AgentIndex icon
AgentIndex
akb logo
akb
★ 163
vs
AgentRecall-MCP logo
AgentRecall-MCP
★ 371

akb vs AgentRecall-MCP

akb: AKB is an agent knowledgebase that serves organizational memory for AI agents over the Model Context Protocol (MCP). It provides hybrid semantic + keyword search, structured tables, files, and a URI graph, all backed by Git for version history. Designed as a drop-in alternative to Confluence or Notion for MCP-aware agents like Claude Code, Cursor, and Windsurf.; 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

akb logo
akbMemory & Context · ★ 163

Provide persistent memory and knowledge management for AI coding agents

Read akb 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
akb logoakb
AgentRecall-MCP logoAgentRecall-MCP
Category
Memory & Context
Memory & Context
Stars
★ 163
★ 371
License
NOASSERTION
MIT
Install Command
cp config/app.yaml.example config/app.yaml && cp config/secret.yaml.example config/secret.yaml && docker compose up -d
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, claude, claude-code
agent-memory, ai-agents, claude-code
03

Features

akb logoakb
01Git-backed version history for all documents and files
02MCP (Model Context Protocol) integration via Streamable HTTP and stdio
03Hybrid search (dense + BM25) with RRF fusion
04Structured documents and tables with Markdown and YAML frontmatter
05Explicit knowledge graph with relations (depends_on, related_to, implements)
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

akb logoakb
↳Provide persistent memory and knowledge management for AI coding agents
↳Replace Confluence or Notion for agent-accessible documentation
↳Manage complex project knowledge with structured docs, tables, and graph relationships
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 akb and AgentRecall-MCP?
Both akb and AgentRecall-MCP are in the Memory & Context category. akb has 163 stars, while AgentRecall-MCP has 371 stars.
Which is better, akb or AgentRecall-MCP?
The best choice depends on your use case. Choose akb if Provide persistent memory and knowledge management for AI coding agents, and AgentRecall-MCP if Maintain context across AI agent sessions (Claude Code, Cursor, etc.).
Is akb free or open source?
Yes, akb is open source on GitHub (NOASSERTION).
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 akb →Alternatives to AgentRecall-MCP →akb details →AgentRecall-MCP details →