@juspay/neurolink 12.19.1 → 12.19.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +2 -2
- package/README.md +12 -12
- package/dist/browser/neurolink.min.js +213 -213
- package/dist/proxy/vertexAnthropicFallback.d.ts +0 -1
- package/dist/proxy/vertexAnthropicFallback.js +30 -0
- package/docs/changelog.md +14 -5
- package/docs-site/static/search-index.json +1 -1
- package/package.json +2 -2
package/CHANGELOG.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
|
1
|
-
## [12.19.
|
|
1
|
+
## [12.19.2](https://github.com/juspay/neurolink/compare/v12.19.1...v12.19.2) (2026-09-22)
|
|
2
2
|
|
|
3
3
|
### Bug Fixes
|
|
4
4
|
|
|
5
|
-
- **(proxy):**
|
|
5
|
+
- **(proxy):** convert the system turns Vertex refuses so the fallback survives ([a7fd9bf](https://github.com/juspay/neurolink/commit/a7fd9bf0410f81d3efee5e35d3457d74f750f409))
|
|
6
6
|
|
|
7
7
|
## [11.2.3](https://github.com/juspay/neurolink/compare/v11.2.2...v11.2.3) (2026-08-19)
|
|
8
8
|
|
package/README.md
CHANGED
|
@@ -39,17 +39,17 @@ const decision = await pipe.tryDecide({
|
|
|
39
39
|
// decision?.answers.autoApprove.probability -> 0.91
|
|
40
40
|
```
|
|
41
41
|
|
|
42
|
-
**[→ Docs](https://docs.neurolink.ink) · [→ Quick Start](https://docs.neurolink.ink/docs/getting-started/quick-start) · [→ npm](https://www.npmjs.com/package/@juspay/neurolink)**
|
|
42
|
+
**[→ Docs](https://docs.neurolink.ink) · [→ Quick Start](https://docs.neurolink.ink/docs/getting-started/quick-start) · [→ npm](https://www.npmjs.com/package/@juspay/neurolink) · [→ Blog](https://blog.neurolink.ink)**
|
|
43
43
|
|
|
44
44
|
---
|
|
45
45
|
|
|
46
46
|
## 🧠 What is NeuroLink?
|
|
47
47
|
|
|
48
|
-
**NeuroLink is the
|
|
48
|
+
**NeuroLink is the pipe layer of an AI nervous system.** Providers — OpenAI, Anthropic, Google, AWS, Azure, Mistral, local runtimes like Ollama, and dozens more — are the neurons: each generates a different kind of intelligence, at a different cost and latency. NeuroLink is the vascular layer that carries that intelligence, as a stream, to the applications — the organs — that consume it, across three inference types: `generate` and `stream` produce text, `decide` produces a calibrated `boolean`/`choice`/`score` judgment instead. A curated model registry (64 models, 132 aliases) backs metadata, routing, and context-window checks out of the box, and hundreds more models are reachable through aggregator providers — 100+ via LiteLLM, 300+ via OpenRouter.
|
|
49
49
|
|
|
50
|
-
Extracted from production systems at Juspay, NeuroLink provides a practical, TypeScript-first way to
|
|
50
|
+
Extracted from production systems at Juspay, NeuroLink provides a practical, TypeScript-first way to plug any application into that nervous system. Switch which neuron answers a request with a single parameter change — OpenAI, Anthropic, Google, AWS Bedrock, Azure, a local runtime, or any provider you add. `decide` is the third inference type — a typed, calibrated judgment instead of text — for the model-routing and gating decisions `generate`/`stream` were never meant to make, powered by a purpose-built decision model (TypeSafe Jev) rather than a general-purpose LLM: routing decisions land in ~400ms for about $0.00002, instead of a full generation call.
|
|
51
51
|
|
|
52
|
-
**Why NeuroLink?** Three genuine inference types, not one dressed up three ways — `generate` and `stream` produce text; `decide` produces a calibrated `boolean`/`choice`/`score` judgment, and which types a provider serves is declared per-provider via `inferenceKinds` rather than inferred from behavior.
