AgentIndex icon
AgentIndex
AgentRecall logo
AgentRecall
★ 371
vs
AgentRecall-MCP logo
AgentRecall-MCP
★ 371

AgentRecall vs AgentRecall-MCP

AgentRecall: AgentRecall is a learning system that bridges the gap between human thinking and AI agent behavior. It provides persistent, compounding memory with automatic correction capture via MCP server, SDK, and CLI. Every mistake is recorded once and never repeated, and token savings compound over sessions.; AgentRecall-MCP: AgentRecall is a learning loop for AI agents that provides persistent, compounding memory. It captures corrections automatically, surfaces past insights across projects, and uses a five-layer memory pyramid with Ebbinghaus decay and Bayesian feedback. Zero cloud, all local markdown files.

01

TL;DR

AgentRecall logo
AgentRecallMemory & Context · ★ 371

Scattered human: structurize non-linear instructions across sessions

Read AgentRecall full review →
AgentRecall-MCP logo
AgentRecall-MCPMemory & Context · ★ 371

Maintain context across AI agent sessions (Claude Code, Cursor, etc.)

Read AgentRecall-MCP full review →
02

Side-by-Side Comparison

Field
AgentRecall logoAgentRecall
AgentRecall-MCP logoAgentRecall-MCP
Category
Memory & Context
Memory & Context
Stars
★ 371
★ 371
License
MIT
MIT
Install Command
npm install -g agent-recall-cli
claude mcp add --scope user agent-recall -- npx -y agent-recall-mcp
Updated
1w ago
1w ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
agent-memory, ai-agents, claude-code
agent-memory, ai-agents, claude-code
03

Features

AgentRecall logoAgentRecall
01Persistent, compounding memory with 200-line awareness cap
02Automatic correction capture and recall
03Cross-project insight recall via keyword matching
04MCP, SDK, and CLI for universal compatibility
05Zero cloud, all local markdown storage
AgentRecall-MCP logoAgentRecall-MCP
01Persistent, compounding memory with 200-line awareness cap
02Automatic correction capture and alignment checking
03Cross-project insight recall via keyword and semantic (pgvector) search
04Zero cloud, all local markdown files, Obsidian-compatible
0510 MCP tools for agents, plus SDK and CLI
04

Use Cases

AgentRecall logoAgentRecall
↳Scattered human: structurize non-linear instructions across sessions
↳Cross-project lesson transfer: rate limiting insight from Project A to Project B
↳Correction that sticks: agent never repeats a correction again
AgentRecall-MCP logoAgentRecall-MCP
↳Maintain context across AI agent sessions (Claude Code, Cursor, etc.)
↳Capture and learn from user corrections in software development
↳Coordinate memory across multiple parallel agents
FAQ

FAQ

What is the difference between AgentRecall and AgentRecall-MCP?
Both AgentRecall and AgentRecall-MCP are in the Memory & Context category. AgentRecall has 371 stars, while AgentRecall-MCP has 371 stars.
Which is better, AgentRecall or AgentRecall-MCP?
The best choice depends on your use case. Choose AgentRecall if Scattered human: structurize non-linear instructions across sessions, and AgentRecall-MCP if Maintain context across AI agent sessions (Claude Code, Cursor, etc.).
Is AgentRecall free or open source?
Yes, AgentRecall is open source on GitHub (MIT).
Is AgentRecall-MCP free or open source?
Yes, AgentRecall-MCP is open source on GitHub (MIT).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to AgentRecall →Alternatives to AgentRecall-MCP →AgentRecall details →AgentRecall-MCP details →