GPT-5.6 (Sol / Terra / Luna) is now evaluated on TrustVector โ€” with day-1 independent verification, incl. METR's benchmark-cheating findings.

Read the evaluation
Evaluation record ยท superagi

SuperAGI

v0.x

Community

Agentautonomousself-hostedopen-sourceunmaintained
73
Adequate
About This Agent

UNMAINTAINED: the SuperAGI repository is dormant โ€” the last commit was January 2025 (an IDOR security fix) and the last release was v0.0.14 in January 2024; it is not recommended for new deployments. Formerly an open-source autonomous AI agent framework for running and managing multiple AI agents concurrently, with GUI-based management, a tool marketplace, and agent templates.

Last Evaluated: July 9, 2026
Official Website

Trust Vector Analysis

Dimension Breakdown

๐Ÿš€Performance & Reliability
+
autonomous execution

Autonomous task testing

Evidence
SuperAGI Documentation โ€” Autonomous agent execution with goal-oriented planning
mediumVerified: 2026-07-09
multi agent orchestration

Multi-agent coordination testing

Evidence
Agent Management โ€” Run multiple agents concurrently with resource management
mediumVerified: 2026-07-09
tool integration

Tool integration testing

Evidence
Tool Marketplace โ€” Extensive tool marketplace with 40+ pre-built tools
highVerified: 2026-07-09
planning capability

Planning effectiveness testing

Evidence
Agent Planning โ€” Multi-step planning with goal decomposition
mediumVerified: 2026-07-09
memory management

Memory system evaluation

Evidence
Vector Memory โ€” Vector-based memory for agent context retention
mediumVerified: 2026-07-09
latency

Performance monitoring

Evidence
Performance โ€” Depends on LLM calls, tool usage, and planning complexity
mediumVerified: 2026-07-09
๐Ÿ›ก๏ธSecurity
+
tool sandboxing

Security architecture review

Evidence
Tool Execution โ€” Limited sandboxing, tools execute with agent permissions
mediumVerified: 2026-07-09
self hosting

Deployment security assessment

Evidence
Deployment โ€” Full self-hosting with Docker Compose
highVerified: 2026-07-09
authentication

Authentication assessment

Evidence
Security Features โ€” Basic authentication, requires additional hardening
mediumVerified: 2026-07-09
open source

Open source assessment

Evidence
GitHub โ€” MIT license, 17.6k stars, source remains fully available but development is dormant
highVerified: 2026-07-09
api security

API security review

Evidence
API Documentation โ€” Basic API security, needs production hardening
mediumVerified: 2026-07-09
๐Ÿ”’Privacy & Compliance
+
data retention

Privacy architecture review

Evidence
Data Management โ€” Local database storage with configurable retention
mediumVerified: 2026-07-09
gdpr compliance

Compliance capabilities assessment

Evidence
Self-Hosted โ€” GDPR compliance possible with self-hosted deployment
mediumVerified: 2026-07-09
local deployment

Deployment options assessment

Evidence
Installation โ€” Complete local deployment with Docker Compose
highVerified: 2026-07-09
llm data sharing

Data flow analysis

Evidence
LLM Integration โ€” Agent data sent to configured LLM providers
mediumVerified: 2026-07-09
agent logs

Data storage assessment

Evidence
Logging โ€” Agent execution logs stored locally
mediumVerified: 2026-07-09
๐Ÿ‘๏ธTrust & Transparency
+
documentation quality

Documentation completeness review

Evidence
SuperAGI Docs โ€” Good documentation but still evolving
mediumVerified: 2026-07-09
gui interface

UI/UX assessment

Evidence
UI Features โ€” Web-based GUI for agent management and monitoring
highVerified: 2026-07-09
open source

Open source assessment

Evidence
GitHub โ€” MIT license, 17.6k stars; code transparent but no active development since January 2025
highVerified: 2026-07-09
agent traceability

Traceability features assessment

Evidence
Agent Logs โ€” Agent execution history and decision logs
mediumVerified: 2026-07-09
community support

Community engagement analysis

Evidence
Community โ€” Growing community, Discord support
GitHub Activity โ€” Maintainer activity has ceased (no commits since 2025-01-22); community itself flagged the project as inactive (issue #1431) and open issues go unanswered
highVerified: 2026-07-09
โš™๏ธOperational Excellence
+
ease of setup

Setup complexity assessment

Evidence
Installation Guide โ€” Docker Compose setup, requires technical knowledge
mediumVerified: 2026-07-09
scalability

Scalability testing

Evidence
Architecture โ€” Designed for small-medium scale, scaling requires work
mediumVerified: 2026-07-09
cost predictability

Pricing model analysis

Evidence
Open Source โ€” Free MIT license, costs only for infrastructure and LLMs
highVerified: 2026-07-09
monitoring

Monitoring features assessment

Evidence
Monitoring Features โ€” GUI-based monitoring, limited production metrics
mediumVerified: 2026-07-09
tool marketplace

Tool ecosystem assessment

Evidence
Tool Ecosystem โ€” Growing marketplace with 40+ tools
highVerified: 2026-07-09
production readiness

Production readiness assessment

Evidence
Maturity โ€” Early stage project, production use requires hardening
GitHub Repository Status โ€” Repository dormant: last commit 2025-01-22 (IDOR security fix), last release v0.0.14 (2024-01-16); no maintenance for ~18 months, unresolved issue backlog
highVerified: 2026-07-09
Strengths
  • +GUI-based agent management for easy monitoring and control
  • +Open source (MIT) with historically large community (17k+ stars)
  • +Tool marketplace with 40+ pre-built tools and extensibility
  • +Multi-agent orchestration for concurrent autonomous tasks
  • +Self-hosted deployment for data privacy and control
  • +Agent templates for quick start with common use cases
Limitations
  • !Early stage project with limited production maturity
  • !Limited enterprise features (security, monitoring, RBAC)
  • !Can be expensive due to multiple LLM calls in autonomous loops
  • !Autonomous agent reliability can be unpredictable
  • !Requires technical knowledge for setup and customization
  • !Limited documentation compared to more mature frameworks
  • !Unmaintained (2026-07): no commits since January 2025 and no releases since v0.0.14 (January 2024); security patches and dependency updates are not being shipped
Metadata
license: MIT
supported models
0: OpenAI GPT-4
1: GPT-3.5
2: Claude
3: PaLM
programming languages
0: Python
deployment type: Self-hosted (Docker Compose)
tool support
0: 40+ marketplace tools
1: Custom tools
2: API integrations
pricing model: Free open source
github stars: 17600+
first release: 2023
status: Dormant/unmaintained: last commit 2025-01-22, last release v0.0.14 (2024-01-16); repo not archived but inactive
database: PostgreSQL
agent features
0: Goal-oriented
1: Multi-agent
2: Tool marketplace
3: Web GUI
pricing: Free (MIT license)

Use Case Ratings

customer support

Can build support agents but better suited for autonomous tasks

code generation

Good for autonomous coding agents with tool integration

research assistant

Suitable for autonomous research and web scraping tasks

data analysis

Can integrate analysis tools for autonomous data work

content creation

Autonomous content generation possible but limited

education

Better for autonomous learning tasks than tutoring

healthcare

Early stage, not suitable for clinical use

financial analysis

Limited enterprise features for compliance

legal compliance

Can build document analysis agents with tools

creative writing

Good for autonomous ideation and research tasks