01 · Roasts
README-Driven Development
agentic-research-lab is 2 days old, 7MB, no tests, no CI, no license — but somehow has ARCHITECTURE.md. You're writing docs for code that doesn't exist yet.
scaleless Indeed
scaleless: 0 commits, 0 files, 0 KB. The repo name is doing a lot of heavy lifting for a folder that has never seen a keystroke.
Burst Shipper, No Sitter
codegraph-mcp, typai, agent-relaybase all launched within a 2-week window. You clearly can sprint — but 0 stars across 11 repos suggests nobody knows the sprint happened.
3 Followers, 15 PRs
You've filed 15 external PRs this year but only 3 people follow you. Your contributions are invisible to the audience that would reward them.
The Heatmap Crater
Weeks 0–8 of your year are completely empty — a 9-week dead zone. Then you discovered GitHub in week 9 and shipped 7 repos in 3 weeks. Consistency is not your love language.
Built using
Zoral
Shadows one worker for a week, then takes over their job with zero extra setup. Behaves exactly like the original.
zoral.ai
02 · Category breakdown
- Impact25% weight62C
- Consistency20% weight65C
- Quality20% weight72B
- Depth15% weight65C
- Breadth10% weight80A
- Community10% weight25F
03 · Stats
365-day commit heatmap
51 active days
Language distribution
- Rust40%
- TypeScript16%
- Python14%
- Shell11%
- JavaScript7%
- Go4%
- Other8%
04 · Numbers
Owned repos
non-fork
23
Commits
last 12 months
262
Followers
3
Joined GitHub
Oct 2023
05 · Top repos
Cameloo1 /
codegraph-mcp
Early-stage Rust tool for code graph indexing and retrieval. Typed, well-documented (README + ARCHITECTURE.md + STATUS.md), comprehensive test suite, CI/CD in place. 30 recent commits across 16 days show active development but limited external adoption (0 stars).
Cameloo1 /
agent-search-tool
Research-grade TypeScript evidence engine for AI agents with 8-stage pipeline, deterministic fallbacks, comprehensive scoring & dedup logic, published on npm (@agent-search/sdk), but zero stars/forks and minimal adoption signals yet.
Cameloo1 /
machine-learning-projects
Portfolio of 11 self-contained ML projects spanning market regimes, trading agents, SOC anomaly detection, AutoML, and model serving; typed Python, comprehensive docs, and reproducibility verification harness.
Cameloo1 /
typai
Alpha-stage deterministic spelling correction engine: C++ core compiled to Wasm with TypeScript adapters for text editors. Typed, documented, tested, and CI-gated; 5MB codebase with multi-package monorepo structure (core, adapters, plugins). Not yet published; no production adoption visible.
Cameloo1 /
agent-relaybase
TypeScript MCP server for local app lifecycle management with stable routing, health checks, and process control. Early-stage shipping project with strong docs, tests, and CI, but minimal ecosystem adoption yet.
Cameloo1 /
nvidia-dev-codex-plugin
Early-stage NVIDIA integration plugin for Codex with comprehensive planning scope (Unreal/Unity DLSS, D3D12 DXR, NRD, RTX Video SDK, NVENC/NVDEC), documented architecture, CI, and MIT license. Only 1 star and 8 of last 30 commits; 10-day-old project shipping scope without proven adoption or implementation examples.
Cameloo1 /
red-triage
A nascent Go-based incident response triage CLI tool with multi-platform support and detection engine. Typed, documented, and structured (cmd/, collector/, detector/, reporter/) but nascent adoption (0 stars), minimal git history, incomplete implementation (truncated source files), and untested production readiness.
Cameloo1 /
openrouter-codex-plugin
Early-stage MCP server plugin for OpenRouter model catalog with comprehensive feature list (search, pricing, SDK generation), MIT license, and structured documentation, but no tests, CI, or sample code visibility.
