A high-performance in-browser LLM inference engine. WebLLM runs language models directly in a browser tab on WebGPU with no server round trip, which makes it possible to ship model-backed features that never send user input anywhere.
Be the first to rate WebLLM. Your feedback helps other users decide.
Run a chat model entirely in the tab with no API key and no server.
Process text locally so it never leaves the device.
Keep a model cached so the feature still works without a network.
Similar tools in the same category — compare side-by-side
Fine-tune LLMs from one YAML file. Soup uses layer streaming so an 8B model can be trained on a 4 GB...
A local AI-powered red teamer that runs on a phone. Nightcrawler brings an agent-driven security tes...
Zero-cost epistemic uncertainty quantification and hallucination detection for LLMs. Spanda estimate...
Guides and comparisons about code tools
Eleven recent open-source projects for running inference, transcription, deep research and security work entirely on hardware you control.
Nine Show HN launches beneath the model: filesystems, snapshots, gateways and deploy tools that decide what an agent sees and what survives.
Nine launches that check agent work: per-call access policy, MCP server vetting, runtime verification, readable diffs and a hard stop at 95%.
Nine Show HN launches sitting under the agent: a model gateway, vectorless retrieval, on-device inference, an MCP browser layer and connectors for real systems.
Eight Show HN projects for trusting long agent runs: work context capture, distilled memory, folder fences, dollar budgets, plan review and tool governance.
