skills.rest
eduardtomasek
eduardtomasekCOMMUNITY
Explore all skills by this author →
GitHub

grepai-workspaces

Configure GrepAI workspaces to index and search multiple related projects together.

Updated May 12, 2026
Search Tags:#semantic search#microservices#mcp#workspace#monorepo#code indexing#grepai
One-click install
npx skills add https://github.com/eduardtomasek/codex-dev-stack --skill grepai-workspaces-eduardtomasek
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: grepai-workspaces
Source: https://github.com/eduardtomasek/codex-dev-stack/tree/main/skills/.agents/grepai-workspaces
Command: npx skills add https://github.com/eduardtomasek/codex-dev-stack --skill grepai-workspaces-eduardtomasek

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Searching across monorepos, microservices, or split frontend/backend codebases requires switching between separate indexes, making cross-project code discovery slow and fragmented. ## Core Features & Use Cases - Workspace Management: Create workspaces, add or remove projects, and inspect per-project indexing status with the grepai workspace commands. - Unified Indexing and Search: Index all projects with one watch process and run semantic searches across the whole workspace or filter to a single project. - MCP Integration: Serve a workspace through grepai mcp-serve so AI coding agents can query the combined index. - Use Case: A team maintaining a frontend, backend, and shared library creates a fullstack workspace, indexes all three projects, and searches for authentication logic across every repository at once. ## Quick Start Ask the assistant to create a GrepAI workspace, add your project directories to it, and index them for cross-project semantic search.

Frequently Asked Questions about grepai-workspaces

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search across multiple projects with GrepAI?▼

Create a workspace with grepai workspace create, add each project path with grepai workspace add, then index everything using grepai watch --workspace. After indexing, grepai search --workspace runs semantic search across all projects with results labeled by project.

How do I search only one project inside a GrepAI workspace?▼

Use the --project flag with your search command, for example grepai search --workspace my-workspace --project frontend "query". This restricts results to the named project while keeping the shared workspace index intact.

Can GrepAI workspaces be used with MCP servers?▼

Yes. Configure an MCP server entry that runs grepai mcp-serve --workspace <name>, and AI coding agents can query the combined workspace index through the MCP protocol.

Does deleting a GrepAI workspace delete my project files?▼

No. Running grepai workspace delete only removes the workspace configuration stored under ~/.grepai/workspaces/<name>/. Your source project directories on disk remain untouched.

Why is my GrepAI workspace search returning mixed results?▼

Mixed results happen because workspace search spans every indexed project by default. Add the --project flag to scope the query to a single project, or verify indexing status with grepai workspace status.

Related Skills

Explore More Software Engineering Skills→
yoanbernabeuyoanbernabeu
18

grepai-ollama-setup

Configure Ollama for private local embeddings in GrepAI.

Community
Advanced
yoanbernabeuyoanbernabeu
18

grepai-mcp-cursor

Integrate GrepAI semantic code search and call graph tools into Cursor via MCP.

Community
Intermediate
audibleblinkaudibleblink
4

grepai

Perform semantic code search and trace call relationships across codebases.

Community
Advanced
yoanbernabeuyoanbernabeu
18

grepai-troubleshooting

Diagnose and resolve GrepAI configuration, indexing, and MCP integration issues.

Community
Advanced