whereismyai
Vexus
Vexus is a command-line tool that finds relevant code locally and adds location hints to AI coding agents.
Vexus indexes repositories locally to help AI coding agents locate relevant code before executing full-text searches. A hook runs on each prompt, identifies likely code locations, and provides a small set of hints to the agent. It supports macOS, Linux, and Windows, featuring a background file watcher to keep indexes updated automatically. An optional MCP server provides tools such as explore, open, trace, and status for clients like Cursor, Windsurf, and Cline. The system combines vector KNN and BM25 keyword results with graph expansion to deliver fast semantic search without sending code externally.
Vexus at a glance
- Best for: Software engineer
- Runs on: macOS, Linux, Windows, API, CLI
- Pricing: Free
- Released: November 2026
- Category: AI coding tool
- Website: github.com/faique43/vexus
Key features
- Hybrid retrieval combining vector KNN and BM25 keyword search
- Background file watcher to keep the index current
- Command-line tool for repository setup and management
- Optional MCP server for tools like explore, open, and trace
- Local embedding model execution without sending code externally
- Automatic index freshness checks on tool responses
Use it for
- Directing AI agents to relevant code locations before searches
- Exploring code repositories semantically using an MCP server
- Tracing symbol callers, callees, and change reachability
- Fetching exact file ranges or symbols for AI agents
Companions
Tools that articles about Vexus recommend using with it, each with its job.
- Context7 — Provides up-to-date documentation for AI agents and code editors.
- Ollama — Run local models at zero marginal cost, with code kept on your machine.
- OpenRouter — Access over 500 models and 80 providers through one unified API.
- Daytona — Runs sessions in isolated sandboxes synced to git branches.
- Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
- Oh My OpenCode Slim — Lightweight multi-agent orchestration and background tasks.
Alternatives to Vexus
- jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
- Vesalius — Cuts AI assistant tokens and turns roughly in half while answering questions.
- CodeGraph — It eliminates file crawling, reducing AI agent tool calls by 88% and cutting costs.
- OpenCode — Works with 75+ model providers, local models, and existing subscriptions
- SmallCode — Runs fully local with budget-managed context and a forgiving parser for small models.
- CodeSight — Reduces AI token usage significantly and maps projects instantly.
- OpenClaude — Connects one terminal interface to over 200 different AI models.
- Codebase Memory MCP — High-speed indexing and persistent knowledge graphs for AI coding agents.
- Mindwalk — Visualize how coding agents explore and edit files on a 3D repository map.
- Knock — It reduces token usage and provides codebase memory across agent sessions.
- Chemical X — Stops wasting agent context on CLI noise and compiler dumps.
- Velu — Evaluates documentation across 23 checks and 7 categories in seconds without a signup.
All Vexus alternatives