Security News
Happy Birthday, Shai-Hulud
It has been one year since Shai-Hulud made its first appearance on npm.
By Sarah Gooding - Sep 18, 2026
New:Microsoft Teams Notifications Are Now Available in Socket.Learn more →
Package was removed
Sorry, it seems this package was removed from the registry
llm-corpus
Local-first, LLM-native knowledge base CLI toolkit. Ingest, classify, and search documents with BM25/FTS5 ranking.
llm-corpus
Local-first, LLM-native knowledge base CLI toolkit.
Ingest documents (PDF, web, audio, video), classify with local LLM, search with BM25/FTS5 ranking. Works as a standalone CLI or as an MCP server for AI agents (Claude Code, Gemini CLI, Codex CLI).
Status: Under active development. Full release coming soon.
Planned Features
corpus search "query"— BM25-ranked full-text searchcorpus ingest --url <URL>— Ingest web pages, PDFs, audio, videocorpus validate— Schema compliance checkingcorpus mcp-server— MCP server for AI agent integration- Pluggable LLM (Ollama, LM Studio, cloud APIs, or none)
- Progressive feature tiers (search-only → full pipeline)
FAQs
Local-first, LLM-native knowledge base CLI toolkit. Ingest, classify, and search documents with BM25/FTS5 ranking.
We found that llm-corpus demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Package last updated on 21 Apr 2026
Related posts
Research
/Security News
PolinRider Spreads Through Compromised GitHub Accounts and Packagist
Operators behind PolinRider used a compromised GitHub account to plant malware in four development versions of a Packagist package with 700,000+ downloads.
By Karlo Zanki - Sep 17, 2026
Security News
GitHub Actions Adds cache-mode to Limit Cache Poisoning Risk
GitHub Actions now supports cache-mode, a least-privilege control on the Actions cache aimed at the cache poisoning technique behind recent compromises.
By Sarah Gooding - Sep 16, 2026