Is Cognee safe to use?

Cognee has an HVTrust score of 85.8/100 (Grade A), ranked #79 of 1371 tracked AI agent projects. This score reflects verifiable supply-chain integrity, transparency, maintenance, and adoption signals.

What is the trust score for Cognee?

Cognee scores 85.8/100 on HVTracker's evidence-weighted HVTrust scale. It has 31.9k GitHub stars and is categorized under Memory & Knowledge.

Cognee

Repository

Website

Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free

Memory & Knowledge Python Listed Apache-2.0

Is Cognee safe? Strong public trust posture, backed by multiple independent signals.

OSSF Scorecard 6.9 / 10

Provenance Attested

Signed commits 56%

Last push today

Advisories None known

Compare Cognee

How does it stack up against its Memory & Knowledge neighbours?

Pick any agent to compare →

Suggest a correction

In detail: Cognee scores 85.8/100 (Grade A), ranked #79 of 1371 tracked open-source AI agent projects, on evidence coverage B (3 of 5 independent signal types). The public evidence: its packages ship with cryptographic provenance; OSSF Scorecard rates its supply-chain practices 6.9/10; 56% of recent commits are signed; no published advisory affects its latest release (cognee); last pushed 2026-10-09. Every point is earned from checkable signals — never paid placement. How scoring works →

How Cognee could raise its score

Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.

Raise the OSSF Scorecard from 6.9 to 9.0lowest checks: CII-Best-Practices 0, Fuzzing 0, Token-Permissions 0 +3.1 → 88.9 A · #1 of 49
Sign every commit56% signed today +1.5 → 87.3 A · #4 of 49

Already done? Suggest a correction Add the trust badge

Chain of custody

Scanners check what the code says. This traces who ships Cognee and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.

Source Partly signed

github.com/topoteretes/cognee, Apache-2.0, last pushed 2026-10-09. 56% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.
Review and release Mixed

OpenSSF Scorecard rates the repository's practices 6.9/10 (scanned Oct 9, 2026). The checks that decide who can get a change released:
- Code Review4
- Branch Protectionn/a
- Signed Releases10
- Dangerous Workflow10
- Token Permissions0
- Pinned Dependencies8
All 18 Scorecard checks

Binary-Artifacts 10

Branch-Protection -1

CI-Tests 10

CII-Best-Practices 0

Code-Review 4

Contributors 10

Dangerous-Workflow 10

Dependency-Update-Tool 10

Fuzzing 0

License 10

Maintained 10

Packaging 10

Pinned-Dependencies 8

SAST 7

Security-Policy 9

Signed-Releases 10

Token-Permissions 0

Vulnerabilities 0
Published packages Linked and attested
- PyPI cognee Source link points back to this repo Build provenance attested
What you install today No known advisories

Latest release checked: cognee 1.6.3. No published advisory affects it (OSV, checked 2026-10-09).

Changes to this chain

2026-09-03 Package provenance attestation detected

Evidence behind this score

Coverage B: 3 of 5 independent evidence types found.

GitHub repository data
Package downloads
Supply-chain checks
Public actions (missing)
Community mentions (missing)

Verify this score yourself

Every build re-issues Cognee’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.

Signed credential (JSON) How to verify

What this score doesn’t check

It covers who ships the code, not what the code does. It doesn’t read tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.

How Cognee compares in Memory & Knowledge

Bars show each HVTrust score; the tick marks Cognee’s 85.8.

Where the 85.8 comes from

HVTrust dimensions vs the Memory & Knowledge average

85.8 / 100 · 100.0% confidence

Cognee Memory & Knowledge average (49 agents)

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

18.9 / 25

7.6 above avg 11.3

Identity / Provenance60% listing status · 40% build provenance

18.0 / 18

5.4 above avg 12.6

Transparency50% declared license · 50% OSSF Scorecard

14.4 / 17

1.8 above avg 12.6

Maintenance60% last-push freshness · 40% commit activity

20.0 / 20

2.6 above avg 17.4

AdoptionLog-scaled stars · package downloads

16.7 / 20

3.5 above avg 13.2

Quick Trust Read

What Would Improve It

Improve safety / integrity to lift the weakest part of the trust profile.

Recent Changes

2026-10-09

Rank Moved

Rank rose 11 spots (#90 → #79)

2026-10-06

Rank Moved

Rank dropped 17 spots (#72 → #89)

2026-09-25

Rank Moved

Rank rose 10 spots (#79 → #69)

Maintainer Checklist

Raise Scorecard signals Current OSSF Scorecard is 6.9/10. Tighten the weakest checks to improve public safety evidence.

