Independent research lab.
Peer-reviewable output.

Skelf Research is an independent UK AI research lab. 25 production-grade open-source projects. Five research pillars. One methodology: every hypothesis is a runnable, testable, peer-reviewable repository. The most-replicable, hardest-to-fake moat in open-source AI research.

What makes Skelf different

01

Independent research lab

No venture backing, no product, no hosted service. The output is peer-reviewable software, not proprietary technology. The lab is funded by the founders and supported by academic and research partnerships.

02

25 production-grade open-source projects

Every project is a real artefact that someone has used: MIT or GPL-3.0 licensed. No demos, no toy repos. The GitHub stars and forks are real (and modest — we are early).

03

Five research pillars

LLM Cognition & Prompt Theory, Safe & Verifiable Computing, Formal Optimisation & Decision Science, Edge Intelligence & On-Device AI, and Robotics & Autonomous Systems. Each pillar has multiple projects, an article series, and a community of contributors.

04

Methodology is the moat

Hypotheses as software. Every research question is encoded in a runnable, testable, falsifiable repository. This is the part that compounds — every year we have more artefacts that are public, peer-reviewable, and impossible to replicate without doing the work.

05

Geographic and regulatory positioning

United Kingdom. EU AI Act, GDPR, SOX, HIPAA — Skelf's projects (mpl, perishable, zviz) are designed for the regulated enterprise from day one. We do not need to retrofit compliance; it is the design constraint.

06

Multi-language stack

Rust, Go, Zig, Python, Dart, Lua, JavaScript, TypeScript. The thesis is language-agnostic — we choose the language for falsifiability, not fashion. The system is not a single point of failure.

Geographic focus

We target the markets where open-source AI infrastructure has the highest leverage: US, UK, EU, Canada, AUSNZ, Japan, China. Our 5,380 quarterly Google impressions (3 months) come predominantly from these regions; we convert almost none of them. That gap is the opportunity.

RegionQuarterly impressionsClicksTarget?Focus
US 3,256 0 Yes AI infrastructure, on-device, observability
UK 133 3 Yes EU AI Act, GDPR, fintech, sovereign AI
India 143 1 No (deprioritised; non-target region)
Canada 155 0 Yes Sovereign AI, MILA, Toronto Vector Institute
Germany 105 0 Yes EU AI Act, Max Planck, formal methods
France 81 0 Yes INRIA, formal methods, sovereign AI
Australia 59 0 Yes ANZ fintech, sigc quant trading
Japan 50 0 Yes Sakana, Preferred Networks, formal verification
Netherlands 48 0 Yes EU AI Act, A11Y, edge AI

The portfolio

25 production-grade open-source projects, organised by pillar. Click through for the deep dive, GitHub stars, license, and comparison with the alternatives.

LLM Cognition & Prompt Theory

promptel · blogus · memorg · mpl · mullama · perishable · route-switch · l0l1 · direktor

Safe & Verifiable Computing

zviz · numaperf · liath · liath-rs · memista · embedcache · polymathy

Formal Optimisation & Decision Science

savanty · compere · sigc

Edge Intelligence & On-Device AI

llamafu · ukkin · anouk · slorg

Robotics & Autonomous Systems

waremax

Roadmap

  1. 2026 H1 25 public repositories, 5 research pillars, 12 long-form research articles, 28 glossary terms
  2. 2026 H2 3-5 new repositories, expanded article series on prompt theory and on-device AI, comparison articles for every project, /research taxonomy page
  3. 2027 H1 First external research collaborations; first papers co-authored with academic partners; expanded robotics pillar
  4. 2027 H2 Foundation / research-grant partnerships; second wave of projects in compliance + robotics

Team

Dipankar Sarkar

Researcher · Founder

Independent AI researcher. Designs and implements the projects. Writes the articles. Edits the YAMLs.

Contact

  • Research collaborations contact@skelfresearch.com
  • Press and media contact@skelfresearch.com
  • GitHub organisation github.com/Skelf-Research