Skip to content
Back to search

vexor-marketplace

MarketplaceWorks with Claude CodeGitHub

A semantic search engine for files and code.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/scarletkc--vexor/badge.svg)](/listings/scarletkc--vexor)

HTML

<a href="/listings/scarletkc--vexor"><img src="/api/listings/scarletkc--vexor/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Download standalone binary from [releases](https://github.com/scarletkc/vexor/releases) (no Python required), or:

pip install vexor  # also works with pipx, uv

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 19 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "name": "vexor-marketplace",
  3. "metadata": {
  4. "description": "Marketplace for the Vexor Claude Code plugin (skills for indexing and semantic search)."
  5. },
  6. "owner": {
  7. "name": "scarletkc"
  8. },
  9. "plugins": [
  10. {
  11. "name": "vexor",
  12. "source": "./plugins/vexor",
  13. "description": "A semantic search engine for files and code (Vexor skill bundle).",
  14. "category": "developer-tools",
  15. "tags": ["search", "indexing", "cli"],
  16. "strict": true
  17. }
  18. ]
  19. }
README.md · README · 191 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. <img src="https://raw.githubusercontent.com/scarletkc/vexor/refs/heads/main/assets/vexor.svg" alt="Vexor" width="35%" height="auto">
  3. # Vexor
  4. [![Python](https://img.shields.io/badge/python-3.11%2B-blue)](https://www.python.org/downloads/)
  5. [![PyPI](https://img.shields.io/pypi/v/vexor.svg)](https://pypi.org/project/vexor/)
  6. [![CI](https://img.shields.io/github/actions/workflow/status/scarletkc/vexor/publish.yml?branch=main)](https://github.com/scarletkc/vexor/actions/workflows/publish.yml)
  7. [![Codecov](https://img.shields.io/codecov/c/github/scarletkc/vexor/main)](https://codecov.io/github/scarletkc/vexor)
  8. [![CodeRabbit Pull Request Reviews](https://img.shields.io/coderabbit/prs/github/scarletkc/vexor?utm_source=oss&utm_medium=github&utm_campaign=scarletkc%2Fvexor&labelColor=171717&color=FF570A&link=https%3A%2F%2Fcoderabbit.ai&label=CodeRabbit+Reviews)](https://coderabbit.ai)
  9. [![License](https://img.shields.io/github/license/scarletkc/vexor.svg)](https://github.com/scarletkc/vexor/blob/main/LICENSE)
  10. [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/scarletkc/vexor)
  11. </div>
  12. ---
  13. **Vexor** is a semantic search engine that builds reusable indexes over files and code.
  14. It supports configurable embedding and reranking providers, and exposes the same core through a Python API, a CLI tool, and an MCP server.
  15. <video src="https://github.com/user-attachments/assets/4d53eefd-ab35-4232-98a7-f8dc005983a9" controls="controls" style="max-width: 600px;">
  16. Vexor Demo Video
  17. </video>
  18. ## Featured In
  19. Vexor has been recognized and featured by the community:
  20. - **[Ruan Yifeng's Weekly (Issue #379)](https://github.com/ruanyf/weekly/blob/master/docs/issue-379.md#ai-%E7%9B%B8%E5%85%B3)** - A leading tech newsletter in the Chinese developer community.
  21. - **[Awesome Claude Skills](https://github.com/VoltAgent/awesome-claude-skills?tab=readme-ov-file#development-and-testing)** - Curated list of best-in-class skills for AI agents.
  22. - **[Awesome MCP Servers](https://github.com/punkpeye/awesome-mcp-servers#-developer-tools)** - Curated list of Model Context Protocol servers.
  23. - **[Awesome CLI Apps](https://github.com/agarrharr/awesome-cli-apps#search)** - Curated list of command-line apps.
  24. ## Why Vexor?
  25. When you remember what a file *does* but forget its name or location, Vexor finds it instantly—no grep patterns or directory traversal needed.
  26. Designed for both humans and AI coding assistants, enabling semantic file discovery in autonomous agent workflows.
  27. ## Install
  28. Download standalone binary from [releases](https://github.com/scarletkc/vexor/releases) (no Python required), or:
  29. ```bash
  30. pip install vexor # also works with pipx, uv
  31. ```
  32. ## Quick Start
  33. ### 0. Guided Setup (Recommended)
  34. ```bash
  35. vexor init
  36. ```
  37. The wizard also runs automatically before the first interactive operational
  38. command when no config exists. Configuration-management (`vexor config`), MCP,
  39. help, and version commands run directly.
  40. ### 1. Search
  41. ```bash
  42. vexor "api client config" # defaults to search current directory
  43. # or explicit path:
  44. vexor search "api client config" --path ~/projects/demo --top 5
  45. # in-memory search only:
  46. vexor search "api client config" --no-cache
  47. ```
  48. Vexor auto-indexes on first search. Example output:
  49. ```
  50. Vexor semantic file search results
  51. ──────────────────────────────────
  52. # Similarity File path Lines Preview
  53. 1 0.923 ./src/config_loader.py - config loader entrypoint
  54. 2 0.871 ./src/utils/config_parse.py - parse config helpers
  55. 3 0.809 ./tests/test_config_loader.py - tests for config loader
  56. ```
  57. ### 2. Explicit Index (Optional)
  58. ```bash
  59. vexor index # indexes current directory
  60. # or explicit path:
  61. vexor index --path ~/projects/demo --mode code
  62. ```
  63. Useful for CI warmup or when `auto_index` is disabled.
  64. ## Python API
  65. Vexor can also be imported and used directly from Python:
  66. ```python
  67. from vexor import index, search
  68. index(path=".", mode="head")
