Skip to content
Atlas profile

TacoTakumi

@TacoTakumiVerified GitHub profile

AI-Atlas score

Specialist
0100
Strongest
AI Agents
73.7/100 domain score
Rank
2nd=
Canada
1st=
  • CanadaLocation
  • 6 Nov 2026Mapped
  • 9 / 19AI projects
01Skills matrix

AI Skills Matrix

AI Skills Matrix scores, 0 to 100
Machine Learning57
Computer Vision20
Data Science0
NLP & LLMs71
AI Agents74
MLOps37

Each node is one domain, scored only from evidence in these public repositories. Select one to see why.

Deep, repeated, well-engineered work in this domain.

02Evaluated projects6 of 9

19 public repositories → 9 with AI work, evaluated. The other 10 (repositories without AI code, forks and empty repositories) are not scored and have no effect on the result. How repositories are selected

Ranked by contribution

Ordered by how much each project adds to the Atlas score, not by its own score. A project with evidence in several domains can rank above one with a slightly higher project score. Choose a domain to focus on the projects with meaningful evidence there.

01
67.3

Advanced

34% of Atlas Score

AI Developer Tool· Python

Agent Wiki is a Python-based tool that provides a plain-markdown vault for AI agents to store and retrieve knowledge, featuring a CLI, HTTP server, and integrations with agents like Claude Code and OpenCode for persistent memory across sessions.

AI Agents0.95NLP & LLMs0.90Machine Learning0.60
agent-memoryai-agentsclaudeclaude-codecli
02
65.0

Advanced

24% of Atlas Score

AI Developer Tool· Python

VRAM Lend is a tool that enables inference engines to lend GPU memory to other processes while continuing to serve requests, consisting of a borrower CLI, documentation for engine integration, and benchmarks/tests. It is designed for use with large Mixture of Experts models on consumer GPUs.

NLP & LLMs0.80Machine Learning0.70MLOps0.50AI Agents0.40
deepseek-v4-1-flashglm-5-3-flashinference-enginelocal-aiproject-maya
03
66.7

Advanced

16% of Atlas Score

AI Developer Tool· TypeScript

pi-clearthen is a TypeScript extension for the pi coding agent that provides a `/clearthen` command to clear the agent's context and run a prompt, featuring a self-clearing handoff mode for managing long tasks via automatic context boundary detection and handoff document generation.

AI Agents0.90NLP & LLMs0.80Machine Learning0.20
04
65.3

Advanced

5% of Atlas Score

AI Developer Tool· Python

AgentSquire is a Python library and CLI tool that enables developers to package and install agent skills into various agent harnesses (such as Claude Code, pi, Hermes, and opencode) from their Python packages.

AI Agents0.90
agent-skillsclillmllm-agentspython
05
51.2

Implementation

5% of Atlas Score

AI Developer Tool· Python

The repository provides a Hermes plugin that enables Hermes to use llama.cpp servers (llama-server or llama-swap) as a model provider, featuring endpoint detection, template capability probing, and reasoning control.

AI Agents0.90NLP & LLMs0.80Machine Learning0.30
06
52.9

Implementation

5% of Atlas Score

ML Application· Kotlin

HermesConsole is an Android application that provides an always-on voice console for a wall tablet, integrating wake word detection, speech-to-text, text-to-speech, and an LLM agent via Hermes gateway to enable hands-free voice interactions.

Machine Learning0.70NLP & LLMs0.60AI Agents0.50