updated 2026-10-09 16:07 UTC

AgentOps

Repository Website

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

Observability & Evaluation Python Listed MIT

Is AgentOps safe? Thin or incomplete trust evidence. Review carefully before production use.

OSSF Scorecard 3.5 / 10
Provenance None
Signed commits 100%
Last push 106d ago
Advisories None known
Compare AgentOps

How does it stack up against its Observability & Evaluation neighbours?

Pick any agent to compare →
Suggest a correction

In detail: AgentOps scores 53.6/100 (Grade C), ranked #856 of 1371 tracked open-source AI agent projects, on evidence coverage A (4 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 3.5/10; 100% of recent commits are signed; no published advisory affects its latest release (agentops); last pushed 2026-06-25. Every point is earned from checkable signals — never paid placement. How scoring works →

How AgentOps 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.

Already done? Suggest a correctionAdd the trust badge

Chain of custody

Scanners check what the code says. This traces who ships AgentOps 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 Signed

    github.com/agentops-ai/agentops, MIT, last pushed 2026-06-25. 100% of the last 100 commits carry a verified signature, so changes trace to a verified account.

  2. Review and release Weak

    OpenSSF Scorecard rates the repository's practices 3.5/10 (scanned Jun 22, 2026, refresh pending). The checks that decide who can get a change released:

    • Code Review1
    • Branch Protection5
    • Signed Releasesn/a
    • Dangerous Workflown/a
    • Token Permissionsn/a
    • Pinned Dependenciesn/a
    All 18 Scorecard checks
    Binary-Artifacts 10
    Branch-Protection 5
    CI-Tests 1
    CII-Best-Practices 0
    Code-Review 1
    Contributors 10
    Dangerous-Workflow -1
    Dependency-Update-Tool 0
    Fuzzing 0
    License 10
    Maintained 0
    Packaging -1
    Pinned-Dependencies -1
    SAST 0
    Security-Policy 0
    Signed-Releases -1
    Token-Permissions -1
    Vulnerabilities 10

  3. Published packages Linked, not attested

    • PyPI agentops Source link points back to this repo No build attestation

    Without a build attestation, nothing proves the published files were built from this repository.

  4. What you install today No known advisories

    Latest release checked: agentops 0.4.21. No published advisory affects it (OSV, checked 2026-10-09).

Changes to this chain

No change to package provenance, package source links, Scorecard coverage or license in HVTracker's daily snapshots of AgentOps.

Evidence behind this score

Coverage A: 4 of 5 independent evidence types found.

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

Verify this score yourself

Every build re-issues AgentOps’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 AgentOps compares in Observability & Evaluation

  1. #18 agentacct 55.7 +2.1
  2. #19 Ragas 53.6 ±0
  3. #20 AgentOps 53.6 this agent
  4. #21 TruLens 47.3 −6.3
  5. #22 SimWorld 41.2 −12.4

Bars show each HVTrust score; the tick marks AgentOps’s 53.6.

Where the 53.6 comes from

HVTrust dimensions vs the Observability & Evaluation average

53.6 / 100 · 100.0% confidence

AgentOps Observability & Evaluation average (26 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
9.4 / 25
1.8 below avg 11.2
Identity / Provenance60% listing status · 40% build provenance
10.8 / 18
2.5 below avg 13.3
Transparency50% declared license · 50% OSSF Scorecard
11.5 / 17
in line with avg 12.0
Maintenance60% last-push freshness · 40% commit activity
4.9 / 20
10.4 below avg 15.3
AdoptionLog-scaled stars · package downloads
15.0 / 20
1.6 above avg 13.4

Quick Trust Read

What Would Improve It
Publish package provenance or release attestations for stronger supply-chain evidence.
Recent Changes
2026-10-09
Rank Moved
Rank dropped 15 spots (#841 → #856)
2026-09-30
Rank Moved
Rank dropped 11 spots (#830 → #841)
2026-09-23
Activity Went Stale
No commits for 90 days
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 3.5/10. 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.
Refresh maintenance signals The repo was last pushed 106 days ago. Fresh activity helps separate stable projects from stale ones.
Compare with another agent Get email alerts for AgentOps View Observability & Evaluation Report missing data
46.0
Activity sub-score · out of 100
#20
In Observability & Evaluation

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade C reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage A is separate — it grades how many independent signal types back the score (4 of 5), so a high score on thin evidence stays visible. Full methodology →

Signals refreshed 2026-10-09 16:07 UTC · Repo last pushed 106 days ago

Rank Trend

2026-09-29 2026-10-09

Activity & Reach

Stars
5.9k
Forks
644
Last Push
2026-06-25
106 days ago
Commits (4 wk)
0
Downloads (7d)
27,848
pypi
HN mentions (30d)
1325
Open Issues
113
Rank Change
▼15
was #841