  69. response = search("config loader", path=".", mode="name")
  70. for hit in response.results:
  71. print(hit.path, hit.score)
  72. ```
  73. Configuration follows the same global and project-level resolution as the CLI.
  74. For runtime overrides, cache controls, and per-call options, see
  75. [`docs/api/python.md`](https://github.com/scarletkc/vexor/tree/main/docs/api/python.md).
  76. ## AI Agent Skill
  77. This repo includes a skill for AI agents to use Vexor effectively:
  78. ```bash
  79. vexor install --skills claude # Claude Code
  80. vexor install --skills codex # Codex
  81. ```
  82. Skill source: [`plugins/vexor/skills/vexor-cli`](https://github.com/scarletkc/vexor/raw/refs/heads/main/plugins/vexor/skills/vexor-cli/SKILL.md)
  83. ## MCP Server
  84. <!-- mcp-name: io.github.scarletkc/vexor -->
  85. [![vexor MCP server](https://glama.ai/mcp/servers/scarletkc/vexor/badges/score.svg)](https://glama.ai/mcp/servers/scarletkc/vexor)
  86. > [!NOTE]
  87. > The Agent Skill and the MCP server provide the same core capability — pick **one** per agent.
  88. > The skill teaches shell-capable agents (Claude Code, Codex) to drive the full CLI and assumes `vexor` is installed on PATH; the MCP server exposes search as native tools, works in any MCP client (Cursor, Windsurf, Zed, ...), and can bootstrap without prior setup via `uvx` and environment variables.
  89. Vexor ships a built-in [MCP](https://modelcontextprotocol.io) stdio server, so any MCP-capable agent can use semantic file search as a native tool:
  90. ```bash
  91. claude mcp add vexor -- vexor mcp # Claude Code
  92. codex mcp add vexor -- vexor mcp # Codex
  93. ```
  94. Or configure manually in any MCP client, optionally supplying the API key
  95. and any config overrides via `env` (no `vexor init` needed):
  96. ```json
  97. {
  98. "mcpServers": {
  99. "vexor": {
  100. "command": "vexor",
  101. "args": ["mcp"],
  102. "env": {
  103. "VEXOR_API_KEY": "sk-...",
  104. "VEXOR_CONFIG_JSON": "{\"provider\": \"gemini\", \"rerank\": \"bm25\"}"
  105. }
  106. }
  107. }
  108. }
  109. ```
  110. The server exposes two tools: `vexor_search` (semantic file search, returning the matching source text so an agent rarely needs a follow-up file read) and `vexor_index` (explicit index warm-up). No extra dependencies are required. Vexor is listed on the [official MCP registry](https://registry.modelcontextprotocol.io) as `io.github.scarletkc/vexor`. See [`docs/mcp.md`](https://github.com/scarletkc/vexor/tree/main/docs/mcp.md) for tool schemas, environment variables, and client setup details.
  111. ## Configuration
  112. ```bash
  113. vexor init # guided setup (recommended)
  114. vexor config --set-api-key "YOUR_KEY" # or env: VEXOR_API_KEY / OPENAI_API_KEY / ...
  115. vexor config --set-provider openai # default; also gemini/voyageai/custom/local
  116. vexor config --rerank hybrid # optional: fuse exact keyword + semantic ranking
  117. vexor config --show # view effective settings and origins
  118. ```
  119. Global config lives in `~/.vexor/config.json`; the nearest
  120. `<project>/.vexor/config.json` can override a restricted set of behavior fields
  121. for that project. Non-secret fields can also be injected via `VEXOR_CONFIG_JSON`
  122. (useful for MCP clients and CI), and fully offline use is supported through
  123. local embedding models.
  124. See [`docs/configuration.md`](https://github.com/scarletkc/vexor/blob/main/docs/configuration.md) for the complete reference: project config fields and precedence, all config commands, API keys and environment variables, rerank strategies (hybrid / BM25 / FlashRank / remote), remote vs local providers, embedding dimensions, and offline local model setup.
  125. ## CLI Reference
  126. Everyday usage fits in `vexor "query"`, `vexor search`, and `vexor index` (see Quick Start). The full command table, common flags, index modes (`--mode auto/name/head/brief/full/code/outline`), `.vexorignore` files, project-local indexes (`vexor index --local`), cache behavior, and porcelain output format are documented in [`docs/cli.md`](https://github.com/scarletkc/vexor/blob/main/docs/cli.md).
  127. ## Documentation
  128. - [Configuration](https://github.com/scarletkc/vexor/blob/main/docs/configuration.md) — providers, API keys, rerank, embedding dimensions, local models
  129. - [CLI reference](https://github.com/scarletkc/vexor/blob/main/docs/cli.md) — commands, flags, index modes, cache behavior
  130. - [MCP server](https://github.com/scarletkc/vexor/blob/main/docs/mcp.md) — client setup, environment variables, tool schemas
  131. - [Python API](https://github.com/scarletkc/vexor/blob/main/docs/api/python.md) — programmatic usage
  132. - [Collections API](https://github.com/scarletkc/vexor/blob/main/docs/api/collections.md) — database-backed text records and filtered search
  133. ## Contributing
  134. Contributions, issues, and PRs welcome! Commit messages and PR titles follow [Conventional Commits](https://www.conventionalcommits.org) (e.g. `feat(mcp): add stdio server`). Star if you find it helpful.
  135. ## Star History
  136. [![Star History Chart](https://api.star-history.com/svg?repos=scarletkc/vexor&type=date&legend=top-left)](https://www.star-history.com/#scarletkc/vexor&type=date&legend=top-left)
  137. ## License
  138. [MIT](http://github.com/scarletkc/vexor/blob/main/LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.