caveman
Caveman empire
The portfolio appears to have built an entire civilization around one caveman-themed flagship; at this point the roadmap probably arrives etched on stone tablets.
Roasts
cavekit
The mysterious toolkit
A project called cavekit with an unknown language is a wonderfully committed refusal to explain whether the cave contains tools, bats, or both.
Repository binding unavailable
Genre expansion
After JavaScript, TypeScript, and Python, Swift enters the cave: apparently the next phase is not a rewrite, but a full multilingual expedition.
Historical result · no repository binding was retained
Repository binding unavailable
The study artifact
A repository of class notes sits beside ambitious tools and AI projects, giving the portfolio the charming energy of someone documenting the lecture while quietly building the laboratory.
Historical result · no repository binding was retained
pebble
The borrowed pebble
The Swift fork named pebble is the smallest object in a very large cave, but even a borrowed pebble can become evidence of an expedition outside the main tunnel.
Category breakdown
Impact
25% weight
The portfolio includes a highly prominent JavaScript project, several related developer-tooling or AI-oriented projects, and multiple projects with substantial apparent external interest; metadata supports unusually strong visible impact.
Consistency
15% weight
The supplied repositories show recent activity across nearly the entire set, with dates concentrated in 2026 and additional activity in 2025.
Quality
25% weight
The non-fork, non-archived status and sustained activity are positive maturity signals, but source, tests, CI, documentation, and implementation quality are unavailable.
Depth
20% weight
The portfolio shows sustained ownership across a coherent family of projects, with many non-fork repositories and activity extending across multiple years.
Breadth
10% weight
Languages include JavaScript, TypeScript, Python, Swift, and an unknown-language project, spanning tooling, notes, AI-related work, libraries, and applications.
Community
5% weight
Follower and star counts provide a strong but limited community signal. This is used only as a weak tie-breaker and does not determine the other scores.
Stats
52-week commit heatmap
237 active daysLanguage distribution
5 langs
- Python33%
- JavaScript25%
- Swift17%
- TypeScript17%
- Unknown8%
Based on the bounded repository sample saved with this analysis.
Numbers
Owned repos
Non-fork sample
11
Commits
Last 12 months
1358
Followers
Accepted fact
2426
Joined GitHub
Profile date
Apr 2022
Top repos
Scores marked Profile rating use bounded public repository metadata. Full repo analysis appears only when a separate accepted repository analysis exists.
juliusbrussee /
caveman
95/100
A prominently visible, actively maintained JavaScript project with exceptionally high apparent external interest; its premise and implementation scope cannot be assessed from metadata alone.
OwnedActiveProfile ratingJavaScript
★ 97071 · 2d agoOpen on GitHub ↗
juliusbrussee /
cavekit
78/100
An actively maintained repository with the highest apparent interest among the supporting projects; its unknown language limits technical assessment.
OwnedActiveProfile ratingUnknown
★ 1137 · 2mo agoOpen on GitHub ↗
juliusbrussee /
caveman-code
75/100
An actively maintained TypeScript companion project with substantial apparent interest, suggesting a meaningful extension of the portfolio's central project theme.
OwnedActiveProfile ratingTypeScript
★ 912 · 2mo agoOpen on GitHub ↗
juliusbrussee /
cavemem
73/100
A recently updated TypeScript project with notable apparent interest, indicating a substantial project rather than a merely nominal repository.
OwnedActiveProfile ratingTypeScript
★ 669 · 1mo agoOpen on GitHub ↗
juliusbrussee /
revu-swift
70/100
An actively maintained Swift project with notable apparent interest, demonstrating ownership beyond the JavaScript, TypeScript, and Python cluster.
OwnedActiveProfile ratingSwift
★ 359 · 4mo agoOpen on GitHub ↗
juliusbrussee /
cavegemma
67/100
A recent Python project with a distinctive AI-oriented name and moderate apparent interest; ownership is clear, while maturity beyond metadata is unknown.
OwnedActiveProfile ratingPython
★ 113 · 1mo agoOpen on GitHub ↗
juliusbrussee /
skills
65/100
A recently updated JavaScript repository with moderate apparent interest, adding a practical-looking project dimension to the portfolio.
OwnedActiveProfile ratingJavaScript
★ 145 · 3d agoOpen on GitHub ↗
juliusbrussee /
the-prompt-library
58/100
A Python prompt-library project with recent activity and moderate apparent interest, representing a focused resource-oriented contribution.
OwnedActiveProfile ratingPython
★ 67 · 1y agoOpen on GitHub ↗
juliusbrussee /
auto-karpathy
56/100
A recently updated Python project with an AI-training-oriented name and some apparent interest, suggesting an ambitious experimental direction.
OwnedActiveProfile ratingPython
★ 27 · 4mo agoOpen on GitHub ↗
juliusbrussee /
loop-factory
55/100
A recent Python project with a focused, evocative name and some apparent interest; the available evidence suggests an exploratory but real project.
OwnedActiveProfile ratingPython
★ 16 · 2mo agoOpen on GitHub ↗
juliusbrussee /
dsai-2025-2026-class-notes
45/100
A JavaScript class-notes repository with recent activity but limited apparent external interest; it reads as useful learning or reference material rather than a flagship project.
