yoanbernabeu avatar

Grepai Storage Gob

GOB storage is GrepAI's default backend that keeps your vector embeddings in a single local file using Go's binary format. It's dead simple for solo projects and small to medium codebases, requiring zero infrastructure setup. The index lives in .grepai/index.gob and loads entirely into RAM for sub-second searches. You'll hit limits around 10K files or when your index pushes past 1GB, at which point you should migrate to Postgres or Qdrant. Works great for local dev environments where you don't need to share the index across a team. Just add .grepai/ to your gitignore and let each developer run their own indexer.

skills.sh installs
692
GitHub stars
20
last updated
Aug 21, 2026

Install

$ npx -y skills add yoanbernabeu/grepai-skills --skill grepai-storage-gob --agent claude-code

Installs into .claude/skills of the current project.

Files

GrepAI Storage with GOB

This skill covers using GOB (Go Binary) as the storage backend for GrepAI, the default and simplest option.

When to Use This Skill

  • Single developer projects
  • Small to medium codebases
  • Simple setup without external dependencies
  • Local development environments

What is GOB Storage?

GOB is Go's native binary serialization format. GrepAI uses it to store:

  • Vector embeddings
  • File metadata
  • Chunk information

Everything is stored in a single local file.

Advantages

BenefitDescription
πŸš€ SimpleNo external services needed
⚑ Fast setupWorks immediately
πŸ“ PortableSingle file, easy to backup
πŸ’° FreeNo infrastructure costs
πŸ”’ PrivateData stays local

Limitations

LimitationDescription
πŸ“ ScalabilityNot ideal for very large codebases
πŸ‘€ Single userNo concurrent access
πŸ”„ No sharingCan't share index across machines
πŸ’Ύ MemoryLoads into RAM for searches

Configuration

Default Configuration

GOB is the default backend. Minimal config:

Sponsors

Details

Repository
github.com/yoanbernabeu/grepai-skills
First seen
Jun 3, 2026

More from yoanbernabeu/grepai-skills

All 27

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs