- Chicago, IL
- http://theexceptioncatcher.com
Starred repositories
A quick and convenient way to emulate Flock Safety OUI's from an ESP32 to test other hardware for Flock Safety detections capabilities.
ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.
Skills for Real Engineers. Straight from my .agents directory.
Self-hosted AI SRE for Kubernetes — zero-instrumentation eBPF observability plus a copilot that fixes issues through guardrailed, self-verifying actions. BYO-LLM, air-gapped capable.
Software-only version of the USBridge ecosystem for secure, low-latency remote desktop control and peer-to-peer networking.
Breathe fresh life into your bricked Nest, now with 100% less evil!
ianchanning / ilya-sutskever-recommended-reading
Forked from dzyim/ilya-sutskever-recommended-readingIt is said that, Ilya Sutskever gave John Carmack this reading list of ~ 30 research papers on deep learning.
Invite others to grab times on your calendar. Choose a date. Make appointments as easy as it gets.
LLM inference decode throughput benchmark with Rich TUI dashboard. Measures token generation speed across concurrency levels and context lengths. Supports SGLang and vLLM engines.
NVIDIA Linux open GPU with P2P support
RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink
About Awesome things towards foundation agents. Papers / Repos / Blogs / ...
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
A bare-bones GUI application for the local inference engine, llama.cpp. Built-in TPE optimiser to find the best flags for your system
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static bin…
The agent that grows with you
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini C…
The HIP Environment and ROCm Kit - A lightweight open source build system for HIP and ROCm
Orchestration-builder SDK for multi-agent coding workflows
🧑🎨 A collection of Golang agentic skills that works
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…
The best-benchmarked open-source AI memory system. And it's free.