Public recordExcellent
Software health reportschema 0.14.0 · metrics 2.10.0 · 2026-07-18 21:50 UTC
SciSharp / LLamaSharp
A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.
SciSharp/LLamaSharp holds a health index of 89 out of 100, placing it in the Excellent band. It scores highest on Vitality (91/100) and lowest on AI Readiness (37/100). It was last updated 1 day ago. A single contributor accounts for most of its recent work.
89
overall / 100Software health index
Metrics are grouped into weighted categories on one standardized 1–100 scale. Overall starts as their weighted mean, calibrated against the distribution of the public record so bands carry percentile meaning; when public evidence triggers the High-Risk Jurisdiction Policy, the rating is adjusted and receives an At Risk ceiling of 34.
89
Exceptional93-100The record's top tier (≈ top 5%); essentially all checked criteria met
Excellent80-92Strong across the board; minor gaps
Good65-79Healthy; gaps are limited and manageable
Moderate50-64Acceptable with notable gaps; review recommended
Weak35-49Material weaknesses across several areas
At Risk20-34Significant weaknesses; adoption warrants caution
Critical1-19Severe problems (abandoned, single-maintainer, no hygiene)
Score profile
Each axis is a category. The shape matters more than the average — a healthy subject fills the whole shape, while a spike-and-crater profile means strength in one dimension is masking risk in another.
The weighted overall 75 is calibrated to 89 on the published index scale (record calibration 2026-08-02).
Ownership
SciSharp STACKOrganization
1,327 followers72 public repossince Nov 2018
This repository is backed by an organization — shared, accountable stewardship that can outlive any single maintainer.
Package ecosystems
| Registry | Package | Version | Downloads / mo | Versions | Last publish | Tags |
|---|---|---|---|---|---|---|
| NuGet | LLamaSharp.kernel-memory | 0.27.0 | - | 22 | 83 days ago | llamallmgptchatgptkernel-memoryvectorsearchscisharp |
| NuGet | LLamaSharp.semantic-kernel | 0.27.0 | - | 25 | 83 days ago | llamallmgptchatgptsemantic-kernelscisharp |
| NuGet | LLamaSharp | 0.27.0 | - | 26 | 83 days ago | llamallmgptchatgptnlpaichatbotscisharp |
Metrics by category
Vitality
Is the project alive — is code being written and are releases shipping?
91
Development activity
91Excellent
How it's scored
| 36/36 | Push recency — last push 1 days ago |
| 27/36 | Commit cadence — 39/52 weeks with commits |
| 18/18 | Commit volume — 324 commits in the last year |
| 10/10 | OpenSSF Scorecard: Maintained — 30 commit(s) and 4 issue activity found in the last 90 days -- score normalized to 10 |
Inputs used
| commits_last_year | 324 |
| human_commit_share | — |
| days_since_last_push | 1 |
| active_weeks_last_year | 39 |
Release discipline
92Excellent
How it's scored
| 27/27 | Ships releases — 30 releases published |
| 36/36 | Release recency — latest release 83 days ago |
| 19.8/27 | Release cadence — a release every ~62.2 days |
| 0/10 | OpenSSF Scorecard: Signed-Releases — no data |
Inputs used
| releases_count | 30 |
| latest_release_tag | v0.27.0 |
| releases_from_tags | no |
| days_since_latest_release | 83 |
| mean_days_between_releases | 62.2 |
Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.
Community & Adoption
Does the project have users, downloads, attention, and a welcoming setup for contributors?
81
Popularity & adoption
91Excellent
How it's scored
| 58/60 | Stars — 3,742 stars |
| 22.5/25 | Forks — 500 forks |
| 10.1/15 | Watchers — 66 watchers |
Inputs used
| forks | 500 |
| stars | 3,742 |
| watchers | 66 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
Community health
70Good
How it's scored
| 22.5/22.5 | README |
| 22.5/22.5 | License — recognized license (MIT) |
| 18/18 | CONTRIBUTING guide |
| 0/13.5 | Code of conduct |
| 0/7.2 | Issue template |
| 0/6.3 | PR template |
Inputs used
| has_readme | yes |
| has_license | yes |
| readme_badges | — |
| has_contributing | yes |
| has_issue_template | no |
| has_code_of_conduct | no |
| readme_badge_services | — |
| has_pull_request_template | no |
Sustainability & Governance
Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?
