What is AgentGPT?

A web interface for building and configuring autonomous AI agents. You assign each agent an objective, and it independently determines necessary tasks, executes them, and adapts based on results to achieve the goal.

Independently observed

AgentGPT pricing

We don't have AgentGPT's full plan breakdown yet (its pricing page resisted automated reading). Here's what we could confirm. Always check live pricing for exact numbers.

What AgentGPT does

The capabilities that matter for no code agent builders, normalised so it lines up with every alternative. “-” means we haven't confirmed it, not that it's missing.

Capabilities
Architecture model
Open source self hosted
Rag knowledge base document upload and chunking
-
Notion google drive confluence sync connectors
-
Visual drag and drop node canvas builder
-
Multi model selection openai anthropic local
Custom API tool calling and webhook execution
Team sharing and role based access control RBAC
-
Embeddable iframe or chat widget export
-
Agent memory and persistent conversation threads
-
Slack or microsoft teams bot deployment
-
SOC2 type ii
-
Mit or apache permissive oss license
Pricing model
Free open source
Independently observed

Platform & deployment

Independently observed
Platforms
  • Web
Deployment
  • Cloud / SaaS
  • Self-hosted

Integrations (3)

Independently observed
  • OpenAI
  • Serper
  • Replicate

Security & compliance

Known vulnerabilities: 0 (0 in the last 12 months) sourcea count reflects scale & disclosure, not quality

AgentGPT alternatives

Other no code agent builders we track, ranked by the same independent score.

All AgentGPT alternatives, ranked →

Compare AgentGPT

Side by side against other no code agent builders, attribute by attribute, with a source on every value.

Independent · unbought · dated

The Vioscale score: one lens on the evidence

Not user reviews and not a paid placement: a confidence-weighted blend of the independent signals below (adoption, activity, security posture, and more), which you can sort and re-weight yourself. Vendors can correct their listing but can never move their rank, and stars are weighted low as a vanity metric. It is one way to read the evidence for AgentGPT, not the verdict.

Balanced composite 37 / 100
low · 21%updating
Signal contributions to the composite score
SignalScoreWeightContributionEvidence
Release cadence940.054.9
Capabilities290.082.3
Stars860.032.2
Integrations170.071.2
Dependent projects00.060.0
Development activity00.090.0-
Security posture00.070.0-
Package downloads00.140.0-
Security score00.040.0-
Developer Q&A activity00.060.0-

Computed . Re-weight it by intent, or see the full method.

All data & sourcesshow ↓

Every value we hold, with its source, retrieval date, and confidence. This is the evidence behind the score: don't trust it, verify it.

Adoption

AttributeValueEvidence
Dependent repos0highsource · 2026-08-26 · 85%
Github stars36,303highsource · 2026-08-26 · 90%

Features

AttributeValueEvidence
CapabilitiesPricing model: free_open_source · Architecture model: open_source_self_hosted · Mit or apache permissive oss license: No · Multi model selection openai anthropic local: No · Custom api tool calling and webhook execution: Yesmediumsource · 2026-08-21 · 60%

Integrations

AttributeValueEvidence
Count3mediumsource · 2026-08-21 · 60%

Language

AttributeValueEvidence
PrimaryTypeScripthighsource · 2026-08-26 · 90%

License

AttributeValueEvidence
SpdxGPL-3.0highsource · 2026-08-26 · 95%

Pricing

AttributeValueEvidence
Free tierYesmediumsource · 2026-08-21 · 60%
Modelopen_sourcemediumsource · 2026-08-21 · 60%
Price levelfreemediumsource · 2026-08-21 · 60%

Release

AttributeValueEvidence
Cadence days10mediumsource · 2026-08-26 · 70%
History12 itemsmediumsource · 2026-08-26 · 70%

Security

AttributeValueEvidence
VulnerabilitiesCount: 0 · Source: https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=reworkd-platform&per_page=100 · Last 12m: 0highsource · 2026-08-26 · 90%