. Observes tool sequences, user preferences, and recurring fixes; confidence-based promotion (hits ≥5 → mature, ≥10 → rule) so agents stop repeating mistakes without explicit instruction. SQLite-backed, project-aware, zero external deps. Works with Claude Code, Cursor, Windsurf, Goose, Codex. Published on PyPI as instinct-mcp and registered in the MCP Registry.
Quality signal28/100 (Emerging)24/100 (Emerging)
Install pathnpx · highnpx · low
Engagement 0 0 0 311 0 0 0
ToolsNot listed yetNot listed yet
Verified / officialNoNo
Open listingView AgentRecallView Instinct
More alternatives to AgentRecallMore alternatives to InstinctKnowledge & Memory category

Other servers like AgentRecall