78
How it's scored
| 9/54 | Bus factor — 1 contributor(s) cover half of all commits |
| 10.9/22.5 | Commit distribution — top contributor authored 51% of commits |
| 13.5/13.5 | Contributor breadth — 88 contributors |
| 10/10 | OpenSSF Scorecard: Contributors — project has 22 contributing companies or organizations |
Inputs used
| bus_factor | 1 |
| contributors_sampled | 88 |
| top_contributor_share | 0.514 |
Issue & PR responsiveness
85Excellent
How it's scored
| 40.5/42 | Issue resolution — 96% of issues closed |
| 26/30 | PR acceptance — 744/860 decided PRs merged |
| 0/13 | Newcomer PR acceptance — no first-time contributor's PR decided in 30d |
| 7.5/15 | OpenSSF Scorecard: Code-Review — Found 2/4 approved changesets -- score normalized to 5 |
Inputs used
| merged_prs | 744 |
| open_issues | 17 |
| closed_issues | 456 |
| prs_merged_7d | — |
| prs_decided_7d | — |
| prs_merged_30d | — |
| prs_decided_30d | — |
| issue_closed_ratio | 0.964 |
| closed_unmerged_prs | 116 |
| first_time_authors_30d | — |
| first_time_prs_merged_30d | — |
| first_time_prs_decided_30d | — |
Excluded from scoring (no data or not applicable): Newcomer PR acceptance. Remaining weights renormalized.
Ownership & stewardship
97Exceptional
How it's scored
| 30/30 | Ownership backing — organization-owned |
| 0/20 | Verified domain — verified-domain status not read for this organization |
| 22.5/25 | Owner reach — 1,327 followers of SciSharp |
| 25/25 | Track record — 72 public repos, account ~7 yr old |
Inputs used
| followers | 1,327 |
| owner_type | Organization |
| is_verified | — |
| owner_login | SciSharp |
| public_repos | 72 |
| account_age_days | 2,804 |
Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.
Package maintenance
100Exceptional
How it's scored
| 25/25 | Published & resolvable — 3 package(s) on nuget |
| 35/35 | Publish recency — latest publish 83 days ago |
| 20/20 | Version history — 26 published versions |
| 20/20 | Not deprecated — active, not deprecated or yanked |
Inputs used
| packages | LLamaSharp.kernel-memory, LLamaSharp.semantic-kernel, LLamaSharp |
| ecosystems | nuget |
| any_deprecated | no |
| min_days_since_publish | 83 |
Engineering Quality
Are baseline engineering and documentation practices in place?
65
Engineering practices
48Weak
How it's scored
| 24/24 | CI workflows — 11 workflow(s) |
| 0/24 | Tests present |
| 0/16 | Linter config |
| 0/9.6 | Pre-commit hooks |
| 6.4/6.4 | .editorconfig |
| 18/20 | OpenSSF Scorecard: CI-Tests — 13 out of 14 merged PRs checked by a CI test -- score normalized to 9 |
Inputs used
| has_ci | yes |
| has_tests | no |
| has_editorconfig | yes |
| has_linter_config | no |
| has_precommit_config | no |
Documentation
90Excellent
How it's scored
| 30/30 | README |
| 25/25 | Documentation directory |
| 15/15 | Documentation / homepage site — https://scisharp.github.io/LLamaSharp |
| 10/10 | Repository description |
| 10/10 | Topics — 11 topics |
| 0/10 | Wiki |
Inputs used
| topics | chatbot, gpt, llama, llamacpp, llm, semantic-kernel, llava, multi-modal, llama2, llama3, llama-cpp |
| has_wiki | no |
| homepage | https://scisharp.github.io/LLamaSharp |
| docs_site | https://scisharp.github.io/LLamaSharp |
| has_readme | yes |
| has_docs_dir | yes |
| has_description | yes |
Security
Are visible security and supply-chain practices strong, without unresolved high-risk jurisdiction exposure?
