AgentIndex icon
AgentIndex
AgentRecall-MCP logo
AgentRecall-MCP
★ 371
vs
dreamgraph logo
dreamgraph
★ 127

AgentRecall-MCP vs dreamgraph

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.; dreamgraph: DreamGraph is a cognitive layer for software systems that continuously discovers, verifies, and resolves problems using structured reasoning loops. It augments software development with autonomous reasoning loops, structured knowledge graphs, evidence-based validation, and controlled speculative exploration, ultimately building an abstract representation of system intent.

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 →
dreamgraph logo
dreamgraphMemory & Context · ★ 127

Automated system architecture discovery and documentation

Read dreamgraph full review →
02

Side-by-Side Comparison

Field
AgentRecall-MCP logoAgentRecall-MCP
dreamgraph logodreamgraph
Category
Memory & Context
Memory & Context
Stars
★ 371
★ 127
License
MIT
NOASSERTION
Install Command
claude mcp add --scope user agent-recall -- npx -y agent-recall-mcp
git clone https://github.com/mikajussila/dreamgraph.git && cd dreamgraph && npm install && npm run build
Updated
1w ago
2w ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
agent-memory, ai-agents, claude-code
agent-memory, ai-agents, autonomous-agents
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
dreamgraph logodreamgraph
01Autonomous reasoning loops and knowledge graphs
02Evidence-based verification with Truth Filter
03Controlled speculative exploration ('dreaming')
04Self-cleaning memory via decay and resolution
05Adversarial security scanning (NIGHTMARE state)
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
dreamgraph logodreamgraph
↳Automated system architecture discovery and documentation
↳Continuous security vulnerability detection and remediation
↳Cross-platform application transcompilation from intent abstraction
FAQ

FAQ

What is the difference between AgentRecall-MCP and dreamgraph?
Both AgentRecall-MCP and dreamgraph are in the Memory & Context category. AgentRecall-MCP has 371 stars, while dreamgraph has 127 stars.
Which is better, AgentRecall-MCP or dreamgraph?
The best choice depends on your use case. Choose AgentRecall-MCP if Maintain context across AI agent sessions (Claude Code, Cursor, etc.), and dreamgraph if Automated system architecture discovery and documentation.
Is AgentRecall-MCP free or open source?
Yes, AgentRecall-MCP is open source on GitHub (MIT).
Is dreamgraph free or open source?
Yes, dreamgraph is open source on GitHub (NOASSERTION).
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 dreamgraph →AgentRecall-MCP details →dreamgraph details →