AgentIndex icon
AgentIndex
magic-context logo
magic-context
★ 2.4k
vs
AgentRecall-MCP logo
AgentRecall-MCP
★ 371

magic-context vs AgentRecall-MCP

magic-context: Magic Context is a context and memory plugin for coding agent harnesses (OpenCode, Pi and OMP) that compresses history in the background, lifts decisions and conventions into project memory and recalls them each turn. It replaces the host's built-in compaction so one session per project can run for weeks without pauses.; 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

magic-context logo
magic-contextMemory & Context · ★ 2.4k

Keep one coding-agent session per project running for weeks

Read magic-context 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
magic-context logomagic-context
AgentRecall-MCP logoAgentRecall-MCP
Category
Memory & Context
Memory & Context
Stars
★ 2.4k
★ 371
License
MIT
MIT
Install Command
npx @cortexkit/magic-context@latest setup
claude mcp add --scope user agent-recall -- npx -y agent-recall-mcp
Updated
1d ago
1w ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
agent-framework, agent-memory, ai
agent-memory, ai-agents, claude-code
03

Features

magic-context logomagic-context
01Background history compression that lifts durable knowledge into project memory
02Overnight dreamer agents verify, deduplicate and curate memories
03Automatic recall each turn plus search across memories, past conversations and git history
04Setup wizard that configures OpenCode, Pi or OMP and disables built-in compaction
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

magic-context logomagic-context
↳Keep one coding-agent session per project running for weeks
↳Avoid compaction pauses that drop context mid-task
↳Give an agent memory of past decisions and project conventions
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
05

Best For

magic-context logomagic-context
EssentialTrending
AgentRecall-MCP logoAgentRecall-MCP
—
FAQ

FAQ

What is the difference between magic-context and AgentRecall-MCP?
Both magic-context and AgentRecall-MCP are in the Memory & Context category. magic-context has 2.4k stars, while AgentRecall-MCP has 371 stars.
Which is better, magic-context or AgentRecall-MCP?
The best choice depends on your use case. Choose magic-context if Keep one coding-agent session per project running for weeks, and AgentRecall-MCP if Maintain context across AI agent sessions (Claude Code, Cursor, etc.).
Is magic-context free or open source?
Yes, magic-context 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 magic-context →Alternatives to AgentRecall-MCP →magic-context details →AgentRecall-MCP details →