62
Security posture
62Moderate
How it's scored
| 7.5/7.5 | Binary-Artifacts — no binaries found in the repo |
| 0/7.5 | Branch-Protection — no data |
| 2.2/2.5 | CI-Tests — 13 out of 14 merged PRs checked by a CI test -- score normalized to 9 |
| 0/2.5 | CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected |
| 3.8/7.5 | Code-Review — Found 2/4 approved changesets -- score normalized to 5 |
| 2.5/2.5 | Contributors — project has 22 contributing companies or organizations |
| 10/10 | Dangerous-Workflow — no dangerous workflow patterns detected |
| 7.5/7.5 | Dependency-Update-Tool — update tool detected |
| 0/5 | Fuzzing — project is not fuzzed |
| 2.5/2.5 | License — license file detected |
| 7.5/7.5 | Maintained — 30 commit(s) and 4 issue activity found in the last 90 days -- score normalized to 10 |
| 5/5 | Packaging — packaging workflow detected |
| 0/5 | Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
| 0/5 | SAST — SAST tool is not run on all commits -- score normalized to 0 |
| 0/5 | Security-Policy — security policy file not detected |
| 0/7.5 | Signed-Releases — no data |
| 0/7.5 | Token-Permissions — detected GitHub workflow tokens with excessive permissions |
| 7.5/7.5 | Vulnerabilities — 0 existing vulnerabilities detected |
Inputs used
| source | openssf_scorecard |
| checks_evaluated | 16 |
| scorecard_version | v5.5.0 |
| checks_inconclusive | 2 |
| scorecard_aggregate | 6.2 |
Excluded from scoring (no data or not applicable): Branch-Protection, Signed-Releases. Remaining weights renormalized.
AI Readiness
How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight (4%): agent tooling is a real maintenance signal, but a repository with none can still reach 100/100.
37
Agent context & guidance
1Critical
How it's scored
| 0/45 | Agent instructions — no CLAUDE.md / AGENTS.md / editor rules |
| 0/15 | Machine-readable docs (llms.txt) |
| 0/40 | Legible commit history — no data |
Inputs used
| has_llms_txt | no |
| llms_txt_url | — |
| legible_history_share | — |
| agent_instruction_files | — |
| agent_instruction_max_bytes | — |
Excluded from scoring (no data or not applicable): Legible commit history. Remaining weights renormalized.
Verify loop (build / test / typecheck)
18Critical
How it's scored
| 0/18 | One-command bootstrap |
| 0/22 | Automated tests |
| 0/11 | Lint / format config |
| 11/11 | Static type checking — C# (statically typed) |
| 0/10 | Reproducible environment |
| 0/10 | Demonstrated agent practice — no data |
| 5/8 | Automated maintenance — dependency automation configured, none observed in the sampled commits |
| 0/10 | OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
Inputs used
| has_nix | no |
| has_tests | no |
| lockfiles | — |
| has_dockerfile | no |
| typed_language | yes |
| bootstrap_files | — |
| has_devcontainer | no |
| has_linter_config | no |
| typecheck_configs | — |
| agent_commit_share | — |
| toolchain_manifests | — |
| dependency_bot_commit_share | 0 |
Excluded from scoring (no data or not applicable): Demonstrated agent practice. Remaining weights renormalized.
Code legibility for models
99Exceptional
How it's scored
| 45/45 | Type-checkable code — C# (statically typed) |
| 54/55 | Manageable file sizes — 5/276 source files over 60KB |
Inputs used
| primary_language | C# |
| largest_source_bytes | 285,314 |
| source_files_sampled | 276 |
| oversized_source_files | 5 |
Machine-readable interfaces
100Exceptional
How it's scored
| 0/40 | API schema (OpenAPI/GraphQL/proto) — not applicable to this kind of software |
| 0/20 | MCP server — not applicable to this kind of software |
| 40/40 | Runnable examples — examples |
Inputs used
| example_dirs | examples |
| has_mcp_signal | no |
| api_schema_files | — |
| interfaces_expected_of | — |
Excluded from scoring (no data or not applicable): API schema (OpenAPI/GraphQL/proto), MCP server. Remaining weights renormalized.
