We are an open-source organization working next to research in LLMs, diffusion models, and efficient local inference: tools, experiments, and shared artifacts anyone can build on.
Organization site (overview, news): inference-foundry.github.io
Members (handbook & roster): .github-private — private repo; org access required.
Project index & plans: docs/projects
| Project | What it is | Links |
|---|---|---|
| super-ollama | Terminal-native, in-process local LLM engine (no HTTP in the main UX); llama.cpp via CGo, focus on low overhead and clean teardown. |
Repo · Roadmap (wiki) |
| Crucible | Open research journal and experimental log. | Repo |
| BitForge (planned) | Quantization theory, methods, and reproducible experiments across bit-widths and runtimes. | Repo TBD — org doc |
| Lexicon (planned) | Open fine-tuned prompt catalog with versioning, licensing, and analysis for reuse. | Repo TBD — org doc |
| Argus (planned) | Algorithms to detect AI-generated images using JEPA-based representations. | Repo TBD — org doc |
- Contributing (org-wide): CONTRIBUTING.md — each repository may add stricter or domain-specific rules.
- Code of conduct: CODE_OF_CONDUCT.md
- Security reporting: SECURITY.md
- Community: Discord — architecture, papers, and tooling discussion.
Inference Foundry — open tools and honest measurements.
