GitHub · JavaScript
Nehanth/pooled
Peer-to-peer LLM inference in the browser: pool your devices to run big open models, for chat and coding agents.
- Stars
- 658
- Forks
- 98
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: browser, distributed-inference, inference, llm, local-llm, peer-to-peer, speculative-decoding, webgpu, webrtc, wgsl
Latest data point: Nov 21, 2026 · 658 stars · 98 forks