Key facts
3,742GitHub stars
88contributors
324commits, last 12 months
1days since last push
30releases
1bus factor
17open issues
NuGetpackage ecosystems
Data collection warnings
- Could not fetch nuget package 'LLamaSharp.Experimental' from its registry
More detail
OpenSSF Scorecard 6.2 / 10
6.2aggregate
Independent, tool-agnostic security assessment from the open-source OpenSSF Scorecard. Each check rewards a security practice, not a specific vendor's tool. Checks Scorecard could not determine are marked n/a and excluded from the security score (never counted as zero).
| 10 | Binary-Artifacts | no binaries found in the repo |
| n/a | Branch-Protection | internal error: error during branchesHandler.setup: internal error: some github tokens can't read classic branch protection rules: https://github.com/ossf/scorecard-action/blob/main/docs/authentication/fine-grained-auth-token.md |
| 9 | CI-Tests | 13 out of 14 merged PRs checked by a CI test -- score normalized to 9 |
| 0 | CII-Best-Practices | no effort to earn an OpenSSF best practices badge detected |
| 5 | Code-Review | Found 2/4 approved changesets -- score normalized to 5 |
| 10 | Contributors | project has 22 contributing companies or organizations |
| 10 | Dangerous-Workflow | no dangerous workflow patterns detected |
| 10 | Dependency-Update-Tool | update tool detected |
| 0 | Fuzzing | project is not fuzzed |
| 10 | License | license file detected |
| 10 | Maintained | 30 commit(s) and 4 issue activity found in the last 90 days -- score normalized to 10 |
| 10 | Packaging | packaging workflow detected |
| 0 | Pinned-Dependencies | dependency not pinned by hash detected -- score normalized to 0 |
| 0 | SAST | SAST tool is not run on all commits -- score normalized to 0 |
| 0 | Security-Policy | security policy file not detected |
| n/a | Signed-Releases | no releases found |
| 0 | Token-Permissions | detected GitHub workflow tokens with excessive permissions |
| 10 | Vulnerabilities | 0 existing vulnerabilities detected |
Direct dependencies 41
| Registry | Package | Version constraint | Manifest |
|---|---|---|---|
| NuGet | BenchmarkDotNet | 0.15.8 | LLama.Benchmark/LLama.Benchmark.csproj |
| NuGet | BenchmarkDotNet.Diagnostics.Windows | 0.15.8 | LLama.Benchmark/LLama.Benchmark.csproj |
| NuGet | Microsoft.Extensions.Logging.Console | 10.0.5 | LLama.Examples/LLama.Examples.csproj |
| NuGet | Microsoft.KernelMemory.Core | 0.98.250508.3 | LLama.Examples/LLama.Examples.csproj |
| NuGet | Microsoft.SemanticKernel | 1.74.0 | LLama.Examples/LLama.Examples.csproj |
| NuGet | Microsoft.SemanticKernel.Plugins.Memory | 1.44.0-alpha | LLama.Examples/LLama.Examples.csproj |
| NuGet | NAudio | 2.3.0 | LLama.Examples/LLama.Examples.csproj |
| NuGet | SixLabors.ImageSharp | 3.1.12 | LLama.Examples/LLama.Examples.csproj |
