🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
- bloom
- deep-learning
- distributed-systems
- language-models
47,133 repositories indexed
1–3 of 3 · Most stars
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.