{"data":{"slug":"juspay-neurolink","name":"neurolink","tagline":"One TypeScript interface for 24+ LLM providers, supports voice, RAG, memory, file processors","github_url":"https://github.com/juspay/neurolink","owner":"juspay","repo":"neurolink","owner_avatar_url":"https://avatars.githubusercontent.com/u/11497632?v=4","primary_language":"TypeScript","stars":133,"forks":126,"topics":["agents","ai","ai-development","ai-platform","ai-sdk","anthropic","automation","developer-tools","enterprise","llm","local-first","mcp","model-context-protocol","neurolink","openai","rag","stt","tts","typescript","voice-ai"],"archived":false,"github_pushed_at":"2026-09-18T04:19:46+00:00","maintenance_label":"Very active","stars_delta_30d":16,"url":"https://www.graphcanon.com/tools/juspay-neurolink","markdown_url":"https://www.graphcanon.com/tools/juspay-neurolink.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/juspay-neurolink","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=juspay-neurolink","description":"One TypeScript interface for 24+ LLM providers — swap providers without rewriting. MCP-native (connect any MCP server), voice (TTS/STT/realtime), RAG, memory, file processors. Production-origin: powers Tara, Yama, and Clairvoyance at Juspay.","homepage_url":"https://neurolink.ink","license":"MIT","open_issues":85,"watchers":5,"ai_summary":"Neurolink provides a unified TypeScript interface for multiple LLM providers, enabling seamless switching between providers without code changes. It supports voice capabilities (TTS/STT), RAG, memory management, and file processing. It includes cost optimization features and is MCP-native, allowing connections to any MCP server.","readme_excerpt":"## 📚 Quick Start Guide\n\nThis guide will have you generating AI responses in under 5 minutes using either the SDK or CLI.\n\n---\n\n### Installation\n\nChoose your preferred package manager:\n\n```bash\n\n---\n\n# CLI only (no installation needed)\nnpx @juspay/neurolink --help\n```\n\n---\n\n### Cost Optimization Features\n\n- **💰 Automatic Cost Optimization**: Selects cheapest models for simple tasks\n- **🔄 LiteLLM Model Routing**: Access 100+ models with automatic load balancing\n- **🔍 Capability-Based Selection**: Find models with specific features (vision, function calling)\n- **⚡ Intelligent Fallback**: Seamless switching when providers fail\n\n```bash\n\n---\n\n# Cost optimization - automatically use cheapest model\nnpx @juspay/neurolink generate \"Hello\" --optimize-cost","github_created_at":"2025-05-31T15:05:42+00:00","created_at":"2026-07-11T23:17:23.871513+00:00","updated_at":"2026-09-20T04:30:59.946893+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"agents","name":"agents"},{"slug":"ai-development","name":"ai-development"},{"slug":"ai-platform","name":"ai-platform"},{"slug":"ai-sdk","name":"ai-sdk"},{"slug":"anthropic","name":"anthropic"},{"slug":"automation","name":"automation"},{"slug":"enterprise","name":"enterprise"},{"slug":"local-first","name":"local-first"}],"trust":{"provenance":{"is_fork":false,"github_id":993805781,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:27:55.212Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-09-18T04:21:21Z","stars_delta_30d":16,"open_issues_delta_30d":-48},"security_summary":{"status":"no_manifest","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:27:57.416Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"mcp":{"source":"package.json:@modelcontextprotocol/*","observed_at":"2026-09-18T08:27:54.091Z","server_manifest":true},"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:27:54.091Z"},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-09-18T08:27:54.091Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-09-18T08:27:54.091Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-18T08:27:54.091Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need a TypeScript interface that supports over 24 LLM providers and allows for seamless switching between providers without code changes.","If your project requires voice capabilities such as TTS and STT, RAG, memory management, and file processing.","When cost optimization is a priority, as Neurolink automatically selects the cheapest models for simple tasks and includes intelligent fallback mechanisms.","If your application needs to connect to any MCP server, as Neurolink is MCP-native."],"when_not_to_use":["If you are working in a language other than TypeScript, as Neurolink is specifically designed for TypeScript.","If your project does not require support for multiple LLM providers or the ability to switch between them without code changes.","When your project does not need voice capabilities, RAG, memory management, or file processing features.","If cost optimization and automatic model selection are not critical for your application."],"source":"enrich:decision_facts","observed_at":"2026-09-18T09:22:59.079Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Neurolink offers a unified TypeScript interface for over 24 LLM providers, supporting voice capabilities, RAG, memory management, and file processing. It includes cost optimization features and is MCP-native."}]}}