| NuGet | Spectre.Console | 0.54.0 | LLama.Examples/LLama.Examples.csproj |
| NuGet | Spectre.Console.ImageSharp | 0.54.0 | LLama.Examples/LLama.Examples.csproj |
| NuGet | Whisper.net | 1.9.0 | LLama.Examples/LLama.Examples.csproj |
| NuGet | Whisper.net.Runtime | 1.9.0 | LLama.Examples/LLama.Examples.csproj |
| NuGet | Whisper.net.Runtime.Clblast | 1.5.0 | LLama.Examples/LLama.Examples.csproj |
| NuGet | Whisper.net.Runtime.CoreML | 1.9.0 | LLama.Examples/LLama.Examples.csproj |
| NuGet | Whisper.net.Runtime.Cublas | 1.5.0 | LLama.Examples/LLama.Examples.csproj |
| NuGet | HuggingfaceHub | 0.1.3 | LLama.Experimental/LLama.Experimental.csproj |
| NuGet | Microsoft.KernelMemory.Abstractions | 0.98.250508.3 | LLama.KernelMemory/LLamaSharp.KernelMemory.csproj |
| NuGet | Microsoft.SemanticKernel.Abstractions | 1.64.0 | LLama.SemanticKernel/LLamaSharp.SemanticKernel.csproj |
| NuGet | System.Memory | 4.6.3 | LLama.SemanticKernel/LLamaSharp.SemanticKernel.csproj |
| NuGet | Microsoft.NET.Test.Sdk | 18.3.0 | LLama.Unittest/LLama.Unittest.csproj |
| NuGet | Moq | 4.20.72 | LLama.Unittest/LLama.Unittest.csproj |
| NuGet | xunit | 2.9.3 | LLama.Unittest/LLama.Unittest.csproj |
| NuGet | xunit.runner.visualstudio | 3.1.5 | LLama.Unittest/LLama.Unittest.csproj |
| NuGet | coverlet.collector | 10.0.1 | LLama.Unittest/LLama.Unittest.csproj |
| NuGet | Xunit.SkippableFact | 1.5.61 | LLama.Unittest/LLama.Unittest.csproj |
| NuGet | Microsoft.AspNetCore.Mvc.Razor.RuntimeCompilation | 8.0.28 | LLama.Web/LLama.Web.csproj |
| NuGet | Microsoft.VisualStudio.Validation | 17.13.22 | LLama.WebAPI/LLama.WebAPI.csproj |
| NuGet | IsExternalInit | 1.0.3 | LLama/LLamaSharp.csproj |
| NuGet | System.Memory | 4.6.3 | LLama/LLamaSharp.csproj |
| NuGet | System.Text.Json | 10.0.9 | LLama/LLamaSharp.csproj |
| NuGet | CommunityToolkit.HighPerformance | 8.4.2 | LLama/LLamaSharp.csproj |
| NuGet | Microsoft.Bcl.AsyncInterfaces | 10.0.9 | LLama/LLamaSharp.csproj |
| NuGet | Microsoft.Bcl.Memory | 10.0.9 | LLama/LLamaSharp.csproj |
| NuGet | Microsoft.Extensions.AI.Abstractions | 10.7.0 | LLama/LLamaSharp.csproj |
| NuGet | Microsoft.Extensions.Logging.Abstractions | 10.0.9 | LLama/LLamaSharp.csproj |
| NuGet | System.Linq.Async | 7.0.0 | LLama/LLamaSharp.csproj |
| NuGet | System.Linq.AsyncEnumerable | 10.0.2 | LLama/LLamaSharp.csproj |
| NuGet | System.Numerics.Tensors | 10.0.5 | LLama/LLamaSharp.csproj |
| NuGet | Microsoft.Maui.Controls | $(MauiVersion) | Llama.Mobile/Llama.Mobile.csproj |
| NuGet | Microsoft.Maui.Controls.Compatibility | $(MauiVersion) | Llama.Mobile/Llama.Mobile.csproj |
| NuGet | Microsoft.Extensions.Logging.Debug | 8.0.1 | Llama.Mobile/Llama.Mobile.csproj |
All dependencies 45
Full resolved dependency set from the GitHub dependency graph: 40 direct and 5 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.
