ATOM00blue - Overview (original) (raw)

Hi, I'm IRONBEEM -- Harnessing the sun's power to build things that matter.

Building toward ML systems, AI agents, and the infrastructure that scales them. Currently going deep on Rust and Go.

Focus

• Machine learning - training, inference, evaluation
• AI agents - tool use, planning, multi-agent orchestration
• System design - distributed systems, low-latency services, data pipelines
• Languages - Rust and Go for the systems layer, Python for ML work

Stack

Stats

Now

• Studying the internals of inference engines and modern agent frameworks
• Reading papers on RAG, tool use, planning, and long-context evaluation
• Open to collaboration on agent infrastructure and ML systems work

Popular repositories Loading

1. A hand-curated, topic-organized library of the best ML education — 923 docs (391 arXiv papers, 474 Stanford/MIT/Karpathy/fast.ai lectures, 58 explainer articles), normalized to Markdown with full p…
   Python 134 13
2. The complete AI stack, bottom-up from sand to a served token — a source-backed Obsidian vault. 15 domains, 110 topics, beginner to expert: semiconductor physics, fabs, GPUs, datacenters, power, coo…
   JavaScript 3
3. Where are your AI agent's tokens going? Per-session/file/tool token attribution from local Claude Code / Codex / Cursor logs. Single static Go binary, zero runtime deps, no telemetry.
   Go 2
4. WolfDB - the open-source, object-storage-native, bi-temporal memory database for AI agents.
   Python 2
5. MCP server that gives AI agents deep git intelligence: history, blame, hotspots, ownership, and diffs since any ref.
   TypeScript 1
6. Pre-flight risk check before npm/pip/cargo install. Single static Go binary. Built in response to the May 2026 npm Mini Shai-Hulud and Axios hijack supply-chain attacks.
   Go 1