Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Engineering toolkit for building scalable AI systems, including model training pipelines, LLM optimization utilities, and data engineering tools.
| Date | Stars |
|---|---|
| 2026-07-31 | 474 |
| 2026-09-05 | 474 |
| 2026-09-15 | 475 |
| 2026-09-23 | 475 |
| 2026-11-04 | 475 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# 5.0 — AI Engineering Toolkit [](https://github.com/evelyyyyynnnnn/5.0-Ai-Engineering-Toolkit/actions/workflows/tests.yml) Shared, installable engineering infrastructure behind the endeavor. Four rebuilt projects carry it. Part of a five-repository portfolio supporting the endeavor described in the EB2-NIW petition: **optimization-driven, system-level decision frameworks** — integrating operations research, mathematical optimization and applied AI — for domains where a wrong decision carries systemic consequences. The three pillars are financial stability, healthcare safety and secure digital infrastructure. | | | |---|---| | Petition-grade projects today | 0 original, NIW-relevant projects | | Verdict | **Rebuild around its own name** | > "Petition-grade" means: original work, a stated method, real data at a stated > scale, a measured result, and a README a reviewer can follow. Counts exclude > duplicates, forks of third-party work, retired projects, and asset-only > folders. ## Projects | Folder | Project | Pillar | Evidence value | |---|---|---|---| | [`3-quant-productivity-toolkit/`](3-quant-productivity-toolkit/) | Quant Researcher Productivity Toolkit | Financial Stability | CORE — the only honest route to the downloads claim | | [`2-llm-eval-calibration-harness/`](2-llm-eval-calibration-harness/) | LLM Evaluation & Calibration Harness for Finance | Cross-cutting | CORE — serves the hallucination and verification argument | | [`1-data-provenance-library/`](1-data-provenance-library/) | Data Provenance / Lineage Library | Financial Stability | CORE — the through-line of the whole endeavor | | [`4-risk-portfolio-saas/`](4-risk-portfolio-saas/) | Risk-Portfolio SaaS Prototype | Financial Stability | CORE — the strongest of the four Notion tool ideas | ## What each one is ### 1. Quant Researcher Productivity Toolkit — [`3-quant-productivity-toolkit/`](3-quant-productivity-toolkit/) The Notion 综合性工具 idea shipped as a real, installable package with public download statistics. *Why it earns its place:* The credible home for the "LLM agent platform, 2,000+ downloads" claim, which currently has no package behind it. *Target scale:* Public registry download statistics ### 2. LLM Evaluation & Calibration Harness for Finance — [`2-llm-eval-calibration-harness/`](2-llm-eval-calibration-harness/) Grounding, citation accuracy and refusal behaviour evaluation for LLMs applied to finance. *Why it earns its place:* Directly serves the hallucination and verification argument in Section 2 of the petition. *Target scale:* Public filings and public financial corpora ### 3. Data Provenance / Lineage Library — [`1-data-provenance-library/`](1-data-provenance-library/) Span-level citations from extracted values back to their source documents. *Why it earns its place:* Shared infrastructure with the private-credit project in 3.0; provenance is the through-line of your whole endeavor. *Target scale:* Shared across repos 3.0 and 5.0 ### 4. Risk-Portfolio SaaS Prototype — [`4-risk-portfolio-saas/`](4-risk-portfolio-saas/) The Notion 风控组合SaaS idea built as a working risk-portfolio prototype. *Why it earns its place:* Risk tooling maps directly onto the financial-stability pillar. Of the four items in the Notion 综合性工具 section, this is the one to build. *Target scale:* Portfolio universes from repo 3.0 ## Repository layout ``` 5.0-Ai-Engineering-Toolkit/ ├── 3-quant-productivity-toolkit/ ├── 4-risk-portfolio-saas/ ├── 1-data-provenance-library/ └── 2-llm-eval-calibration-harness/ ``` Every rebuilt project carries the same skeleton: `README.md`, `src/`, `data/`, `results/`, `tests/`, `website/`. > Earlier and off-theme prior work (dashboards, consumer apps, templates, and other non-endeavor folders) has been moved to a separate `archive-prior-work` repository to keep this repository focused on the endeavor. It remains
Excerpt of 4,778 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:0d892f8de42cc4f4, llm:Repository description: 'Engineering toolkit for building scalable AI systems, including model training pipelines, LLM optimization utilities, and data engineering tools.'
matched fp:0d892f8de42cc4f4, llm:Repository description: 'Engineering toolkit for building scalable AI systems, including model training pipelines, LLM optimization utilities, and data engineering tools.'
matched fp:0d892f8de42cc4f4, llm:Repository description: 'Engineering toolkit for building scalable AI systems, including model training pipelines, LLM optimization utilities, and data engineering tools.'
matched fp:0d892f8de42cc4f4, llm:Repository description: 'Engineering toolkit for building scalable AI systems, including model training pipelines, LLM optimization utilities, and data engineering tools.'