eBPF agent and MCP server for GPU causal observability
Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically..
Optimized vLLM deployment for NVIDIA Blackwell (RTX 5090) on Linux Kernel 6.14. Resolves SM_120 kernel incompatibilities, P2P deadlocks, and memory fragmentation for high-performance LLM inference.
Performance analysis tools based on Linux perf_events (aka perf) and ftrace
#1 Persistent memory for AI coding agents based on real-world benchmarks
A Datacenter Scale Distributed Inference Serving Framework
⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
1 capture since 2026-06-05
go.mod
· go · 42 dependencies
go.sum
· go · 78 dependencies
python/ingero-annotate/pyproject.toml
· python · 1 dependencies
tests/workloads/requirements.txt
· python · 6 dependencies
examples/integrations/accelerate/requirements.txt
· python · 3 dependencies
examples/integrations/deepspeed/requirements.txt
· python · 3 dependencies
examples/integrations/hf-trainer/requirements.txt
· python · 3 dependencies
examples/integrations/pytorch-lightning/requirements.txt
· python · 3 dependencies
examples/integrations/ray/requirements.txt
· python · 2 dependencies