Ollama
Website
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Is Ollama safe? Promising trust profile, but some evidence still deserves review.
Compare Ollama
How does it stack up against its LLM Gateways & Infra neighbours?
Pick any agent to compare →In detail: Ollama scores 66.4/100 (Grade B), ranked #466 of 1378 tracked open-source AI agent projects, on evidence coverage B (3 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 5.3/10; 67% of recent commits are signed; last pushed 2026-10-17. Every point is earned from checkable signals — never paid placement. How scoring works →
What Ollama can reach, and who runs it
Checked 2026-10-09, each with its source. PUBLISHER is the company's or project's own statement, which we haven't verified; CHECKED is something we observed ourselves; IN CODE is read from the project's source code. These facts describe the product. They don't change its score.
What it can reach
- PUBLISHER Its API binds 127.0.0.1:11434 by default. The FAQ explains how to expose it on your network by changing the bind address with OLLAMA_HOST.
- IN CODE Its official Docker image sets OLLAMA_HOST=0.0.0.0:11434, so the server listens on every interface, not just localhost.
Where your data goes
- PUBLISHER Local models run on your machine and Ollama doesn't see the prompts. With cloud-hosted models it processes prompts and responses, and says it doesn't store or log that content or train on it. Cloud features can be switched off for local-only use.
Security practice
- CHECKED OSV lists 16 advisories for the github.com/ollama/ollama Go module (1 critical, 11 high, 3 medium, 1 low), 3 of them in the last 12 months. Ollama publishes no GitHub security advisories of its own; reports go through its SECURITY.md and GitHub private vulnerability reporting.
How Ollama 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 5.3 to 9.0lowest checks: CII-Best-Practices 0, Dependency-Update-Tool 0, Pinned-Dependencies 0 +7.7 → 74.1 B · #5 of 14
- Sign every commit67% signed today +1.6 → 68.0 B · #5 of 14
Chain of custody
Scanners check what the code says. This traces who ships Ollama and whether that has changed: from the source repository, through how changes are reviewed and released, to the code you run. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.
-
Source Partly signed
github.com/ollama/ollama, MIT, last pushed 2026-10-17. 67% 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 5.3/10 (scanned Oct 11, 2026). The checks that decide who can get a change released:
- Code Review8
- Branch Protection3
- Signed Releases0
- Dangerous Workflow10
- Token Permissions0
- Pinned Dependencies0
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 3CI-Tests 8CII-Best-Practices 0Code-Review 8Contributors 10Dangerous-Workflow 10Dependency-Update-Tool 0Fuzzing 10License 10Maintained 10Packaging 10Pinned-Dependencies 0SAST 0Security-Policy 10Signed-Releases 0Token-Permissions 0Vulnerabilities 0 -
Published packages None
No registry package. Ollama is used from its repository, so what you run is whatever you check out: pin a release tag or commit.
Changes to this chain
No change to package provenance, package source links, Scorecard coverage or license in HVTracker's daily snapshots of Ollama.
Evidence behind this score
Coverage B: 3 of 5 independent evidence types found.
- GitHub repository data
- Package downloads (missing)
- Supply-chain checks
- Public actions (missing)
- Community mentions
Verify this score yourself
Every build re-issues Ollama’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 Ollama compares in LLM Gateways & Infra
- #3 vLLM 81.0 +14.6
- #4 LiteLLM 78.3 +11.9
- #5 Ollama 66.4 this agent
- #6 Instructor 64.3 −2.1
- #7 Jan 64.2 −2.2
Bars show each HVTrust score; the tick marks Ollama’s 66.4.
Where the 66.4 comes from
HVTrust dimensions vs the LLM Gateways & Infra average
66.4 / 100 · 100.0% confidenceOllama LLM Gateways & Infra average (14 agents)
Quick Trust Read
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade B 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
Activity & Reach
Analysis
Activity Inputs
99.8 / 100Common questions about Ollama
Does Ollama publish package provenance?
Does Ollama have an OpenSSF Scorecard?
Is Ollama actively maintained?
What license does Ollama use?
Are Ollama's commits signed?
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 Ollama head-to-head
AI agent surface
MCP, providers, tool surface
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 signal live
- External deps live
- Tool / plugin surface live
- Package provenance drift live
Maintain Ollama?
For maintainers
HVTrust scores Ollama 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
Embed Badge Badge guide for maintainers →
For maintainers
[](https://hvtracker.net/agents/ollama)
<a href="https://hvtracker.net/agents/ollama"><img src="https://hvtracker.net/badge/ollama.svg" alt="HVTrust"></a>
Other agents in LLM Gateways & Infra
GitHub REST API (repo, commits, stars, forks, license) · OpenSSF Scorecard CLI · Algolia HN Search API
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON