AI Dispatch
agent · ai security

Superagent vs Tellumen Agent

55 fields both were evaluated on, 23 of them different — including where one discloses something the other does not. Every value links to the document it came from. 32 further fields are disclosed by neither and are listed at the end rather than tabled.

Assurance

FieldSuperagentTellumen Agent
Audit trail·
Records a timestamped attestation of intent before a payment happens, so there is a real record of what was authorized if a dispute arises later.
tellumen.vercel.app · checked Aug 2, 2026
Explainability·
findings on the exact line, fixes as pull requests.
superagent.sh · checked Aug 4, 2026

Not in our latest capture. We captured this page again on Sep 16, 2026 and this quote was not there. How we re-check citations

Returns a verdict ( clean / minor issues / suspicious ) plus any prior report another agent already logged against that same source.
tellumen.vercel.app · checked Aug 2, 2026
Runtime governance·
runtime guardrails: deterministic rules that decide what your agent may do
runtime guardrails deterministic rules that decide what your agent may do.
superagent.sh · checked Aug 18, 2026
Spend guardrails are an advisory ledger, not wallet-level enforcement
tellumen.vercel.app · checked Aug 2, 2026
Evaluation coverage·
self-serve red teaming against what you actually run.
superagent.sh · checked Aug 4, 2026

Not in our latest capture. We captured this page again on Sep 16, 2026 and this quote was not there. How we re-check citations

Safety

FieldSuperagentTellumen Agent
Safety evaluations·
self-serve red teaming against what you actually run.
superagent.sh · checked Aug 4, 2026

Not in our latest capture. We captured this page again on Sep 16, 2026 and this quote was not there. How we re-check citations

Red teaming·
self-serve red teaming against what you actually run.
superagent.sh · checked Aug 4, 2026

Not in our latest capture. We captured this page again on Sep 16, 2026 and this quote was not there. How we re-check citations

Model or system card·
Data handling·
Records a source-tagged, timestamped observation about an entity. Never overwrites — prior observations are kept so contradictions stay visible instead of silently lost.
tellumen.vercel.app · checked Aug 2, 2026

Practicality

FieldSuperagentTellumen Agent
Pricing model·
pay-per-call REST routes ( /paid/* ) via x402
tellumen.vercel.app · checked Aug 2, 2026
Price point·
verify-agent-card and check-content-safety at $0.10/call, and get-dispute-evidence at $1.00/call
tellumen.vercel.app · checked Aug 2, 2026
Availability·
Deployment options·
you already work in your coding agent and github. so that's where superagent works too — no new workflows or tools to learn.
superagent.sh · checked Aug 4, 2026
https://tellumen-a2a-agent.onrender.com
tellumen.vercel.app · checked Aug 2, 2026
Integrations·
connect to github — keeps your repos secure
superagent.sh · checked Aug 4, 2026

Ecosystem

FieldSuperagentTellumen Agent
Protocols supported·
Ships MCP-related capability: a "contributor trust" API and MCP integration (per product changelog, 2026-08-11).
contributor trust api and mcp
superagent.sh · checked Aug 18, 2026

Not in our latest capture. We captured this page again on Sep 16, 2026 and this quote was not there. How we re-check citations

Tool use·
Deterministic runtime rules govern what agents may do; sensitive activity is confined to the endpoint
control it where it runs deterministic rules for what agents do, trust scores for everything they consume — and sensitive activity stays on the endpoint.
superagent.sh · checked Aug 18, 2026

Not in our latest capture. We captured this page again on Sep 16, 2026 and this quote was not there. How we re-check citations

17 skills are callable over the free A2A JSON-RPC endpoint
tellumen.vercel.app · checked Aug 2, 2026
Multi-agent·
another agent's orchestrator would read to decide whether to trust or invoke it
tellumen.vercel.app · checked Aug 2, 2026
API access·
Contributor Trust API and MCP integration shipped per product changelog (2026-08-11); no separate REST/webhooks API documented on current homepage.
contributor trust api and mcp
superagent.sh · checked Aug 18, 2026

Not in our latest capture. We captured this page again on Sep 16, 2026 and this quote was not there. How we re-check citations

Open source·

Impact

FieldSuperagentTellumen Agent
User base·
ubicloud, evry health, dotenvx, firecrawl, capchase, nango, mastra, paperclip
ubicloud evry health dotenvx firecrawl capchase nango mastra paperclip
superagent.sh · checked Aug 4, 2026
Deployment scale·
free for open source. the whole suite, on any public repo. private repos are paid — contact us and we'll set you up.
superagent.sh · checked Aug 4, 2026

Not in our latest capture. We captured this page again on Sep 16, 2026 and this quote was not there. How we re-check citations

Target sectors·
Security for AI-native developers
superagent.sh · checked Aug 4, 2026
High-risk domains·
payment spend — plus small-business data tooling other agents can call directly.
tellumen.vercel.app · checked Aug 2, 2026
Documented incidents·
Motivated directly by the July 2026 incident where an OpenAI cyber-testing agent escaped its sandbox and hacked an unrelated real company (Hugging Face)
tellumen.vercel.app · checked Aug 2, 2026

Disclosed by neither

Both Superagent and Tellumen Agent publish nothing on these 32 fields. That is a finding about the category rather than a difference between them, so it is recorded here instead of as 32 identical table rows. Each is shown with its source check on the individual profiles.

  • Autonomy level
  • Human oversight
  • Goal complexity
  • Action space
  • Operating environment
  • Initiative
  • Supported regions
  • Support model
  • Base models
  • Model provider
  • Model swappable
  • Open weights
  • Fine-tuning
  • Context window
  • Marketplace presence
  • Safety policy
  • Usage restrictions
  • Incident reporting
  • Third-party evaluations
  • Insurance available
  • Insurance carriers
  • Coverage limits
  • Indemnification
  • Liability cap
  • Tamper-evident log
  • Permission scopes
  • Compliance certifications
  • Regulatory alignment
  • Outcome-based pricing
  • Settlement mechanism
  • Dispute process
  • SLA terms

Questions

How do Superagent and Tellumen Agent compare on user base?
Superagent: ubicloud, evry health, dotenvx, firecrawl, capchase, nango, mastra, paperclip. Tellumen Agent: no public information disclosed.