juspay/neurolink

Universal AI Development Platform with MCP server integration, multi-provider support, and professional CLI. Build, test, and deploy AI applications with multiple ai providers.

64
/ 100
Established

Abstracts multi-provider LLM communication as composable token streams using a pipe-based architecture, unifying 13 AI providers (OpenAI, Anthropic, Google, AWS Bedrock, Azure, etc.) under a single TypeScript API. Built-in features include 64+ MCP server tools, Redis-backed persistent memory with LLM-powered condensation, context window auto-compaction with per-provider token estimation, RAG with hybrid search and reranking, and multi-provider failover for cost optimization. Deployable via professional CLI or as HTTP servers (Hono, Express, Fastify, Koa) with full observability hooks for existing OpenTelemetry instrumentation.

112 stars. Available on npm.

Maintenance 13 / 25
Adoption 9 / 25
Maturity 18 / 25
Community 24 / 25

How are scores calculated?

Stars

112

Forks

95

Language

TypeScript

License

MIT

Last pushed

Mar 11, 2026

Commits (30d)

0

Dependencies

64

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/juspay/neurolink"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.