AgentIndex icon
AgentIndex
AgentRecall-MCP logo
AgentRecall-MCP
★ 371
vs
pm-skills-mcp logo
pm-skills-mcp
★ 20

AgentRecall-MCP vs pm-skills-mcp

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.; pm-skills-mcp: PM-Skills MCP is an MCP server that transforms a collection of 40 best-practice product management skills into programmatically accessible tools, resources, and prompts for any AI assistant. It provides 59 MCP tools, 11 workflows, and 3 prompts, enabling instant integration with platforms like Claude Desktop, Cursor, and Continue.

01

TL;DR

AgentRecall-MCP logo
AgentRecall-MCPMemory & Context · ★ 371

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

Read AgentRecall-MCP full review →
pm-skills-mcp logo
pm-skills-mcpWorkflow Automation · ★ 20

Quickly generate a Product Requirements Document (PRD) using the pm_prd skill

Read pm-skills-mcp full review →
02

Side-by-Side Comparison

Field
AgentRecall-MCP logoAgentRecall-MCP
pm-skills-mcp logopm-skills-mcp
Category
Memory & Context
Workflow Automation
Stars
★ 371
★ 20
License
MIT
Apache-2.0
Install Command
claude mcp add --scope user agent-recall -- npx -y agent-recall-mcp
npm install -g pm-skills-mcp
Updated
1w ago
2mo ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
agent-memory, ai-agents, claude-code
agent-skills, ai-agents, claude-code
03

Features

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
pm-skills-mcp logopm-skills-mcp
0159 MCP Tools — 40 PM skills, 11 workflows, and 8 utility tools
02MCP Resources — Direct access to skill instructions, templates, and examples via URI
033 MCP Prompts — Guided conversation starters for common workflows
0411 Workflows — Pre-built multi-skill workflows for common scenarios
05Zero Configuration — Works out of the box with embedded skills
04

Use Cases

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
pm-skills-mcp logopm-skills-mcp
↳Quickly generate a Product Requirements Document (PRD) using the pm_prd skill
↳Validate a product hypothesis with the pm_hypothesis skill and experiment design workflow
↳Execute a full feature kickoff workflow from problem statement to user stories
FAQ

FAQ

What is the difference between AgentRecall-MCP and pm-skills-mcp?
Both AgentRecall-MCP and pm-skills-mcp are in the Memory & Context category. AgentRecall-MCP has 371 stars, while pm-skills-mcp has 20 stars.
Which is better, AgentRecall-MCP or pm-skills-mcp?
The best choice depends on your use case. Choose AgentRecall-MCP if Maintain context across AI agent sessions (Claude Code, Cursor, etc.), and pm-skills-mcp if Quickly generate a Product Requirements Document (PRD) using the pm_prd skill.
Is AgentRecall-MCP free or open source?
Yes, AgentRecall-MCP is open source on GitHub (MIT).
Is pm-skills-mcp free or open source?
Yes, pm-skills-mcp is open source on GitHub (Apache-2.0).
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-MCP →Alternatives to pm-skills-mcp →AgentRecall-MCP details →pm-skills-mcp details →