OwnedActiveProfile ratingJavaScript
★ 3 · 10mo agoOpen on GitHub ↗
juliusbrussee /
pebble
38/100
A Swift fork with recent activity and limited apparent interest; it is evidence of experimentation or adaptation, but provides weaker evidence of wholly original ownership.
ForkActiveProfile ratingSwift
★ 3 · 29d agoOpen on GitHub ↗
Timeline
- Joined GitHub
- Created juliusbrussee/the-prompt-library - A curated collection of production‑ready AI prompts with MCP integration, organised for humans and machines alike.
- Created juliusbrussee/dsai-2025-2026-class-notes
- Created juliusbrussee/cavekit - A Claude Code plugin that turns natural language into blueprints, blueprints into parallel build plans, and build plans into working software with automated iteration, validation, and cross-model peer review.
- Created juliusbrussee/revu-swift - Local-first macOS study app with FSRS review, decks, study guides, exams, import/export, and a polished SwiftUI desktop interface.
- Created juliusbrussee/caveman - 🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
- Created juliusbrussee/caveman-code
- Created juliusbrussee/cavemem - Cross-agent persistent memory for coding assistants. Stored compressed. Retrieved fast. Local by default.
- Created juliusbrussee/auto-karpathy
- Created juliusbrussee/cavegemma - LoRA fine-tune Gemma 4 31B to speak caveman-mode natively. Style: github.com/JuliusBrussee/caveman
- Created juliusbrussee/loop-factory
- Created juliusbrussee/skills
- Created juliusbrussee/pebble - Pebble PC Port
- Most recent push to juliusbrussee/caveman
Compare
JULIUSBRUSSEE · 6DMEDIAN CODER
Rubric
How this score was produced
Overall = Σ(category × weight) + deterministic top-end curve
| Category | Weight | Score | Contribution |
|---|---|---|---|
| Impact | 25% | 91 | 22.75 |
| Quality | 25% | 72 | 18.00 |
| Depth | 20% | 88 | 17.60 |
| Consistency | 15% | 87 | 13.05 |
| Breadth | 10% | 84 | 8.40 |
| Community | 5% | 76 | 3.80 |
Impact · 91/100
What it measures. Project usefulness, ambition, originality, and coherence. Popularity is not impact.
Evidence for juliusbrussee. The portfolio includes a highly prominent JavaScript project, several related developer-tooling or AI-oriented projects, and multiple projects with substantial apparent external interest; metadata supports unusually strong visible impact.
Quality · 72/100
What it measures. Engineering and project-maturity signals supported by the available public metadata.
Evidence for juliusbrussee. The non-fork, non-archived status and sustained activity are positive maturity signals, but source, tests, CI, documentation, and implementation quality are unavailable.
Depth · 88/100
What it measures. Sustained ownership, meaningful scope, and continued maintenance rather than one-shots.
Evidence for juliusbrussee. The portfolio shows sustained ownership across a coherent family of projects, with many non-fork repositories and activity extending across multiple years.
Consistency · 87/100
What it measures. Recency and contribution patterns across the supplied activity window.
Evidence for juliusbrussee. The supplied repositories show recent activity across nearly the entire set, with dates concentrated in 2026 and additional activity in 2025.
Breadth · 84/100
What it measures. Language entropy and project-type diversity across owned repos.
Evidence for juliusbrussee. Languages include JavaScript, TypeScript, Python, Swift, and an unknown-language project, spanning tooling, notes, AI-related work, libraries, and applications.
Community · 76/100
What it measures. A weak positive tie-breaker for supplied community signals, never a popularity penalty.
Evidence for juliusbrussee. Follower and star counts provide a strong but limited community signal. This is used only as a weak tie-breaker and does not determine the other scores.
- Raw total
- 83.60
- Top-end curve
- +0.00
- Final overall
- 83.6
Tier thresholds
S 90-100 Mass-producing humansA 80-89 Ship machineB 70-79 Solid engineerC 60-69 Getting thereD 40-59 README enthusiastF 0-39 GitHub tourist
I. How this saved profile rating was produced
- 01
Validate. The server validates the login, signed browser session, attempts, cooldown, daily ceiling, and the single provider permit.
- 02
Collect. The VPS collector reads bounded public profile metadata and up to 12 recent repository metadata rows in volatile memory.
- 03
Rate. One pinned provider returned a closed profile-rating object with no tools, browsing, shell, or repository-content access.
- 04
Verify. Server checks bound the subject, rejected unsafe or echoed text, validated the schema, and recomputed rubric-v3 final arithmetic.
- 05
Save. Only a valid completion and allowlisted post-completion facts commit atomically; the public projection is then rebuilt.
This saved profile analysis is metadata-only and did not read repository trees, README files, or source code. Availability of new analysis is separate from this historical result.
Rated 2026-08-10 · rating-rubric/3
II. Data sources & caveats
- Scores summarize one accepted, subject-bound analysis; they are not a security audit or endorsement.
- Rank, percentile, and median use 1095 currently accepted public profiles and can change as the leaderboard changes.
- Repository and language details reflect the bounded analyzed sample, not necessarily every repository.
- Missing data is shown as unavailable or not evaluated instead of being inferred as zero.
- Analysis completed Aug 10, 2026, 12:10 AM UTC and is marked aging.