j-sperling
Follow
Stars
A pattern-based approach to learn technical interview questions
AtomMem: a long-term memory system for personalized LLM agents.
An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.
Vercel's official collection of agent skills
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
Fused Triton kernels for late-interaction (MaxSim) scoring
The open agent skills tool - npx skills
AI-powered travel hacking and search with cash, points, miles, and award flights. Drop-in skills and MCP servers for Claude, Codex, and OpenCode.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
Puzzles for exploring transformers
Solve puzzles. Improve your pytorch.
SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
Puzzles for learning Triton
autonomous nanogpt optimizer speedrun
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.
Every API has a secret identity. This finds it, absorbs every feature from every competing tool, then builds the GOAT CLI — designed for AI agents first, with SQLite sync, offline search, and compo…
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.
resume any AI coding session in another tool — Claude Code, Copilot, Gemini, Codex, Cursor
Find vulnerabilities, misconfigurations, secrets, SBOM in containers, Kubernetes, code repositories, clouds and more
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models