AgentStack
SKILL verified MIT Self-run

Gbrain Lite

skill-cosmicstack-labs-mercury-agent-skills-gbrain-lite · by cosmicstack-labs

Lightweight personal knowledge base — markdown + YAML frontmatter structured notes with full-text search and cross-referencing for AI agents

No reviews yet
0 installs
11 views
0.0% view→install

Install

$ agentstack add skill-cosmicstack-labs-mercury-agent-skills-gbrain-lite

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Gbrain Lite? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

GBrain Lite — Lightweight Personal Knowledge Base

> Organize books, people, concepts, and news items from conversations into a searchable, cross-referenced markdown knowledge base.

Workspace

  • Knowledge base directory: brain/
  • Subdirectories by type: books/ people/ meetings/ ideas/ articles/ projects/ news/
  • One entry = one .md file
  • News entries by date: news/YYYY-MM-DD/

Workflow

  1. Trigger check — Book/person/concept/news mentioned in conversation → proactively check brain
  2. Search — Full-text search in brain/ directory (ripgrep/grep)
  3. Decide
  • Existing entry → reference it, update if needed
  • No entry + important → create immediately
  • No entry + uncertain → ask user
  1. Create — Write brain/{type}/{slug}.md
  • Slug: lowercase/hyphenated
  • Must include YAML frontmatter (title, type, date, tags, summary)
  1. Cross-reference — Update links field in related entries
  2. Sync — Keep key entry index in agent memory

Rules

  • Don't dump long content directly into agent memory — prefer brain
  • Don't create entries without title and date
  • Don't skip the summary field — search and listing depend on it
  • Don't manually write updated — it auto-updates on save
  • News entries must use item_id as dedup key (format: github:owner/repo / hn:12345 / arxiv:url)
  • Don't do full overwrite updates on existing entries — use targeted patches

Validation

  • [ ] New entry has complete frontmatter (title, type, date, tags, summary)
  • [ ] Full-text search finds the new entry
  • [ ] News entries contain item_id + first_seen + star_history (GitHub entries)
  • [ ] Agent memory usage below 90%, otherwise trigger distillation to brain

Pitfalls

Brain vs Memory confusion

  • Symptom: Long-form content consumed all agent memory space
  • Root cause: Everything dumped into memory instead of brain
  • Fix: >500 chars → brain entry; memory only keeps index pointers. (Fixed: 2026-05-12)

Missing item_id on news entries

  • Symptom: Duplicate news entries accumulate, dedup impossible
  • Root cause: Agent skipped item_id field when creating news entries
  • Fix: Always include item_id for news entries, validated in creation workflow

References

  • references/garry-tan-gbrain-inspiration.md — GBrain system design reference

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.