Cameloo1 /
agentic-research-lab
Early-stage agentic research platform with ambitious scope (staged architecture, Codex integration, multi-runtime support) but minimal adoption (0 stars, 7MB codebase). Created 2 days ago with sparse commit history and no tests, CI, license, or type safety. README describes extensive CLI capabilities but incomplete imp
Cameloo1 /
cameloo1
Personal portfolio README with no actual code shipped. 1584 KB size suggests boilerplate or empty structure. 30 commits in 7 days, no tests, untyped Python, lacks substance beyond self-introduction.
Cameloo1 /
scaleless
Empty scaffold with zero commits, no files, no documentation, and no meaningful content. Created and pushed same timestamp indicates initial repo setup only.
06 · Timeline
- Oct 11, 2023Joined GitHub
- Aug 26, 2025Created red-triage — Professional Incident Response Triage Tool - Cross-platform CLI for rapid incident assessment, artifact collection, and threat detection. Built in Go with multi-terminal support.
- Nov 22, 2025Created machine-learning-projects — A collection of machine learning models and projects that increase in complexity and difficulty. Mainly to sharpen machine learning and quantitive finance skills, as well as build
- Apr 30, 2026Created openrouter-codex-plugin — Build AI apps with ease using an Openrouter Codex plugin for live lookups.
- May 4, 2026Created nvidia-dev-codex-plugin — Codex plugin for NVIDIA RTX, DLSS, Streamline, Reflex, Nsight, RTX Video SDK, and Video Codec SDK integration planning and validation.
- May 6, 2026Created agent-relaybase — Agent Relaybase lets AI agents manage multiple local dev servers from one place, with stable routes, start/stop control, health checks, and logs through MCP.
- May 7, 2026Created agent-search-tool — A research grade embeddable engine & search tool for AI agents.
- May 8, 2026Created codegraph-mcp — Local code-graph evidence layer for AI coding agents. Indexes repos into typed program graphs and returns context packets labeled by claim type.
- May 15, 2026Created scaleless
- May 17, 2026Created typai — Light, embeddable, deterministic, context-aware writing intelligence & autocorrect. No server, no model.
- May 20, 2026Created cameloo1
- May 21, 2026Created agentic-research-lab — Codex-based research lab with custom dedicated quant, ml, and business modeling tools, with smart data processing and storage and cost management.
- May 27, 2026Most recent push to cameloo1
07 · Compare
08 · Rubric
How this score was produced
Overall = Σ (category × weight) + gentle top-end curve
Tier thresholds
▸ How the pipeline works
- 01Scrape.Pull every non-fork repo pushed in the last 90 days, plus your contribution calendar, followers, and language byte counts — straight from GitHub's REST & GraphQL APIs.
- 02Triage.A small model reads every repo's file tree + README and picks the 20 files per repo that actually reveal how you code.
- 03Grade each repo. All repos run in parallel through a fast scoring model that reads the picked files and rates each one independently on Impact, Quality, and Depth — with evidence citations.
- 04Aggregate. A larger reasoning model combines the per-repo scores with server-computed stats (heatmap, commit cadence, language entropy, follower count) to produce the 6-dimension profile score + roasts.
- 05Correct.Deterministic server-side checks enforce anchor-scale floors (e.g. a profile with 2,000+ public commits can't score 30 Consistency) and recompute the final verdict.
~90 seconds per profile, ~$0.25 in compute. Total of ~240 files read across your top-12 repos. One rating per GitHub account per day.
▸ Data sources & caveats
- Heatmap & commit totals: GitHub GraphQL
contributionsCollection— covers the last 365 days, includes private repos when the user has opted in (default). - Language %: byte totals across the top 30 owned non-fork repos.
- Curve: a small upward nudge centered on raw score ≈ 70, capping at 100. Prevents specialists from being unfairly penalised for narrow breadth.
- Anchor corrections: when server-measured signals (e.g. privateWorkLikely, multiRepoVolume, follower count) mandate a minimum category score, the aggregation step enforces it. These are signal-conditional, not identity-based floors.