I built a concurrent BitTorrent engine in Go to master P2P protocols
BitTorrent engine tackles real distributed systems problems—slow peers, data poisoning, pipelining.

BitTorrent for LLMs with on-device PII scanning before prompts leave your machine.
Developers, privacy advocates, and GPU owners looking for free inference
Petals · Gensyn · Together AI
BitTorrent engine tackles real distributed systems problems—slow peers, data poisoning, pipelining.
Browser-based GPU cluster for LLM inference with HTTP API and SSE broker coordination.
BitTorrent-style distributed inference for biology LLMs across consumer GPUs.
Hands-on distributed ML simulator—gamified learning for tensor parallelism without spinning up clusters.
SETI@home for LLMs where agents coordinate hyperparameter searches across volunteer GPUs.
RDMA-backed distributed KV cache cuts prefill latency 3.1× where vLLM's built-in caching maxes out.