Is AgentLite safe to use?

AgentLite has an HVTrust score of 41.6/100 (Grade D), ranked #570 of 1204 tracked AI agent projects. This score reflects verifiable supply-chain integrity, transparency, maintenance, and adoption signals.

What is the trust score for AgentLite?

AgentLite scores 41.6/100 on HVTracker's evidence-weighted HVTrust scale. It has 650 GitHub stars and is categorized under Agent Frameworks.

AgentLite

SalesforceAIResearch/AgentLite

Agent Frameworks Jupyter Notebook Grade D Listed Apache-2.0

41.6/100

Rank #570 of 1204

Compare AgentLite

How does it stack up against its Agent Frameworks 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 A · 4/5 signals

Last push

2026-06-02 · 68d ago

Recent change

Rank

Is AgentLite safe? AgentLite scores 41.6/100 (Grade D), ranked #570 of 1204 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 3.2/10; recent commits are unsigned; last pushed 2026-06-02. Every point is earned from checkable signals — never paid placement. How scoring works →

Ranked neighbours in Agent Frameworks

#77 Parlant — 44.1 (D) → #78 OpenSSA — 42.0 (D) → #80 Magentic — 37.1 (D) → #81 Youtu-Agent — 35.0 (D) →

Quick Trust Read

What Would Improve It

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

Recent Changes

2026-08-08

Rank Moved

Rank dropped 188 spots (#382 → #570)

2026-07-15

Rank Moved

Rank dropped 25 spots (#324 → #349)

2026-07-14

Rank Moved

Rank dropped 16 spots (#308 → #324)

Maintainer Checklist

Raise Scorecard signals Current OSSF Scorecard is 3.2/10. 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 68 days ago. Fresh activity helps separate stable projects from stale ones.

Compare with another agent Get email alerts for AgentLite View Agent Frameworks Report missing data

41.4

Activity sub-score · out of 100

#79

In Agent Frameworks

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 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 →

Activity & Reach

Stars

650

Forks

Last Push

2026-06-02

68 days ago

Commits (4 wk)

Downloads (7d)

pypi

HN mentions (30d)

Open Issues

Rank Change

was #570

Analysis

HVTrust Dimensions vs Agent Frameworks

41.6 / 100 · 100.0% confidence

AgentLite Agent Frameworks average (117 agents)

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

4.0 / 25

4.2 below avg 8.2

Identity / Provenance60% listing status · 40% build provenance

10.8 / 18

0.8 below avg 11.6

Transparency50% declared license · 50% OSSF Scorecard

11.2 / 17

in line with avg 11.6

Maintenance60% last-push freshness · 40% commit activity

7.5 / 20

6.8 below avg 14.3

AdoptionLog-scaled stars · package downloads

9.1 / 20

2.3 below avg 11.4

Activity Inputs

41.4 / 100

StarsRepository reach

16.9 / 30

FreshnessLast push recency

15.6 / 25

ActivityRecent commits

0.0 / 25

CommunityFork signal

8.9 / 20

Supply Chain Trust

Package Provenance

None

No package attestations found

OSSF Scorecard

3.2 / 10

OpenSSF Scorecard · scanned Aug 8, 2026

Signed Commits

—

Unable to query

Binary-Artifacts 10

Branch-Protection 6

CI-Tests 0

CII-Best-Practices 0

Code-Review 1

Contributors 0

Dangerous-Workflow -1

Dependency-Update-Tool 0

Fuzzing 0

License 10

Maintained 0

Packaging -1

Pinned-Dependencies -1

SAST 0

Security-Policy 10

Signed-Releases -1

Token-Permissions -1

Vulnerabilities 3

Is AgentLite safe?

Public trust evidence for AgentLite 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 AgentLite publish package provenance?

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

Does AgentLite have an OpenSSF Scorecard?

AgentLite has an OpenSSF Scorecard score of 3.2/10. 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 AgentLite actively maintained?

Slowing down. Last push was 68 days ago — keep an eye on whether activity resumes.

What license does AgentLite use?

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

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

None detected

No MCP server signal detected.

Detailed evidence is not shown in the public view.

External Service Dependencies

high confidence

1 detected

Public provider/service dependencies detected.

OpenAI

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

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 AgentLite'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.

2026-06-05

Provider Added

Runtime surface grew — new detected provider dependency: OpenAI

2026-06-02

Activity Resumed

Activity resumed

Maintain AgentLite?

For maintainers

HVTrust scores AgentLite 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

2026-08-08

Rank Moved

Rank dropped 188 spots (#382 → #570)

2026-07-15

Rank Moved

Rank dropped 25 spots (#324 → #349)

2026-07-14

Rank Moved

Rank dropped 16 spots (#308 → #324)

2026-07-13

Rank Moved

Rank dropped 37 spots (#271 → #308)

2026-06-24

Rank Moved

Rank dropped 32 spots (#217 → #249)

2026-06-23

Rank Moved

Rank dropped 17 spots (#200 → #217)

2026-06-21

Rank Moved

Rank dropped 11 spots (#180 → #191)

2026-06-18

Rank Moved

Rank dropped 13 spots (#162 → #175)

2026-06-08

Rank Moved

Rank rose 33 spots (#190 → #157)

2026-06-08

HVTrust Changed

HVTrust up 13.4pts (35.0 → 48.4)

2026-06-07

Rank Moved

Rank dropped 34 spots (#156 → #190)

2026-06-07

HVTrust Changed

HVTrust down 13.5pts (48.5 → 35.0)

2026-06-06

Rank Moved

Rank rose 34 spots (#190 → #156)

2026-06-06

HVTrust Changed

HVTrust up 13.5pts (35.0 → 48.5)

2026-06-05

Provider Added

Runtime surface grew — new detected provider dependency: OpenAI

2026-06-02

Activity Resumed

Activity resumed

2026-06-02

Rank Moved

Rank rose 23 spots (#169 → #146)

2026-06-02

HVTrust Changed

HVTrust up 12.6pts (34.3 → 46.9)

2026-06-02

Activity Score Changed

Activity score up 29pts (26 → 54)

2026-06-01

Rank Moved

Rank dropped 20 spots (#149 → #169)

2026-05-29

HVTrust Changed

HVTrust up 10.0pts (25.3 → 35.3)

2026-05-27

Scorecard Added

OSSF Scorecard: 3.4/10

2026-05-27

Grade Changed

Trust grade D → C

2026-05-27

HVTrust Changed

HVTrust up 11.7pts (7.7 → 19.4)

2026-05-25

Newly Listed

First tracked at rank #166

GitHub → PyPI: agentlite-llm

Embed Badge Badge guide for maintainers →

For maintainers

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

Other agents in Agent Frameworks

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 v4.2 · Raw JSON