Persistent, correction-driven memory for AI agents. Cross-session, cross-platform (Claude Code, Codex, Gemini — any MCP client). Learns from mistakes, compresses context to save tokens, consolidates knowledge overnight. npm: agent-recall-mcp
Last commit July 16, 2026, 120 days ago.
310 GitHub stars and 0 Honeystax upvotes. Copy the install, test the workflow, then decide if it earns a permanent slot.
You can test this quickly and remove it cleanly if it misses.
Starts at 6. Added: last commit 120 days ago +14, GitHub health 71/100 +8, no security policy +8, no code of conduct +3.
AI Agent
Multiple
Model
Multiple
Fastest way to find out if AgentRecall-MCP belongs in your setup.
Copy the install command, run a real test, and back it out cleanly if it slows you down.
claude mcp add agentrecall-mcp -- npx agentrecall-mcpRun this first. You will know quickly if the workflow earns a permanent slot.
claude mcp remove agentrecall-mcpNo messy cleanup loop. If it misses, remove it and keep moving.
Install Location
~/ └─ .claude.json └─ mcp_servers/ └─ agentrecall-mcp ← registers here
AgentRecall-MCP is listed on Honeystax as a MCP Server for Multiple, since May 23, 2026. Its code is at github.com/Goldentrii/AgentRecall-MCP, with 310 GitHub stars and 26 open issues. Last commit July 16, 2026, 120 days ago. GitHub's community health check gives it 71 out of 100.
Source: GitHub repository
Source check: July 18, 2026
Upstream commit: July 16, 2026
Repository state: Not marked archived
Honeystax upvotes are community interest signals, not star ratings. GitHub stars and repository health are source measurements; editorial risk and trial-cost notes are Honeystax analysis.