|
|
52
|
+
**Why NeuroLink?** Three genuine inference types, not one dressed up three ways — `generate` and `stream` produce text; `decide` produces a calibrated `boolean`/`choice`/`score` judgment, and which types a provider serves is declared per-provider via `inferenceKinds` rather than inferred from behavior. Every neuron plugs into the same pipe, including 3 fully local runtimes (Ollama, LM Studio, llama.cpp) with per-request credential overrides, and MCP support covers all 4 transports (stdio, HTTP, SSE, WebSocket). Every AI-driven optimization the pipe performs — model routing, context compaction, tool selection — fails open: no key configured behaves exactly like NeuroLink without it, and routing uses asymmetric confidence thresholds (upgrade at 0.3, downgrade at 0.6) rather than a single cutoff, because a wrong downgrade costs more than a wrong upgrade. Switch providers with a single parameter change, leverage built-in tools plus any MCP-compliant tool server, deploy with confidence using enterprise features like Redis memory and multi-provider failover, and optimize costs automatically with intelligent routing. Use it via our professional CLI or TypeScript SDK—whichever fits your workflow.
|
|
53
53
|
|
|
54
54
|
**Where we're headed:** We're building for the future of AI—edge-first execution and continuous streaming architectures that make AI practically free and universally available. **[Read our vision →](docs/about/vision.md)**
|
|
55
55
|
|
|
@@ -410,7 +410,7 @@ npx @juspay/neurolink --help
|
|
|
410
410
|
|
|
411
411
|
### Configuration
|
|
412
412
|
|
|
413
|
-
NeuroLink works with
|
|
413
|
+
NeuroLink works with every major AI provider — and local runtimes that need no API key at all. You'll need at least one to get started:
|
|
414
414
|
|
|
415
415
|
**Option 1: Interactive Setup (Recommended)**
|
|
416
416
|
|
|
@@ -597,7 +597,7 @@ const result = await neurolink.generate({
|
|
|
597
597
|
### Next Steps
|
|
598
598
|
|
|
599
599
|
- **[Complete Documentation](https://docs.neurolink.ink)** - Comprehensive guides and API reference
|
|
600
|
-
- **[Provider Setup Guide](docs/getting-started/provider-setup.md)** - Configure
|
|
600
|
+
- **[Provider Setup Guide](docs/getting-started/provider-setup.md)** - Configure any provider
|
|
601
601
|
- **[SDK API Reference](docs/sdk/api-reference.md)** - Full TypeScript API documentation
|
|
602
602
|
- **[CLI Command Reference](docs/cli/commands.md)** - Complete CLI documentation
|
|
603
603
|
- **[Example Projects](docs/examples/index.md)** - Real-world integration examples
|
|
@@ -629,7 +629,7 @@ NeuroLink is a comprehensive AI development platform. Every feature below is shi
|
|
|
629
629
|
|
|
630
630
|
### 🤖 AI Provider Integration
|
|
631
631
|
|
|
632
|
-
**
|
|
632
|
+
**Every provider neuron behind one API** - Switch providers with a single parameter change. Nearly all serve `generate`/`stream`; TypeSafe Jev alone serves `decide`. Tool support: 29 native tool-calling, 3 model-dependent, 8 that serve no tools at all (embedding-, media- and decision-only). 3 are fully local runtimes (Ollama, LM Studio, llama.cpp) and 4 need zero configuration to start (those three plus LiteLLM) — no cloud account, no API key. 9 providers (OpenAI, Google AI Studio, Google Vertex, Amazon Bedrock, Cohere, Ollama, LiteLLM, Voyage, Jina) expose `embed()`/`embedMany()` natively for RAG and custom vector search.
|
|
633
633
|
|
|
634
634
|
| Provider | Models | Free Tier | Tool Support | Status | Documentation |
|
|
635
635
|
| --------------------- | -------------------------------------------------------------------------- | --------------- | ------------ | ------------- | ----------------------------------------------------------------------------------------------------------------------------- |
|
|
@@ -668,7 +668,7 @@ NeuroLink is a comprehensive AI development platform. Every feature below is shi
|
|
|
668
668
|
**Decision-only provider:** **TypeSafe Jev** (`TYPESAFE_API_KEY`) does not appear in the table above because it does not serve `generate`/`stream` — it is the first provider for the `decide` inference type. See [Decide: Calibrated Judgments, Not Text](#decide-calibrated-judgments-not-text).
