Find your path through the pipe.

NeuroLink is an enterprise AI development platform that provides unified access to AI providers (OpenAI, Anthropic, Google AI, AWS Bedrock, Azure, DeepSeek, NVIDIA NIM, LM Studio, llama.cpp, plus voice providers like ElevenLabs, Deepgram, and more) through a single TypeScript SDK and professional CLI — most of them for generate()/stream(), plus TypeSafe, Laya, XOR, Perplexity Decisions and Cloudflare Clef for calibrated decide() judgements. It is extracted from production systems at Juspay and battle-tested at enterprise scale.

NeuroLink focuses on provider unification with zero lock-in. Unlike LangChain, it uses a lightweight factory architecture without heavy abstractions. Compared to Vercel AI SDK, NeuroLink adds built-in MCP integration with 58+ tool servers, RAG pipelines, workflow orchestration, multimodal support for 50+ file types, and a full-featured CLI.

Yes. NeuroLink is open source and free to use under the MIT license. You only pay for the AI provider API calls you make (e.g., OpenAI, Anthropic). NeuroLink itself adds no additional cost.

Most NeuroLink providers serve generate()/stream(): OpenAI, Anthropic, Google AI Studio, Google Vertex AI, AWS Bedrock, Azure OpenAI, Mistral, Ollama, LiteLLM, HuggingFace, SageMaker, OpenRouter, DeepSeek, NVIDIA NIM (400+ catalog models), LM Studio (local), llama.cpp (local GGUF), any OpenAI-compatible endpoint, and voice providers — OpenAI TTS, ElevenLabs, Google TTS, Azure TTS, Whisper, Deepgram, Azure STT, Google STT. Some serve decide() only — calibrated typed judgements, no text: TypeSafe; Laya, a self-hosted open-weights model (LAYA_API_KEY + LAYA_BASE_URL); XOR, Juspay's open-weights model (XOR_API_KEY + XOR_BASE_URL); Perplexity Decisions, a hosted API that also reads images (PERPLEXITY_API_KEY, the same key as Perplexity's text provider); and Cloudflare Clef, hosted on Workers AI, which also reads images (CLOUDFLARE_API_KEY + CLOUDFLARE_ACCOUNT_ID, the same two as Cloudflare's text provider). Switching generate/stream providers requires changing a single parameter.

Yes. NeuroLink has full MCP integration with 58+ external tool servers including GitHub, PostgreSQL, Google Drive, Slack, and more. It supports all four transport protocols: stdio for local servers, HTTP/Streamable HTTP for remote servers, SSE, and WebSocket.

Absolutely. NeuroLink is extracted from production systems and includes enterprise features like Redis-backed conversation memory, provider failover, observability with 9 exporters and Langfuse integration, context compaction, and workflow orchestration with checkpointing.

decide() is a third inference type alongside generate() and stream() — a separate modality, not a mode of the other two, so a text-only provider is never reachable from it and a decide-only provider is never reachable from generation fallback. A decision model takes one state plus a set of named, typed questions and returns one typed, calibrated answer per question in a single parallel pass — no text, nothing to parse out of prose. Because the confidence is calibrated rather than self-reported, it can gate action directly: NeuroLink's classifier router uses asymmetric thresholds (0.3 confidence to route a request up to a pricier model, 0.6 to route it down) since routing too cheap and routing too expensive don't cost the same. Six consumers build on it today — model routing, a registry-derived model catalogue (64 models across 7 providers, 132 aliases, added on top of a host's own declared pool rather than replacing it), context budget sizing, compaction quality gating, calibrated MCP/tool-server routing, and RAG retrieval planning — and every one fails open: with no decision provider configured, behavior is byte-for-byte what it was before. Decisions get their own model.decision observability span with independent cost attribution, kept separate from generation metrics, across all 9 supported exporters. TypeSafe's Jev, Laya — an open-weights model you can run yourself — XOR — Juspay's open-weights decision model — Perplexity's hosted Decisions API and Cloudflare's hosted Clef models are the decision providers; enabling TypeSafe or Perplexity is one environment variable (Perplexity's, PERPLEXITY_API_KEY, is shared with its text provider), Cloudflare Clef needs two (CLOUDFLARE_API_KEY and CLOUDFLARE_ACCOUNT_ID, shared with Cloudflare's text provider), and Laya or XOR each also need a base URL.