Is deep-research safe to use?

deep-research has an HVTrust score of 39.0/100 (Grade D), ranked #1180 of 1328 tracked AI agent projects. This score reflects verifiable supply-chain integrity, transparency, maintenance, and adoption signals.

What is the trust score for deep-research?

deep-research scores 39.0/100 on HVTracker's evidence-weighted HVTrust scale. It has 4.7k GitHub stars and is categorized under Research & Data.

deep-research

u14app/deep-research

Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.

Research & Data JavaScript Grade D Listed MIT

39.0/100

Rank #1180 of 1328

Compare deep-research

How does it stack up against its Research & Data neighbours?

Pick any agent to compare →

Thin or incomplete trust evidence. Review carefully before production use.

Open compare tool Suggest correction

Listing state

Listed

Evidence coverage

Grade C · 2/5 signals

Last push

2026-06-18 · 94d ago

Recent change

Stale

Is deep-research safe? deep-research scores 39.0/100 (Grade D), ranked #1180 of 1328 tracked open-source AI agent projects, on evidence coverage C (2 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 2.8/10; 5% of recent commits are signed; last pushed 2026-06-18. Every point is earned from checkable signals — never paid placement. How scoring works →

Ranked neighbours in Research & Data

#22 MiroThinker — 42.8 (D) → #23 Sotopia agents — 41.0 (D) → #25 auto-deep-researcher-24x7 — 38.6 (D) → #26 Open Deep Research (dzhng) — 36.1 (D) →

Quick Trust Read

What Would Improve It

Publish package provenance or release attestations for stronger supply-chain evidence.

Recent Changes

2026-09-16

Activity Went Stale

No commits for 90 days

2026-09-12

Rank Moved

Rank dropped 10 spots (#1156 → #1166)

2026-09-09

Rank Moved

Rank dropped 12 spots (#1141 → #1153)

Maintainer Checklist

Raise Scorecard signals Current OSSF Scorecard is 2.8/10. Tighten the weakest checks to improve public safety evidence.

Publish provenance Add package provenance or release attestations so users can verify where shipped artifacts came from.

Increase signed commits Raise the share of verified-signed commits to make maintainer identity and release history easier to trust.

Refresh maintenance signals The repo was last pushed 94 days ago. Fresh activity helps separate stable projects from stale ones.

Compare with another agent Get email alerts for deep-research View Research & Data Report missing data

48.0

Activity sub-score · out of 100

#24

In Research & Data

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade D reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage C is separate — it grades how many independent signal types back the score (2 of 5), so a high score on thin evidence stays visible. Full methodology →

Rank Trend

2026-08-11 2026-09-20

Activity & Reach

Stars

4.7k

Forks

1.1k

Last Push

2026-06-18

94 days ago

Commits (4 wk)

Downloads (7d)

—

HN mentions (30d)

—

Open Issues

Rank Change

▼2

was #1178

Analysis

HVTrust Dimensions vs Research & Data

39.0 / 100 · 100.0% confidence

deep-research Research & Data average (33 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits

3.8 / 25

4.4 below avg 8.2

Identity / Provenance60% listing status · 40% build provenance

10.8 / 18

1.1 below avg 11.9

Transparency50% declared license · 50% OSSF Scorecard

10.9 / 17

0.9 below avg 11.8

Maintenance60% last-push freshness · 40% commit activity

5.7 / 20

7.1 below avg 12.8

AdoptionLog-scaled stars · package downloads

8.8 / 20

2.1 below avg 10.9

Activity Inputs

48.0 / 100

StarsRepository reach

22.0 / 30

FreshnessLast push recency

11.9 / 25

ActivityRecent commits

0.0 / 25

CommunityFork signal

14.1 / 20

Supply Chain Trust

Package Provenance

None

No package attestations found

OSSF Scorecard

2.8 / 10

OpenSSF Scorecard · scanned Sep 18, 2026

Signed Commits

of last 100 commits verified

Binary-Artifacts 10

Branch-Protection 0

CI-Tests 0

CII-Best-Practices 0

Code-Review 2

Contributors 10

Dangerous-Workflow 10

Dependency-Update-Tool 0

Fuzzing 0

License 10

Maintained 0

Packaging 10

Pinned-Dependencies 0

SAST 0

Security-Policy 0

Signed-Releases 0

Token-Permissions 0

Vulnerabilities 0

Is deep-research safe?

