By nozomio-labs
Index and search code repositories, documentation, research papers, and HuggingFace datasets with Nia AI.
Index and search code repositories, documentation, research papers, and HuggingFace datasets with Nia AI.
Nia provides tools for indexing and searching external repositories, research papers, documentation, packages, and performing AI-powered research. Its primary goal is to reduce hallucinations in LLMs and provide up-to-date context for AI agents.
/install nia
/plugin marketplace add nozomio-labs/nia-plugin
/plugin install nia@nozomio-labs/nia-plugin
Get your API key:
npx nia-wizard@latest (guided setup)Store the key:
mkdir -p ~/.config/nia
echo "your-api-key" > ~/.config/nia/api_key
Requirements: curl, jq
| Category | Scripts |
|---|---|
| Repositories | repos-list.sh, repos-index.sh, repos-tree.sh, repos-read.sh, repos-grep.sh, repos-status.sh |
| Data Sources | sources-list.sh, sources-index.sh, sources-tree.sh, sources-ls.sh, sources-read.sh, sources-grep.sh |
| Research Papers | papers-list.sh, papers-index.sh |
| HuggingFace Datasets | datasets-list.sh, datasets-index.sh |
| Search | search-query.sh, search-universal.sh, search-web.sh, search-deep.sh |
| Package Search | package-grep.sh, package-hybrid.sh, package-read.sh |
| Global Sources | global-subscribe.sh |
| Oracle Research | oracle.sh, oracle-job.sh, oracle-job-status.sh, oracle-jobs-list.sh, oracle-sessions.sh |
| Usage | usage.sh |
# List indexed repositories
./scripts/repos-list.sh
# Index a repository
./scripts/repos-index.sh "owner/repo"
# Search all indexed sources
./scripts/search-universal.sh "how does auth work?"
# Index documentation
./scripts/sources-index.sh "https://docs.stripe.com"
# Grep repository code
./scripts/repos-grep.sh "vercel/ai" "streamText"
# Query specific repos/docs
./scripts/search-query.sh "explain hooks" "facebook/react,vercel/next.js" "React Docs"
# Index an arXiv paper
./scripts/papers-index.sh "2312.00752"
# Index a HuggingFace dataset
./scripts/datasets-index.sh "squad"
# Run Oracle research job
./scripts/oracle-job.sh "compare React vs Vue state management"
# Check API usage
./scripts/usage.sh
| Type | Index Method | Identifier Formats |
|---|---|---|
| Repository | repos-index.sh | owner/repo |
| Documentation | sources-index.sh | https://docs.example.com |
| Research Paper | papers-index.sh | 2312.00752, arXiv URL |
| HuggingFace Dataset | datasets-index.sh | squad, owner/dataset |
Most data source endpoints accept:
550e8400-e29b-41d4-a716-446655440000Vercel AI SDK - Core, openai/gsm8khttps://docs.trynia.ai/, https://arxiv.org/abs/2312.00752See skills/nia/SKILL.md for the complete workflow guide.
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub nozomio-labs/nia-plugin --plugin niaDocument search with hybrid BM25/semantic retrieval, GraphRAG knowledge graphs, and pluggable providers for Claude Code. Index documentation and code, then search using keyword matching, semantic similarity, graph relationships, or comprehensive multi-mode fusion.
Multi-source research plugin — code archaeology, community discourse, academic literature, and TRIZ cross-domain analysis with domain-adaptive depth
Optimized file search, semantic indexing, and persistent memory for Claude Code — with optional sync to a self-hosted web dashboard
Deep research coordination: academic papers, technical analysis, data insights, and web intelligence
OpenAI Codex CLI ecosystem plugin with documentation management, scraping, indexing, and search capabilities
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.