AI-Atlas score
| Machine Learning | 34 |
|---|---|
| Computer Vision | 14 |
| Data Science | 22 |
| NLP & LLMs | 65 |
| AI Agents | 57 |
| MLOps | 15 |
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.
44 public repositories → 4 with AI work, evaluated. The other 40 (repositories without AI code, forks and empty repositories) are not scored and have no effect on the result. How repositories are selected
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.
61% of Atlas Score
Kondi is an MCP proxy that aggregates multiple upstream MCP servers and exposes them as a single MCP server with meta‑tools for tool search, code‑filtered search, and execution, accompanied by a CLI, daemon, and Tauri‑based GUI.
36% of Atlas Score
UltimaDB is a high-performance embedded database for Rust with MVCC, WAL, custom indexes, and vector search, featuring formal verification of its B-tree core via Lean.
2% of Atlas Score
ultima_cluster is a State Machine Replication application server implemented in Rust, designed to provide correct, resilient, and high-performance distributed applications. It includes consensus, networking, storage, cryptography, and client SDKs, with extensive documentation and benchmarking.
<1% of Atlas Score
The hi-perf-cmp repository is a cross-language benchmarking suite comparing Rust, Java, and Go in state-machine-replication (SMR) system paths under identical conditions. It includes a uniform benchmark harness, a journal tool for recording and comparing runs, and AWS provisioning infrastructure for real-host measurements.