| Registry | Package | Version | Relation |
|---|---|---|---|
| NuGet | BenchmarkDotNet | 0.15.8 | direct |
| NuGet | BenchmarkDotNet.Diagnostics.Windows | 0.15.8 | direct |
| NuGet | CommunityToolkit.HighPerformance | 8.4.2 | direct |
| NuGet | coverlet.collector | 10.0.1 | direct |
| NuGet | HuggingfaceHub | 0.1.3 | direct |
| NuGet | IsExternalInit | 1.0.3 | direct |
| NuGet | Microsoft.AspNetCore.Mvc.Razor.RuntimeCompilation | 8.0.28 | direct |
| NuGet | Microsoft.Bcl.AsyncInterfaces | 10.0.9 | direct |
| NuGet | Microsoft.Bcl.Memory | 10.0.9 | direct |
| NuGet | Microsoft.Extensions.AI.Abstractions | 10.7.0 | direct |
| NuGet | Microsoft.Extensions.Logging.Abstractions | 10.0.9 | direct |
| NuGet | Microsoft.Extensions.Logging.Console | 10.0.5 | direct |
| NuGet | Microsoft.Extensions.Logging.Debug | 8.0.1 | direct |
| NuGet | Microsoft.KernelMemory.Abstractions | 0.98.250508.3 | direct |
| NuGet | Microsoft.KernelMemory.Core | 0.98.250508.3 | direct |
| NuGet | Microsoft.Maui.Controls | — | direct |
| NuGet | Microsoft.Maui.Controls.Compatibility | — | direct |
| NuGet | Microsoft.NET.Test.Sdk | 18.3.0 | direct |
| NuGet | Microsoft.SemanticKernel | 1.74.0 | direct |
| NuGet | Microsoft.SemanticKernel.Abstractions | 1.64.0 | direct |
| NuGet | Microsoft.SemanticKernel.Plugins.Memory | 1.44.0-alpha | direct |
| NuGet | Microsoft.VisualStudio.Validation | 17.13.22 | direct |
| NuGet | Moq | 4.20.72 | direct |
| NuGet | NAudio | 2.3.0 | direct |
| NuGet | SixLabors.ImageSharp | 3.1.12 | direct |
| NuGet | Spectre.Console | 0.54.0 | direct |
| NuGet | Spectre.Console.ImageSharp | 0.54.0 | direct |
| NuGet | System.Linq.Async | 7.0.0 | direct |
| NuGet | System.Linq.AsyncEnumerable | 10.0.2 | direct |
| NuGet | System.Memory | 4.6.3 | direct |
| NuGet | System.Numerics.Tensors | 10.0.5 | direct |
| NuGet | System.Text.Json | 10.0.9 | direct |
| NuGet | Whisper.net | 1.9.0 | direct |
| NuGet | Whisper.net.Runtime | 1.9.0 | direct |
| NuGet | Whisper.net.Runtime.Clblast | 1.5.0 | direct |
| NuGet | Whisper.net.Runtime.CoreML | 1.9.0 | direct |
| NuGet | Whisper.net.Runtime.Cublas | 1.5.0 | direct |
| NuGet | xunit | 2.9.3 | direct |
| NuGet | xunit.runner.visualstudio | 3.1.5 | direct |
| NuGet | Xunit.SkippableFact | 1.5.61 | direct |
| NuGet | LLamaSharp.Backend.Cpu | — | indirect |
| NuGet | LLamaSharp.Backend.Cuda12.Linux | — | indirect |
| NuGet | LLamaSharp.Backend.Cuda12.Windows | — | indirect |
| NuGet | LLamaSharp.Backend.Vulkan.Linux | — | indirect |
| NuGet | LLamaSharp.Backend.Vulkan.Windows | — | indirect |
Raw JSON report machine-readable
Feedback
Spotted something off in this report, or have thoughts to share? Wrong measurements, missed tooling, ideas, questions — anything is welcome. Every message is read and gets a response.
Scores are signals, not warranties. They reflect publicly visible practices on GitHub — not a code audit, and not a security guarantee.
Missing data is excluded and weights renormalized, never scored as zero. Methodology is versioned and open: metrics v2.10.0, schema v0.14.0 — full methodology · metrics wiki.
How one result sits in the wider record: aggregate statistics — NuGet.