Public trust evidence for deep-research is thin: several supply-chain signals are missing or weak. This does not mean the project is unsafe — it means an outside observer cannot easily verify the usual integrity checks. Treat with extra scrutiny.

Does deep-research publish package provenance?

No published build provenance is currently detected for deep-research. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.

Does deep-research have an OpenSSF Scorecard?

deep-research has an OpenSSF Scorecard score of 2.8/10. The Scorecard checks for branch protection, signed releases, dependency updates, fuzzing, code review, and other supply-chain hygiene items. See the full check breakdown on this page.

Is deep-research actively maintained?

Slowing down. Last push was 94 days ago — keep an eye on whether activity resumes.

What license does deep-research use?

deep-research ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.

Are deep-research's commits signed?

5% of the last 100 commits to deep-research are verified-signed (GPG, SSH, S/MIME, or GitHub's signing flow). Signed commits help confirm that code was authored by who the commit claims.

Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.

AI agent surface

MCP, providers, tool surface

Scored in HVTrust

These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →

MCP Server Support

high confidence

Implemented

deep-research appears to expose MCP server capabilities.

Detailed evidence is not shown in the public view.

External Service Dependencies

high confidence

5 detected

Public provider/service dependencies detected.

Credential signal: API keys or service config markers documented.

Tool / Plugin Surface

None detected

No clear plugin system or broad tool surface detected.

Detailed evidence is not shown in the public view.

Package Provenance Drift

N/A

No package source configured

Detailed evidence is not shown in the public view.

MCP signal live
External deps live
Tool / plugin surface live
Package provenance drift live

How this surface has changed

Detected changes to deep-research's runtime surface and supply-chain posture, from daily public-signal snapshots. A change here means our detectors see something different — a genuinely changed capability, or better evidence of an existing one.

2026-09-16

Activity Went Stale

No commits for 90 days

Maintain deep-research?

For maintainers

HVTrust scores deep-research from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.

Submit a correction → Add the trust badge

Reputation Timeline

Signal history

2026-09-16

Activity Went Stale

No commits for 90 days

2026-09-12

Rank Moved

Rank dropped 10 spots (#1156 → #1166)

2026-09-09

Rank Moved

Rank dropped 12 spots (#1141 → #1153)

2026-09-08

Rank Moved

Rank dropped 14 spots (#1127 → #1141)

2026-09-07

Rank Moved

Rank dropped 23 spots (#1104 → #1127)

2026-09-06

Rank Moved

Rank dropped 15 spots (#1089 → #1104)

2026-09-05

Rank Moved

Rank dropped 40 spots (#1049 → #1089)

2026-09-04

Rank Moved

Rank dropped 27 spots (#1022 → #1049)

2026-09-03

Rank Moved

Rank dropped 55 spots (#967 → #1022)

2026-09-02

Rank Moved

Rank dropped 49 spots (#918 → #967)

2026-09-01

Rank Moved

Rank dropped 42 spots (#876 → #918)

2026-08-31

Rank Moved

Rank dropped 24 spots (#852 → #876)

2026-08-30

Scorecard Added

OSSF Scorecard: 2.8/10

2026-08-30

Rank Moved

Rank rose 416 spots (#1268 → #852)

2026-08-30

HVTrust Changed

HVTrust up 23.6pts (16.8 → 40.4)

2026-08-29

Rank Moved

Rank dropped 12 spots (#1256 → #1268)

2026-08-28

Rank Moved

Rank dropped 10 spots (#1246 → #1256)

2026-08-26

Rank Moved

Rank dropped 30 spots (#1208 → #1238)

2026-08-16

Rank Moved

Rank dropped 25 spots (#1181 → #1206)

2026-08-10

Rank Moved

Rank dropped 70 spots (#1104 → #1174)

2026-08-08

Rank Moved

Rank dropped 597 spots (#505 → #1102)

2026-08-06

Newly Listed

First tracked at rank #504

GitHub →

Embed Badge Badge guide for maintainers →

For maintainers

Markdown:
            [![HVTrust](https://hvtracker.net/badge/deep-research.svg)](https://hvtracker.net/agents/deep-research)
            
HTML:
            <a href="https://hvtracker.net/agents/deep-research"><img src="https://hvtracker.net/badge/deep-research.svg" alt="HVTrust"></a>

Other agents in Research & Data

Data sources
GitHub REST API (repo, commits, stars, forks, license) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.3 · Raw JSON