Keyword: inference

ai
Released
yesterday
Version
7.0.4
AI SDK by Vercel - build apps like ChatGPT, Claude, Gemini, and more with a single interface for any model using the Vercel AI Gateway or go direct to OpenAI, Anthropic, Google, or any other model provider.
ai vercel sdk llm mcp tool-calling +14
@qvac/sdk
Released
37m ago
Version
0.14.0
QVAC SDK is the canonical entry point to develop AI applications with QVAC.
ai bare cross-platform deep-learning diffusion edge-ai +14
@tryhamster/gerbil
Released
4d ago
Version
1.4.1
On-device LLM inference for the browser and Node.js — text, vision, speech (TTS/STT), and embeddings on a native WebGPU engine. Offline, private, no API keys. React hooks, MCP, and Vercel AI SDK included.
llm local gpu webgpu inference ai-sdk +8
try-flow-website-js
Released
4d ago
Version
0.321.0
An NPM package to hold compiled flow.js and libdefs for every Flow version.
flow facebook type inference check checker +3
turbollm
Released
5h ago
Version
1.6.0
TurboLLM — local LLM platform: run any inference engine auto-tuned to your GPU, with a web UI and OpenAI/Anthropic-compatible API. Point Claude Code at your own machine in one command.
llm local-llm llama.cpp llama-server inference gguf +7
costlayers
Released
yesterday
Version
0.8.17
CostLayers cost control for AI coding agents. Build compact repo context packs, gateway reports, and savings dashboards.
ai coding-agent cost-control developer-tools llm inference
@shadegpu/cli
Released
3d ago
Version
2.3.5
Encrypted GPU inference on untrusted infrastructure
gpu encryption inference security
@superlinked/sie-sdk
Released
2d ago
Version
0.6.14
Official TypeScript SDK for SIE (Search Inference Engine)
embeddings vector search inference reranking colbert +1
car-runtime
Released
3d ago
Version
0.31.0
Common Agent Runtime — a deterministic execution layer for AI agents
ai agent runtime llm inference napi
peerllm-host-cli
Released
yesterday
Version
2.1.9
Command-line PeerLLM host: serve decentralized AI compute from a headless machine.
peerllm llm host headless cli ai +4
@turnstileai/sdk
Released
6d ago
Version
0.1.21
Official TypeScript/JavaScript SDK for the TurnstileAI verifiable inference gateway.
ai inference gateway receipts verifiable openai +4
local-model-suitability-mcp
Released
7h ago
Version
1.1.28
AI model router for agents. Checks whether a local model can handle the task before calling cloud inference. LOCAL/CLOUD verdict saves cost on every call.
mcp local-model ollama model-routing cost-optimisation inference +5
@cabloy/zod
Released
3d ago
Version
4.3.8
TypeScript-first schema declaration and validation library with static type inference
typescript schema validation type inference
@runware/sdk
Released
6d ago
Version
1.3.4
Runware SDK — unified API for image, video, audio, text, and 3D generation. Schema-driven types, WebSocket and REST transports, LLM streaming.
runware ai sdk image-generation video-generation audio-generation +5
ludion-router
Released
5d ago
Version
0.3.1
A load balancer between your users' GPUs and your cloud — per-request routing of AI inference between on-device WebGPU and your own server, decided by a versioned, deterministic, empirically derived policy.
webgpu webllm inference router edge-ai on-device
@lloyal-labs/lloyal-agents
Released
1 week ago
Version
3.1.0
Multi-agent inference inside the decode loop — structured concurrency over shared KV state
llm agents multi-agent inference structured-concurrency effection +1
@polargrid/polargrid-sdk
Released
5d ago
Version
0.9.3
JavaScript/TypeScript SDK for PolarGrid Edge AI Infrastructure with Full API Support
ai ml edge inference polargrid machine-learning +6
@mcmcjs/julia
Released
3d ago
Version
0.7.1
Julia toolchain detection and the inference runner for MCMC.js.
mcmc julia juliaup turing inference runner
@mcmcjs/core
Released
6d ago
Version
0.5.0
Core data model and samples-file parsers for MCMC.js.
mcmc bayesian inference arviz mcmcchains samples +1
@mcmcjs/engine
Released
1 week ago
Version
0.4.0
Runtime and PPL engine contract and registry for MCMC.js.
mcmc engine runtime ppl registry inference
@net-mesh/sdk
Released
2d ago
Version
0.29.0
Ergonomic TypeScript SDK for the Net mesh network
net mesh event-bus streaming ai llm +2
@wzrd_sol/goat-plugin
Released
4d ago
Version
0.4.0
WZRD Liquid Attention Protocol plugin for GOAT SDK — free trust preflight, paid ERC-8004 reputation credentials, server-witnessed inference, CCM rewards
goat goat-sdk ai agents solana wzrd +9
@ultralytics/yolo
Released
1 week ago
Version
0.0.23
Run Ultralytics YOLO models in the browser on WebGPU (WebAssembly, ONNX Runtime Web via ort-web).
yolo ultralytics inference webgpu wasm onnx +2
flexinference
Released
17h ago
Version
1.0.1
Official TypeScript SDK for FlexInference - a deadline-aware, OpenAI-compatible inference router.
flexinference openai llm inference ai gpt +2
@lloyal-labs/sdk
Released
2 weeks ago
Version
3.0.2
Backend-agnostic TypeScript SDK for the lloyal inference platform
llm inference branch kv-cache tree-search llama.cpp