|
|
669
669
|
|
|
670
670
|
**[📖 Provider Comparison Guide](docs/reference/provider-comparison.md)** - Detailed feature matrix and selection criteria
|
|
671
|
-
**[🔬 Provider Feature Compatibility](docs/reference/provider-feature-compatibility.md)** - Test-based compatibility reference for all 19 features across
|
|
671
|
+
**[🔬 Provider Feature Compatibility](docs/reference/provider-feature-compatibility.md)** - Test-based compatibility reference for all 19 features across every provider
|
|
672
672
|
|
|
673
673
|
---
|
|
674
674
|
|
|
@@ -854,7 +854,7 @@ neurolink generate "Describe what happens" --file ./demo.mp4
|
|
|
854
854
|
- **ProcessorRegistry** - Priority-based processor selection with fallback
|
|
855
855
|
- **OWASP Security** - HTML/SVG sanitization prevents XSS attacks
|
|
856
856
|
- **Auto-detection** - FileDetector identifies file types by extension and content
|
|
857
|
-
- **Provider-agnostic** - All processors work across
|
|
857
|
+
- **Provider-agnostic** - All processors work across every AI provider
|
|
858
858
|
|
|
859
859
|
**[📖 File Processors Guide](docs/features/file-processors.md)** - Complete reference for all file types
|
|
860
860
|
|
|
@@ -984,7 +984,7 @@ node your-app.js
|
|
|
984
984
|
|
|
985
985
|
### 🤖 GitHub Action
|
|
986
986
|
|
|
987
|
-
Run AI-powered workflows directly in GitHub Actions with
|
|
987
|
+
Run AI-powered workflows directly in GitHub Actions with support for every provider and automatic PR/issue commenting.
|
|
988
988
|
|
|
989
989
|
```yaml
|
|
990
990
|
- uses: juspay/neurolink@v1
|
|
@@ -996,7 +996,7 @@ Run AI-powered workflows directly in GitHub Actions with 40 provider support and
|
|
|
996
996
|
|
|
997
997
|
| Feature | Description |
|
|
998
998
|
| ---------------------- | ----------------------------------------------------------------------------------------- |
|
|
999
|
-
| **Multi-Provider** |
|
|
999
|
+
| **Multi-Provider** | Every provider behind one unified interface |
|
|
1000
1000
|
| **PR/Issue Comments** | Auto-post AI responses with intelligent updates |
|
|
1001
1001
|
| **Multimodal Support** | Attach images, PDFs, CSVs, Excel, Word, JSON, YAML, XML, HTML, SVG, code files to prompts |
|
|
1002
1002
|
| **Cost Tracking** | Built-in analytics and quality evaluation |
|
|
@@ -1189,7 +1189,7 @@ Full command and API breakdown lives in [`docs/cli/commands.md`](docs/cli/comman
|
|
|
1189
1189
|
|
|
1190
1190
|
| Capability | Highlights |
|
|
1191
1191
|
| ------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
1192
|
-
| **Provider unification** |
|
|
1192
|
+
| **Provider unification** | Every provider neuron behind one API, with automatic fallback, cost-aware routing, `providerFallback` policy, `modelChain` config. |
|
|
1193
1193
|
| **Decision inference** | Third inference type (`decide`) alongside generate/stream: calibrated `boolean`/`choice`/`score` judgments via TypeSafe Jev, ~400ms flat, ~$0.00002/decision. Used internally for model routing, context budgeting, relevance compaction and tool routing; per-query RAG planning is opt-in via `RAGPipeline`. |
|
|
1194
1194
|
| **Multimodal pipeline** | Stream images + CSV data + PDF documents across providers with local/remote assets. Auto-detection for mixed file types. |
|
|
1195
1195
|
| **Voice pipeline** | TTS (6 providers: Google, OpenAI, ElevenLabs, Azure, Fish Audio, Cartesia) + STT (4 providers) + realtime voice APIs (OpenAI Realtime, Gemini Live). |
|