Letta (MemGPT)

Robust open-source agent system with strong API/docs and MCP support, tempered by hosted training on user data and recent RCE vuln.

73
Trust score
Visit Letta (MemGPT)Stale · Not verified
✓ Our Verdict

trains_on_user_data (hosted service prompts used for model training without opt-out)

Trust Breakdown

73
Trust scoreSolid
AGENT
75
Autonomous workflow delegation
TRUST
75
Transparency & verification
INTEROP
70
Protocol compatibility breadth
SECURE
55
Security controls & audit trail
DOCS
90
Documentation completeness
How these scores are calculated →

What It Actually Does

Robust open-source agent system with strong API/docs and MCP support, tempered by hosted training on user data and recent RCE vuln.

Fit Assessment

Best for

Agent System
73
Letta (MemGPT)
Solid · 73/100
Visit Letta (MemGPT)

Score Breakdown

AGENT
75
Autonomous workflow delegation
TRUST
75
Transparency & verification
INTEROP
70
Protocol compatibility breadth
SECURE
55
Security controls & audit trail
DOCS
90
Documentation completeness

Protocol Support

MCP—
A2A—
A2H—
REST API—
Agent-callable—

Capabilities

Transaction capable—
ACP support—
Audit trace—

Pricing

Free

Workflow Fit

Agent System

Related Categories

Ready to evaluate Letta (MemGPT) in your stack?
Composite score: 73
Visit Letta (MemGPT)