pharos: local-first agentic RAG for your team's document library

by Laurent00TT · MCP Server · ★ 292

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

Security audit verdict: SAFE · quality 66/100

Flagged: sudo usage. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

agentic-ragembeddingsfastapihybrid-searchknowledge-basellmlocal-firstmcpmodel-context-protocolpython

Quick Facts

Stars292
Forks0
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score66/100
Last Updated2026-07-22
Created2026-05-25
Platformsmcp, python
Est. Tokens~16k

About pharos

English | 中文 Pharos Turn PDFs, scans, docx, pptx and xlsx into a local knowledge base you can ask questions of — with enterprise access control and citations you can trace back to the page. Each RAG component was sharpened on its own, then folded into one repository: multi-identity auth, observability and systemd supervision come with it. A note on language.

Compatible Skills

These tools work well together with pharos for enhanced workflows:

  • scholar-rag-agent — semantic(0.34)+complementary+rare_topics+same_lang+similar_pop+shared_platform (67%)
  • arag — semantic(0.33)+complementary+same_lang+similar_pop+shared_platform (61%)
  • SR-Agents — semantic(0.32)+complementary+same_lang+similar_pop+shared_platform (61%)

pharos alternative? Top 6 similar tools

Looking for a pharos alternative? If you're comparing pharos with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • knowledge-rag by lyonzin · ⭐ 306

    Local RAG server for Claude Code, Cursor and other MCP clients: hybrid BM25 + vector search with cross-encoder

  • pdf-mcp by jztan · ⭐ 171

    Agentic RAG over one PDF or a whole folder, with page-level evidence to check every answer: hybrid search, sel

  • gno by gmickel · ⭐ 118

    Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST AP

  • CoWork-OS by CoWork-OS · ⭐ 554

    Rent the model. Own everything else. Free, open-source AI app for real work.

  • mcp-local-rag by shinpr · ⭐ 430

    Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP o

  • OmoiOS by kivo360 · ⭐ 80

    Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolat

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools