agent · research

GPT Researcher

GPT Researcher is an open-source autonomous research agent. Per the project's own site it takes a question, gathers information from multiple online sources, and returns an organised report with comprehensive cited sources; it supports any LLM (OpenAI, Anthropic, Groq, Llama 3 and Hugging Face are named), any search engine (Google, Bing, Tavily and DuckDuckGo are named), and can be added to a team of agents to collaborate on research. The project states it ranked first on Carnegie Mellon University's DeepResearchGym benchmark of deep research systems over 1,000 complex queries in May 2025 - an independent evaluator, though the benchmark result itself is reported by the project and we have not verified it against the evaluator's own publication. It reports millions of downloads and hundreds of contributors. On assurance the page is silent throughout: no runtime limit on scope, spend or authority, no record of what the agent did, no compliance certification, no insurance, indemnity or outcome-linked payment term is published on the page checked. All five trust-gap dimensions score 0 on this evidence, which is the expected shape for an open-source project distributed without warranty.

gptr.devevidence retrieved Aug 1, 2026view as JSON all research entries 20 alternatives

Reviewed12 or more fields evidenced, and scored by a human against the published rubric

16 fields evidenced · 39 with no public information. Every value below links to the document it came from and the date we checked it.

16 of them are quoted but not yet interpreted: we hold the source sentence and the date we read it, but nobody has written the answer to the question yet. Those rows show the quote and say so rather than repeating it back as an answer. Why these exist

1 of those is flagged for review: our own check found language in the cited source that may address the field. An editor has not adjudicated it yet.

Trust gap

How this is scored

Runtime governance

0/3

Are scope, spend, and authority enforced while the agent runs?

No public evidence found. The page checked publishes no limit on scope, spend or authority, no permission model and no kill switch. It is an open-source research agent whose page is entirely capability copy.

How this gap gets closed →

Audit trail

0/3

Is there a tamper-evident record of what it actually did?

No public evidence found. "GPT Researcher provides comprehensive cited sources for the research results" is source citation in the output, not a record of what the agent did; nothing on the page describes an action log, retention or review.

How this gap gets closed →

Compliance

0/3

Are compliance obligations attached per engagement?

No public evidence found. No certification, framework mapping, auditor or report date appears on the page checked.

How this gap gets closed →

Outcome settlement

0/3

Does payment depend on a verified result?

No public evidence found. No pricing or payment terms of any kind appear on the page checked; the project is distributed as open source.

How this gap gets closed →

Insurance & indemnity

0/3

Can the deployment be insured, and is the customer indemnified?

No public evidence found. No cover, carrier, limit or customer indemnity is published. Consistent with an open-source distribution, which typically disclaims warranty rather than indemnifying.

How this gap gets closed →

Assurance

Insurance available: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Insurance carriers: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Coverage limits: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Indemnification: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Liability cap: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Audit trail: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Tamper-evident log: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Explainability: not yet interpreted
“GPT Researcher provides comprehensive cited sources for the research results.”
gptr.dev · checked Aug 1, 2026
Runtime governance: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Permission scopes: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Compliance certifications: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Regulatory alignment: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Outcome-based pricing: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Settlement mechanism: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Dispute process: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
SLA terms: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Evaluation coverage: not yet interpreted
“Ranked #1 in Academic Benchmarks Carnegie Mellon University's DeepResearchGym (May 2025) evaluated leading deep research systems on 1,000 complex queries.”
gptr.dev · checked Aug 1, 2026

Agency

Autonomy level: not yet interpreted
“Autonomous AI Research Agent”
gptr.dev · checked Aug 1, 2026
Human oversight: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Goal complexity: not yet interpreted
“Research anything, effortlessly: Whether it's company briefs, people and markets analysis, trend spotting, market research, talent recruitment, travel planning, medical studies, stock analysis or business insights”
gptr.dev · checked Aug 1, 2026
Action space: not yet interpreted
“GPT Researcher takes care of everything from accurate source gathering to organization of research results with citations.”
gptr.dev · checked Aug 1, 2026
Operating environment: not yet interpreted
“GPT Researcher will start gathering information from multiple online trusted sources.”
gptr.dev · checked Aug 1, 2026
Initiative: not yet interpreted
“GPT Researcher will start the research process”
gptr.dev · checked Aug 1, 2026

Safety

Safety evaluations: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Red teaming: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Safety policy: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Usage restrictions: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Model or system card: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Incident reporting: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Third-party evaluations: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Data handling: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this

Practicality

Pricing model: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Price point: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Availability: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Deployment options: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Integrations: not yet interpreted
“Use any Search Engine Conduct research with any search engine from Google, Bing to Tavily and DuckDuckGo.”
gptr.dev · checked Aug 1, 2026
Supported regions: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Support model: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this

Foundation models

Base models: not yet interpreted
“Support for all LLMs Easily connect any LLM of your choice from OpenAI, Anthropic, Groq to Llama 3 and HF.”
gptr.dev · checked Aug 1, 2026
Model provider: not yet interpreted
“Support for all LLMs Easily connect any LLM of your choice from OpenAI, Anthropic, Groq to Llama 3 and HF.”
gptr.dev · checked Aug 1, 2026
Model swappable: not yet interpreted
“You can also train your own LLMs and use them with GPT Researcher.”
gptr.dev · checked Aug 1, 2026
Open weights: no public information
Flagged for review — the source below contains language that may address this field. Not yet checked by an editor. How we check absences
gptr.dev · checked Aug 1, 2026
Fine-tuning: not yet interpreted
“You can also train your own LLMs and use them with GPT Researcher.”
gptr.dev · checked Aug 1, 2026
Context window: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this

Ecosystem

Protocols supported: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Tool use: not yet interpreted
“GPT Researcher will start gathering information from multiple online trusted sources.”
gptr.dev · checked Aug 1, 2026
Multi-agent: not yet interpreted
“Multi-Agent Support Add GPT Researcher to a team of agents to collaborate on research.”
gptr.dev · checked Aug 1, 2026
API access: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Open source: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Marketplace presence: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this

Impact

User base: not yet interpreted
“With millions of downloads and hundreds of contributions worldwide”
gptr.dev · checked Aug 1, 2026
Deployment scale: not yet interpreted
“With millions of downloads and hundreds of contributions worldwide, GPT Researcher is the go-to solution for AI-powered research.”
gptr.dev · checked Aug 1, 2026
Target sectors: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
High-risk domains: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this
Documented incidents: no public information
gptr.dev · checked Aug 1, 2026 · source did not state this

Compared with

Side-by-side on the fields where GPT Researcher and the other entry are both on record and actually differ.