Hermes Agent

The agent that grows with you

Coding Agents Python Listed MIT

Is Hermes Agent safe? Strong public trust posture, backed by multiple independent signals. 2 published advisories affect its latest release.

OSSF Scorecard 6.4 / 10
Provenance Attested
Signed commits 8%
Last push today
Advisories 2, worst moderate
Compare Hermes Agent
Suggest a correction

In detail: Hermes Agent scores 85.1/100 (Grade A), ranked #92 of 1378 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 6.4/10; 8% of recent commits are signed; 2 published advisories affect its latest release (hermes-agent); last pushed 2026-10-17. Every point is earned from checkable signals — never paid placement. How scoring works →

Known advisories

Published advisories (from OSV) that affect the release you'd install today: hermes-agent 0.19.0. An unfixed critical advisory caps the HVTrust score at 64.9 (Grade C) and a high one at 79.9 (Grade B), until a fixed release ships; moderate, low and unrated ones are shown, not scored. Checked 2026-10-17.

  • MODERATE hermes-agent has an Uncontrolled Resource Consumption issue GHSA-pmqc-57g8-c22c · CVE-2026-10224 · hermes-agent 0.19.0 · published 2026-06-01
  • MODERATE hermes-agent has an Injection issue GHSA-xq8w-9jvx-gm3v · CVE-2026-10221 · hermes-agent 0.19.0 · published 2026-06-01

How Hermes Agent 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.

Chain of custody

Scanners check what the code says. This traces who ships Hermes Agent 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.

  1. Source Partly signed

    github.com/nousresearch/hermes-agent, MIT, last pushed 2026-10-17. 8% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.

  2. Review and release Mixed

    OpenSSF Scorecard rates the repository's practices 6.4/10 (scanned Oct 4, 2026). The checks that decide who can get a change released:

    • Code Review1
    • Branch Protection3
    • Signed Releasesn/a
    • Dangerous Workflow10
    • Token Permissions0
    • Pinned Dependencies8
    All 18 Scorecard checks
    Binary-Artifacts 10
    Branch-Protection 3
    CI-Tests 10
    CII-Best-Practices 0
    Code-Review 1
    Contributors 10
    Dangerous-Workflow 10
    Dependency-Update-Tool 10
    Fuzzing 0
    License 10
    Maintained 10
    Packaging 10
    Pinned-Dependencies 8
    SAST 10
    Security-Policy 10
    Signed-Releases -1
    Token-Permissions 0
    Vulnerabilities 0
  3. Published packages Partly attested

    • PyPI hermes-agent Source link isn't a GitHub repo Build provenance attested
  4. What you install today 2 advisories

    Latest release checked: hermes-agent 0.19.0. 2 published advisories affect it (OSV, checked 2026-10-17).

Changes to this chain

  • 2026-08-07 Provenance drift warning cleared (now: unknown)

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 Hermes Agent’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.

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 Hermes Agent compares in Coding Agents

  1. #4 Qwen Code 89.3 +4.2
  2. #5 Bernstein 89.2 +4.1
  3. #6 Hermes Agent 85.1 this agent
  4. #7 CodeWhale 84.3 −0.8
  5. #8 oh-my-pi 83.7 −1.4

Bars show each HVTrust score; the tick marks Hermes Agent’s 85.1.

Where the 85.1 comes from

HVTrust dimensions vs the Coding Agents average

85.1 / 100 · 100.0% confidence

Hermes Agent Coding Agents average (77 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
15.9 / 25
6.7 above avg 9.2
Identity / Provenance60% listing status · 40% build provenance
18.0 / 18
6.3 above avg 11.7
Transparency50% declared license · 50% OSSF Scorecard
13.9 / 17
2.0 above avg 11.9
Maintenance60% last-push freshness · 40% commit activity
20.0 / 20
5.2 above avg 14.8
AdoptionLog-scaled stars · package downloads
20.0 / 20
7.9 above avg 12.1

Quick Trust Read

What Would Improve It
Increase the share of verified signed commits for clearer maintainer identity.
Recent Changes
2026-10-14
Provider Added
Runtime surface grew — new detected provider dependencies: Amazon Bedrock, Anthropic, ElevenLabs, Firecrawl, Mistral AI, OpenAI, Postgres
2026-10-14
Rank Moved
Rank dropped 45 spots (#46 → #91)
2026-10-13
Provider Removed
Runtime surface shrank — no longer detected: Amazon Bedrock, Anthropic, ElevenLabs, Firecrawl, Mistral AI, OpenAI, Postgres
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 6.4/10. Tighten the weakest checks to improve public safety evidence.
Increase signed commits Raise the share of verified-signed commits to make maintainer identity and release history easier to trust.
100.0
Activity sub-score · out of 100
#6

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 →

Signals refreshed 2026-10-17 20:06 UTC · Repo last pushed today

Rank Trend

2026-09-29 2026-10-17

Activity & Reach

Stars
254.6k
Forks
55.4k
Last Push
2026-10-17
today
Commits (4 wk)
17589
Downloads (7d)
214,161
pypi
HN mentions (30d)
—
Open Issues
15980
Rank Change
=
was #92

Analysis

Activity Inputs

100.0 / 100
StarsRepository reach
30 / 30
FreshnessLast push recency
25.0 / 25
ActivityRecent commits
25 / 25
CommunityFork signal
20 / 20

Common questions about Hermes Agent

Public supply-chain signals for Hermes Agent are strong: it has multiple independent trust indicators in place. This does not replace your own security review, but Hermes Agent carries less obvious unverified-evidence risk than projects with thin signals.
Does Hermes Agent publish package provenance?
Yes. Hermes Agent's package releases carry build provenance attestations, which cryptographically link the published package back to its source repository and CI workflow.
Does Hermes Agent have an OpenSSF Scorecard?
Hermes Agent has an OpenSSF Scorecard score of 6.4/10. 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 Hermes Agent actively maintained?
Actively maintained. The repository was pushed to within the last 1 day(s).
What license does Hermes Agent use?
Hermes Agent ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are Hermes Agent's commits signed?
8% of the last 100 commits to Hermes Agent 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 Hermes Agent head-to-head

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
Hermes Agent appears to expose MCP server capabilities.
Detailed evidence is not shown in the public view.
External Service Dependencies
high confidence
7 detected
Public provider/service dependencies detected.
Credential signal: No explicit API-key/config marker detected.
Tool / Plugin Surface
high confidence
Declared
Declared plugin/integration surface detected.
  • browser
  • shell
Detailed evidence is not shown in the public view.
Package Provenance Drift
low confidence
Unknown
Package source metadata is missing or inconclusive
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 Hermes Agent'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.

2026-10-14
Provider Added
Runtime surface grew — new detected provider dependencies: Amazon Bedrock, Anthropic, ElevenLabs, Firecrawl, Mistral AI, OpenAI, Postgres
2026-10-13
Provider Removed
Runtime surface shrank — no longer detected: Amazon Bedrock, Anthropic, ElevenLabs, Firecrawl, Mistral AI, OpenAI, Postgres
2026-10-10
Provider Added
Runtime surface grew — new detected provider dependencies: Amazon Bedrock, Anthropic, ElevenLabs, Firecrawl, Mistral AI, OpenAI, Postgres
2026-10-10
Mcp Status Changed
Detected MCP server support changed: declared → implemented
2026-10-09
Provider Removed
Runtime surface shrank — no longer detected: Amazon Bedrock, Anthropic, ElevenLabs, Firecrawl, Mistral AI, OpenAI, Postgres
2026-10-09
Mcp Status Changed
Detected MCP server support changed: implemented → declared
2026-09-09
Provider Added
Runtime surface grew — new detected provider dependencies: Amazon Bedrock, Anthropic, ElevenLabs, Firecrawl, Mistral AI, OpenAI, Postgres
2026-09-09
Mcp Status Changed
Detected MCP server support changed: declared → implemented
2026-09-08
Provider Removed
Runtime surface shrank — no longer detected: Amazon Bedrock, Anthropic, ElevenLabs, Firecrawl, Mistral AI, OpenAI, Postgres
2026-09-08
Mcp Status Changed
Detected MCP server support changed: implemented → declared
2026-08-07
Drift Warning Cleared
Provenance drift warning cleared (now: unknown)

Maintain Hermes Agent?

For maintainers

HVTrust scores Hermes Agent 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.

Reputation Timeline

Signal history
Rank 10MCP 4Surface 3Surface 3Drift 1HVTrust 1
2026-10-14
Provider Added
Runtime surface grew — new detected provider dependencies: Amazon Bedrock, Anthropic, ElevenLabs, Firecrawl, Mistral AI, OpenAI, Postgres
2026-10-14
Rank Moved
Rank dropped 45 spots (#46 → #91)
2026-10-13
Provider Removed
Runtime surface shrank — no longer detected: Amazon Bedrock, Anthropic, ElevenLabs, Firecrawl, Mistral AI, OpenAI, Postgres
2026-10-13
Rank Moved
Rank rose 60 spots (#106 → #46)
2026-10-13
HVTrust Changed
HVTrust up 3.9pts (84.0 → 87.9)
2026-10-10
Provider Added
Runtime surface grew — new detected provider dependencies: Amazon Bedrock, Anthropic, ElevenLabs, Firecrawl, Mistral AI, OpenAI, Postgres
2026-10-10
Mcp Status Changed
Detected MCP server support changed: declared → implemented
2026-10-10
Rank Moved
Rank dropped 28 spots (#77 → #105)
2026-10-09
Provider Removed
Runtime surface shrank — no longer detected: Amazon Bedrock, Anthropic, ElevenLabs, Firecrawl, Mistral AI, OpenAI, Postgres
2026-10-09
Mcp Status Changed
Detected MCP server support changed: implemented → declared
2026-10-09
Rank Moved
Rank rose 27 spots (#104 → #77)
2026-09-28
Rank Moved
Rank rose 11 spots (#106 → #95)
2026-09-23
Rank Moved
Rank dropped 38 spots (#58 → #96)
2026-09-21
Rank Moved
Rank rose 38 spots (#96 → #58)
2026-09-09
Provider Added
Runtime surface grew — new detected provider dependencies: Amazon Bedrock, Anthropic, ElevenLabs, Firecrawl, Mistral AI, OpenAI, Postgres
2026-09-09
Mcp Status Changed
Detected MCP server support changed: declared → implemented
2026-09-09
Rank Moved
Rank dropped 23 spots (#55 → #78)
2026-09-08
Provider Removed
Runtime surface shrank — no longer detected: Amazon Bedrock, Anthropic, ElevenLabs, Firecrawl, Mistral AI, OpenAI, Postgres
2026-09-08
Mcp Status Changed
Detected MCP server support changed: implemented → declared
2026-09-08
Rank Moved
Rank rose 27 spots (#82 → #55)
2026-09-05
Rank Moved
Rank dropped 12 spots (#64 → #76)
2026-08-07
Drift Warning Cleared
Provenance drift warning cleared (now: unknown)

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 85.1 Grade A
Markdown:
[![HVTrust](https://hvtracker.net/badge/hermes-agent.svg)](https://hvtracker.net/agents/hermes-agent)
HTML:
<a href="https://hvtracker.net/agents/hermes-agent"><img src="https://hvtracker.net/badge/hermes-agent.svg" alt="HVTrust"></a>

Other agents in Coding Agents

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