Ross ROSS = Recommend OSS · open-source software intelligence for agents

sashiko-dev/sashiko

Agentic review of Linux Kernel code changes observed · 2026-08-28

github.com/sashiko-dev/sashiko · homepage · Rust · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

60/100

  • Activity 99
  • Release rhythm 35
  • Longevity 17

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 243
  • days_rel: n/a
  • days_push: 7
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1191 stars · 205 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Sashiko is an agentic code review system for the Linux kernel that ingests patches from mailing lists, GitHub PRs, GitLab MRs, or local git, and reviews them using a multi-stage protocol of kernel-specific LLM prompts. It is a self-contained Rust tool with a web interface and CLI, supporting multiple LLM providers, and is also run as a public service reviewing all LKML submissions.

Use cases

  • automatically review linux kernel patches
  • find bugs in kernel commits before they land
  • monitor lkml mailing list for new patches to review
  • review a github pull request with an llm agent
  • run local kernel patch review from a git repo
  • reduce false positives in automated code review

When to choose

  • you maintain or contribute to the Linux kernel and want automated pre-merge review
  • you need kernel-specific review prompts covering architecture, security, and concurrency
  • you want a self-contained reviewer that works with multiple LLM providers
  • you want to watch lore.kernel.org or forges for new patches automatically

When to avoid

  • you need code review for non-kernel or non-C projects
  • you require deterministic, guaranteed bug detection rather than probabilistic LLM output
  • you cannot send proprietary code to external LLM providers
  • you need email-based output, which is not yet supported

Facets

service · maturity active

code-review llm-inference agent-framework cli web-scraping developer-tools version-control artificial-intelligence large-language-models operating-systems cli rust self-hosted linux-kernel patch-review lkml agentic-review code-analysis mailing-list linux web-server

3 sources

Member repositories

RepositoryRoleHealth v2
sashiko-dev/sashikomain60

For agents

markdown · JSON · MCP: product_card(name="sashiko-dev/sashiko")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem