Research

Everything we publish, grouped by area.

Deepfake detection

Detectors that show where they look and how far their scores can be trusted.

xdfdet
Code and eight trained EfficientNet-B4 deepfake detectors from the thesis, with Grad-CAM region analysis and a public site with interactive detection and estimation games.

Code: MIT. Weights: CC BY-NC 4.0, under FaceForensics++ terms.

Small models that answer questions in English, Turkish and German with calibrated probabilities, on a laptop CPU.

JevAlt
Three open decision models for English, Turkish and German. Each answer comes with a calibrated probability, and the models run in about 3 GB of RAM.
Emberwick

A medieval village in the browser where the JevAlt models decide how villagers respond to storms, fires, markets and wolves at dusk.

Agents and tools that run on your own machine.

Tholos
Small agents sharing a local workspace of tables, notes and a task board, with allow, ask and deny rules for each action.
- GitHub
reevesagents
Open source software development

A local tmux workspace for coding agents, with a CLI, terminal interface, web interface and MCP server in one Apache-2.0 npm package.
- GitHub
- npm

Tholos-2B
A 2B agent model fine-tuned from MiniCPM5-2B on executed trajectories, released under Apache-2.0 with GGUF builds.
- GGUF

One of the best research efforts on language preservation with small local models.

Eldalambë

A small language model that reads and writes Quenya and Sindarin, including Tengwar script, grounded in a grammar-verified corpus, with tools for translation, lookup, inflection and Tengwar rendering.

Code and weights are private. Demo by invitation.

Open tests and their results.

JevOss
An open test bench for decision models using the Jev API, measuring accuracy, probability calibration and failure cases.
- GitHub
jevalt-bench

Benchmark and live-test results for JevAlt and the comparison models.
Tholos-Bench

160 scenarios for local agents, each scored on the final state of the workspace.