Convenient OpenAI-compatible LLM provider for the log-parser framework. Implements ILLMProvider using the Vercel AI SDK.

Vercel AI SDK v4 provider for the sference managed-inference API (realtime OpenAI-compatible /v1/chat/completions).

Structured JSON output from 12 LLM providers with a single function call. Type-safe, retry-resilient, zero boilerplate.

Zero-config agentegrity adapter for the Vercel AI SDK (ai). TypeScript-native addition with no Python equivalent.

MindeesNative Synapse - provider-agnostic AI: a pure-TS contract with mock + server backends, streaming via async iterables, structured output, and tool calling (on-device runtime is a research track).

The first view of every schema your AI app runs on. Grades the coherence of your Zod schemas, flags the AI-bound ones, and shows where your vocabulary disagrees with itself. By Penumbra.

Vercel AI SDK provider adapter for @swoosh-dev/router.

Vercel AI SDK provider for Coder AI Gateway. Point the AI SDK at your Coder deployment with a Coder API token and use any model your deployment proxies — across AI Gateway's OpenAI- and Anthropic-compatible surfaces.

<a href="https://github.com/dbo/ai-model-usage-cost/actions"></a> <a href="https://www.npmjs.com/package/ai-model-usage-cost">![NPM Version](https://img.shields.io/npm/v/a

Lean & mean MCP-powered CLI agent — Nemotron, OpenAI, Anthropic, Perplexity

A lightweight utility that makes it easy to generate structured objects from LLMs using the Vercel AI SDK models and Zod schemas — with robust parsing powered by BAML under the hood.

Multi-framework AI agent SDK for the Zynd AI Network. Ed25519 identity, agent discovery, A2A protocol communication, agent cards, x402 micropayments, and one-shot deploy via zynd-deployer.

efferent SDK — Layer implementations of the sdk-core ports: multi-provider LLM router, auth, conversation/context stores (SQLite + Postgres), settings, fs/shell/http. Side effects live here.

Effect AI language model backed by the local Codex CLI

Drop-in telemetry wrapper for the Vercel AI SDK that streams traces to a mesh0 telemetry backend.

Vendor dependencies for plgg projects

TypeScript SDK for Koine gateway

Vercel AI SDK caching middleware for NodeLLMCache

Drop-in proof-carrying memory for the Vercel AI SDK — gate memory before generation and attach an Answer Receipt to every response.

Voight observability for the Vercel AI SDK. OpenTelemetry SpanExporter that ingests `experimental_telemetry` spans from `streamText`/`generateText`/etc. into your Voight dashboard — prompts, tokens, tool calls, cache, latency, errors, all providers normal