Compare with ReMe Get email alerts for Cognee View Memory & Knowledge Report missing data

93.4

Activity sub-score · out of 100

In Memory & Knowledge

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade A reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage B is separate — it grades how many independent signal types back the score (3 of 5), so a high score on thin evidence stays visible. Full methodology →

Rank Trend

2026-09-29 2026-10-09

Activity & Reach

Stars

31.9k

Forks

3.3k

Last Push

2026-10-09

today

Commits (4 wk)

958

Downloads (7d)

26,949

pypi

HN mentions (30d)

—

Open Issues

327

Rank Change

▲11

was #90

Analysis

Activity Inputs

93.4 / 100

StarsRepository reach

27.0 / 30

FreshnessLast push recency

25.0 / 25

ActivityRecent commits

25 / 25

CommunityFork signal

16.4 / 20

Common questions about Cognee

Public supply-chain signals for Cognee are strong: it has multiple independent trust indicators in place. This does not replace your own security review, but Cognee carries less obvious unverified-evidence risk than projects with thin signals.

Does Cognee publish package provenance?

Yes. Cognee's package releases carry build provenance attestations, which cryptographically link the published package back to its source repository and CI workflow.

Does Cognee have an OpenSSF Scorecard?

Cognee has an OpenSSF Scorecard score of 6.9/10. 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 Cognee actively maintained?

Actively maintained. The repository was pushed to within the last 1 day(s).

What license does Cognee use?

Cognee ships under Apache-2.0. A declared, OSI-approved license is one of the transparency signals HVTrust scores.

Are Cognee's commits signed?

56% of the last 100 commits to Cognee 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.

Compare Cognee head-to-head

Cognee vs ReMe → Cognee vs OpenViking → Cognee vs LanceDB →

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

Cognee appears to expose MCP server capabilities.

Detailed evidence is not shown in the public view.

External Service Dependencies

high confidence

9 detected

Public provider/service dependencies detected.

Credential signal: API keys or service config markers documented.

Tool / Plugin Surface

high confidence

Extensions

Extension based plugin/integration surface detected.

browser
code
database
search

Detailed evidence is not shown in the public view.

Package Provenance Drift

high confidence

Match

Published package metadata matches the tracked repo

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 Cognee'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.

2026-09-19

Tool Surface Changed

Detected tool/plugin surface changed: none → extension-based

2026-09-03

Provenance Added

Package provenance attestation detected

Maintain Cognee?

For maintainers

HVTrust scores Cognee 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

2026-10-09

Rank Moved

Rank rose 11 spots (#90 → #79)

2026-10-06

Rank Moved

Rank dropped 17 spots (#72 → #89)

2026-09-25

Rank Moved

Rank rose 10 spots (#79 → #69)

2026-09-23

Rank Moved

Rank dropped 24 spots (#60 → #84)

2026-09-21

Rank Moved

Rank rose 43 spots (#103 → #60)

2026-09-19

Tool Surface Changed

Detected tool/plugin surface changed: none → extension-based

2026-09-19

Rank Moved

Rank dropped 15 spots (#85 → #100)

2026-09-17

Rank Moved

Rank rose 10 spots (#97 → #87)

2026-09-05

Rank Moved

Rank dropped 19 spots (#67 → #86)

2026-09-03

Provenance Added

Package provenance attestation detected

2026-09-03

Grade Changed

Trust grade B → A

2026-09-03

Rank Moved

Rank rose 154 spots (#218 → #64)

2026-09-03

HVTrust Changed

HVTrust up 14.4pts (69.1 → 83.5)

2026-08-31

Rank Moved

Rank dropped 25 spots (#189 → #214)

2026-08-29

Rank Moved

Rank dropped 10 spots (#182 → #192)

2026-08-26

Rank Moved

Rank dropped 14 spots (#160 → #174)

2026-08-24

Rank Moved

Rank dropped 10 spots (#148 → #158)

2026-08-22

Rank Moved

Rank rose 10 spots (#153 → #143)

2026-08-17

Rank Moved

Rank rose 11 spots (#151 → #140)

2026-08-08

Rank Moved

Rank dropped 12 spots (#126 → #138)

2026-07-13

Rank Moved

Rank dropped 14 spots (#105 → #119)

GitHub → Website → PyPI: cognee

Embed Badge Badge guide for maintainers →

For maintainers

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

Other agents in Memory & Knowledge

Data sources
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON

Cognee

How Cognee could raise its score

Chain of custody

Source Partly signed

Review and release Mixed

Published packages Linked and attested

What you install today No known advisories

Changes to this chain

Evidence behind this score

Verify this score yourself

What this score doesn’t check

How Cognee compares in Memory & Knowledge

Where the 85.8 comes from

HVTrust dimensions vs the Memory & Knowledge average

Quick Trust Read

Rank Trend

Activity & Reach

Analysis

Activity Inputs

Common questions about Cognee

Compare Cognee head-to-head

AI agent surface

Maintain Cognee?

Reputation Timeline

Embed Badge Badge guide for maintainers →

Other agents in Memory & Knowledge