Analysis

Activity Inputs

46.0 / 100
StarsRepository reach
22.6 / 30
FreshnessLast push recency
10.3 / 25
ActivityRecent commits
0.0 / 25
CommunityFork signal
13.1 / 20

Common questions about AgentOps

Public trust evidence for AgentOps 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 AgentOps publish package provenance?
No published build provenance is currently detected for AgentOps. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.
Does AgentOps have an OpenSSF Scorecard?
AgentOps has an OpenSSF Scorecard score of 3.5/10. 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 AgentOps actively maintained?
Slowing down. Last push was 106 days ago — keep an eye on whether activity resumes.
What license does AgentOps use?
AgentOps ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are AgentOps's commits signed?
100% of the last 100 commits to AgentOps 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
medium confidence
Declared
MCP support appears present, but direct server implementation is less certain.
Detailed evidence is not shown in the public view.
External Service Dependencies
high confidence
3 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
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 AgentOps'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.

2026-09-23
Activity Went Stale
No commits for 90 days
2026-08-12
Tool Surface Changed
Detected tool/plugin surface changed: declared → none
2026-07-17
Provider Added
Runtime surface grew — new detected provider dependency: Mistral AI

Maintain AgentOps?

For maintainers

HVTrust scores AgentOps 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
Rank 32HVTrust 2Surface 1Surface 1Stale 1
2026-10-09
Rank Moved
Rank dropped 15 spots (#841 → #856)
2026-09-30
Rank Moved
Rank dropped 11 spots (#830 → #841)
2026-09-23
Activity Went Stale
No commits for 90 days
2026-09-23
Rank Moved
Rank dropped 508 spots (#298 → #806)
2026-09-21
Rank Moved
Rank rose 500 spots (#793 → #293)
2026-09-17
Rank Moved
Rank dropped 11 spots (#766 → #777)
2026-09-15
Rank Moved
Rank dropped 13 spots (#758 → #771)
2026-09-12
Rank Moved
Rank dropped 15 spots (#743 → #758)
2026-09-08
Rank Moved
Rank dropped 10 spots (#711 → #721)
2026-09-07
Rank Moved
Rank dropped 44 spots (#667 → #711)
2026-09-06
Rank Moved
Rank dropped 13 spots (#654 → #667)
2026-09-05
Rank Moved
Rank dropped 73 spots (#581 → #654)
2026-09-04
Rank Moved
Rank dropped 15 spots (#566 → #581)
2026-09-03
Rank Moved
Rank dropped 42 spots (#524 → #566)
2026-09-02
Rank Moved
Rank dropped 18 spots (#506 → #524)
2026-08-31
Rank Moved
Rank dropped 31 spots (#467 → #498)
2026-08-29
Rank Moved
Rank dropped 15 spots (#455 → #470)
2026-08-28
Rank Moved
Rank dropped 13 spots (#442 → #455)
2026-08-27
Rank Moved
Rank dropped 13 spots (#429 → #442)
2026-08-26
Rank Moved
Rank dropped 45 spots (#384 → #429)
2026-08-24
Rank Moved
Rank dropped 18 spots (#365 → #383)
2026-08-22
Rank Moved
Rank rose 16 spots (#382 → #366)
2026-08-19
Rank Moved
Rank dropped 15 spots (#367 → #382)
2026-08-17
Rank Moved
Rank rose 16 spots (#384 → #368)
2026-08-16
Rank Moved
Rank dropped 10 spots (#374 → #384)
2026-08-13
Rank Moved
Rank rose 48 spots (#419 → #371)
2026-08-13
HVTrust Changed
HVTrust up 4.9pts (52.9 → 57.8)
2026-08-12
Tool Surface Changed
Detected tool/plugin surface changed: declared → none
2026-08-12
Rank Moved
Rank dropped 47 spots (#372 → #419)
2026-08-12
HVTrust Changed
HVTrust down 4.8pts (57.7 → 52.9)
2026-08-10
Rank Moved
Rank dropped 19 spots (#352 → #371)
2026-08-08
Rank Moved
Rank dropped 85 spots (#260 → #345)
2026-07-28
Rank Moved
Rank dropped 11 spots (#222 → #233)
2026-07-25
Rank Moved
Rank dropped 10 spots (#210 → #220)
2026-07-17
Provider Added
Runtime surface grew — new detected provider dependency: Mistral AI
2026-07-14
Rank Moved
Rank dropped 25 spots (#162 → #187)
2026-07-13
Rank Moved
Rank dropped 12 spots (#150 → #162)
GitHub → Website → PyPI: agentops

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 53.6 Grade C
Markdown:
[![HVTrust](https://hvtracker.net/badge/agentops.svg)](https://hvtracker.net/agents/agentops)
HTML:
<a href="https://hvtracker.net/agents/agentops"><img src="https://hvtracker.net/badge/agentops.svg" alt="HVTrust"></a>

Other agents in Observability & Evaluation

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