Gbrain

Skill onfire7777/universal-ai-skills-library/skills/gbrain

Use when the user asks for GBrain, personal knowledge brain setup, brain-first retrieval, local PGLite brain, hybrid RAG search, gbrain import/query/sync/embed, GBrain skills, Minions, durable agent jobs, soul-audit, brain maintenance, or integrating GBrain with gstack, Hermes, OpenClaw, Claude Code, or Codex.From its SKILL.md

Install

npx -y skills add onfire7777/universal-ai-skills-library --skill gbrain

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

14 stars14 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.1 KB, 713 tokens by cl100k_base, as published. Nobody here has run it

GBrain Universal Adapter

Canonical upstream checkout: %USERPROFILE%\gbrain

GBrain is a real CLI-backed personal knowledge brain. It is not just a skill pack. The universal stack keeps the upstream checkout and local brain state in one place, then exposes GBrain skills and commands through skill-router.

On Windows, the canonical GBrain binary is %USERPROFILE%\.bun\bin\gbrain.exe. The compatibility shim %USERPROFILE%\go\bin\gbrain.cmd delegates to it so AI hosts with an older inherited PATH still resolve gbrain without duplicating the install.

Core Commands

gbrain --version
gbrain doctor --json
gbrain stats
gbrain import <dir> --no-embed
gbrain embed --stale
gbrain search "<query>"
gbrain query "<question>"
gbrain sync --repo <brain-repo>
gbrain jobs smoke

Use keyword search without API keys. In the Universal AI Stack, text vector search uses the local Qwen embedding service through llama-server:qwen3-embedding-0.6b at http://127.0.0.1:18084/v1 with 1024 dimensions, so GBrain text embeddings do not require an OpenAI key. Anthropic query expansion and durable subagent workers require the relevant provider key only for those optional features.

Load GBrain Skills On Demand

The upstream GBrain skills are indexed from:

%USERPROFILE%\gbrain\skills

Examples:

skill-router skill brain-ops
skill-router skill signal-detector
skill-router skill query
skill-router skill ingest
skill-router skill media-ingest
skill-router skill maintain
skill-router skill minion-orchestrator
skill-router skill soul-audit
skill-router skill skillify

Before changing a GBrain workflow, read:

skill-router skill gbrain
skill-router skill brain-ops
skill-router skill query

For setup or repair, read the upstream installer flow first:

Get-Content "$env:USERPROFILE\gbrain\INSTALL_FOR_AGENTS.md"
Get-Content "$env:USERPROFILE\gbrain\AGENTS.md"
Get-Content "$env:USERPROFILE\gbrain\docs\GBRAIN_VERIFY.md"

Integration Policy

Keep %USERPROFILE%\gbrain as the single upstream source checkout.
Keep %USERPROFILE%\.gbrain for GBrain runtime state such as PGLite data and user-level GBrain skills.
Do not vendor GBrain's full skill tree into every AI root.
Use skill-router for on-demand loading and gbrain for persistent brain operations.
GStack and GBrain can cooperate: GStack supplies engineering process skills; GBrain supplies brain-first retrieval, memory, jobs, and durable agent context.

Maintenance

Follow the upstream upgrade path:

git -C "$env:USERPROFILE\gbrain" pull --ff-only
Set-Location "$env:USERPROFILE\gbrain"
bun install
gbrain init
gbrain post-upgrade
gbrain doctor --json

Do not run bun install -g github:garrytan/gbrain; upstream documents that this skips required install behavior.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.