npm - iaurora - Versions diffs - 1.0.16 → 1.0.18 - Mend

iaurora 1.0.16 → 1.0.18

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.

Files changed (3) hide show

package/README.md CHANGED Viewed

@@ -1,8 +1,8 @@
 <div align="center">
-<img alt="Aurora OSS" src="dashboard-ui/public/aurora-oss-logo.svg" width="72">
+<img alt="Aurora OSS" src="https://raw.githubusercontent.com/gurveeer/Aurora/main/dashboard-ui/public/aurora-oss-logo.svg" width="72">
-# Aurora OSS
+# Aurora Gateway
 **One gateway. Every provider. Open source.**
@@ -13,7 +13,7 @@ Self-hosted. No vendor lock-in. Full source visibility.
 <tr>
   <td><a href="https://github.com/gurveeer/Aurora/actions/workflows/test.yml"><img src="https://github.com/gurveeer/Aurora/actions/workflows/test.yml/badge.svg" alt="CI"></a></td>
   <td><a href="https://github.com/gurveeer/Aurora/blob/main/go.mod"><img src="https://img.shields.io/github/go-mod/go-version/gurveeer/Aurora?style=flat-square&label=Go" alt="Go Version"></a></td>
-  <td><a href="https://github.com/gurveeer/Aurora/releases"><img src="https://img.shields.io/github/v/release/gurveeer/Aurora?style=flat-square" alt="Release"></a></td>
+  <td><a href="https://www.npmjs.com/package/iaurora"><img src="https://img.shields.io/npm/v/iaurora?style=flat-square&label=npm" alt="npm"></a></td>
   <td><a href="https://github.com/gurveeer/Aurora/stargazers"><img src="https://img.shields.io/github/stars/gurveeer/Aurora?style=flat-square" alt="Stars"></a></td>
 </tr>
 <tr>
@@ -30,223 +30,293 @@ Self-hosted. No vendor lock-in. Full source visibility.
 </tr>
 </table>
-<a href="docs/assets/dashboard-overview.png">
-  <img src="docs/assets/dashboard-overview.png" alt="Aurora dashboard" width="100%">
+<a href="https://github.com/gurveeer/Aurora/blob/main/docs/assets/dashboard-overview.png">
+  <img src="https://raw.githubusercontent.com/gurveeer/Aurora/main/docs/assets/dashboard-overview.png" alt="Aurora dashboard" width="100%">
 </a>
 </div>
 ---
-## Start your selfhosted gateway
+## CLI reference
-**Docker**
-```bash
-docker run --rm -p 8080:8080 \
-  -e OPENAI_API_KEY="sk-..." \
-  gurveeer/Aurora
 ```
+aurora [flags]
+aurora init [flags]
+aurora update
+aurora uninstall
+aurora models <command> [flags]
+```
+| Command | Description |
+|---------|-------------|
+| `aurora` | Start the gateway server |
+| `aurora init` | Bootstrap config.yaml, .env, and data/ directory |
+| `aurora update` | Self-update to the latest npm version |
+| `aurora uninstall` | Remove aurora from your system |
+| `aurora models sync` | Download upstream model registry to local file |
+| `aurora models diff` | Show pricing diff between upstream and local snapshot |
+| `aurora models show` | Print effective pricing for a model |
+| Flag | Description |
+|------|-------------|
+| `-version` | Print version information |
+| `-help` | Show full configuration reference and env vars |
+| `-help-json` | Dump environment variable schema as JSON |
+| `aurora init` flag | Description |
+|-------------------|-------------|
+| `-dir <path>` | Target directory (default: current directory) |
+| `-force` | Overwrite existing files |
+| `-with-models` | Also download the model registry |
+---
+## Quick start
-**npm (global CLI)**
+### npm (recommended)
 ```bash
+# Install globally
 npm install -g iaurora
-# Now run `aurora` anywhere:
-aurora --help
+# Scaffold a new project
+mkdir my-gateway && cd my-gateway
+aurora init
+# Edit .env with your API key(s)
+# Uncomment one of the provider keys:
+#   GROQ_API_KEY=gsk_...
+#   OPENAI_API_KEY=sk-...
+#   etc.
+# Start the gateway
+aurora
 ```
-Requires Go 1.26.2+ to be installed on the machine; the `aurora` binary is downloaded on first use.
+The gateway boots on `http://localhost:8080` with every free feature enabled.
+Open the dashboard at `http://localhost:8080/admin/dashboard`.
-**From source**
+### Docker
 ```bash
-git clone https://github.com/gurveeer/Aurora.git && cd Aurora
-pnpm --dir dashboard-ui install && pnpm --dir dashboard-ui run build
-go build -o bin/aurora-oss.exe ./apps/aurora
+docker run --rm -p 8080:8080 \
+  -e AURORA_MASTER_KEY="your-secure-key" \
+  -e GROQ_API_KEY="gsk_..." \
+  gurveeer/Aurora
 ```
-Then send your first request:
+For configurable deployments, mount your `config.yaml` and `.env`:
 ```bash
-curl http://localhost:8080/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -d '{"model":"gpt-5-chat-latest","messages":[{"role":"user","content":"Hello!"}]}'
+docker run --rm -p 8080:8080 \
+  -v /path/to/config.yaml:/app/config.yaml \
+  -v /path/to/.env:/app/.env \
+  -e AURORA_CONFIG_PATH=/app/config.yaml \
+  gurveeer/Aurora
 ```
-| | |
-|---|---|
-| Dashboard | `http://localhost:8080/admin/dashboard` |
-| Health check | `http://localhost:8080/health` |
-| Swagger | `http://localhost:8080/swagger/index.html` |
+### From source
----
+```bash
+git clone https://github.com/gurveeer/Aurora.git && cd Aurora
-## What it does
+# Build the dashboard UI (one-time)
+pnpm --dir dashboard-ui install && pnpm --dir dashboard-ui run build
-Aurora sits between your application and AI providers. One API key, one endpoint, every model.
+# Build the binary
+go build -o bin/aurora ./apps/aurora
-<p align="center">
-  <a href="docs/assets/analytics-overview.png">
-    <img src="docs/assets/analytics-overview.png" alt="Usage analytics" width="48%">
-  </a>
-  <a href="docs/assets/audit-logs.png">
-    <img src="docs/assets/audit-logs.png" alt="Audit logs" width="48%">
-  </a>
-</p>
+# Use the CLI's init command
+./bin/aurora init -dir ./my-gateway
+cd ./my-gateway
-**Unified API** -- `/v1/chat/completions`, `/v1/responses`, `/v1/embeddings`, `/v1/models`, `/v1/files`, `/v1/batches`
+# Edit .env with keys, then start
+../bin/aurora
+```
+---
-**12 providers** -- OpenAI, Anthropic, Gemini, DeepSeek, Groq, OpenRouter, Z.ai, xAI, Azure OpenAI, Oracle, Ollama, vLLM (and any OpenAI-compatible backend)
+## What `aurora init` generates
-**Routing** -- Model aliases, provider pools, fallback chains, workflow pipelines, passthrough routes
+```
+my-gateway/
+├── config.yaml              # Full config (all OSS features ON)
+├── .env                     # Every env var documented
+├── configs/
+│   └── fallback.json        # Fallback routing rules (example)
+└── data/
+    └── user_pricing.yaml    # Model pricing overrides
+```
-**Dashboard** -- Live usage analytics, provider status, cache hit rates, cost tracking, audit logs
+**All 15 config sections are active** — nothing needs to be uncommented for the gateway to work. The generated files serve as living documentation: every option is listed with a description and its default value. Commented-out blocks show advanced features that need external infrastructure (Redis, PostgreSQL, vector stores).
+### Feature overview
+| Feature | What it does | How to use |
+|---------|-------------|------------|
+| **HTTP Gateway** | OpenAI-compatible `/v1/chat/completions`, `/v1/embeddings`, `/v1/models`, etc. | Send any OpenAI SDK/client at it |
+| **Admin Dashboard** | Web UI for managing providers, API keys, models, combos | `http://localhost:8080/admin/dashboard` |
+| **Model Discovery** | Detects providers and their models from env vars automatically | Just set `GROQ_API_KEY` — models appear in `/v1/models` |
+| **Passthrough Routes** | Call provider APIs directly through the gateway | `POST /p/groq/v1/chat/completions` |
+| **Anthropic Ingress** | Native Anthropic-format `/v1/messages` endpoint | Send Anthropic SDK traffic directly |
+| **Audit Logging** | Records every request/response with retention | View in dashboard → Audit Logs |
+| **Usage Tracking** | Token counts, cost per request, historical analytics | View in dashboard → Usage |
+| **Prometheus Metrics** | Go runtime + request metrics | `GET /metrics` |
+| **Guardrails** | Content safety filters (system prompt, regex, PII redaction) | Configure in dashboard or `guardrails` in YAML |
+| **Token Saver** | Compresses responses to cut token spend | Set `TOKEN_SAVER_ENABLED=true` (already on by default) |
+| **Swagger UI** | Interactive API docs | `http://localhost:8080/swagger/index.html` |
+| **pprof** | Go performance profiling | `http://localhost:8080/debug/pprof/` |
+| **Fallback Routing** | Auto-failover when a provider returns an error | Configured in `fallback.json` |
+| **Resilience** | Retries transient failures + circuit breaker | On by default (3 retries, 30s backoff) |
+| **Combo Models** | Send one prompt to multiple models, get all responses | Create via dashboard or API |
+| **CLI Tools** | Admin configuration via CLI commands | Enable `apply_enabled` for write access |
+| **SQLite Storage** | Zero-config embedded database for all persistence | Default — no setup needed |
+### Your first request
-**Controls** -- Managed API keys, model overrides, guardrails, pricing recalculation, exact + semantic response caching
+```bash
+curl http://localhost:8080/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $(grep AURORA_MASTER_KEY .env | cut -d= -f2)" \
+  -d '{
+    "model": "groq/llama-3.3-70b-versatile",
+    "messages": [{"role": "user", "content": "Hello!"}]
+  }'
+```
-**Storage** -- SQLite (default), PostgreSQL, MongoDB
+Or using the admin dashboard at `http://localhost:8080/admin/dashboard` to test models interactively.
 ---
-## Publish readiness and boundaries
-This repository is intended to be published as the **Aurora OSS source tree**. It should contain source code, tests, examples, generated OpenAPI/docs assets, and public documentation only.
+## Providers
-**Current review status:** source publish is acceptable after the checks below pass locally. Do not publish any local runtime files, compiled binaries, package tarballs, databases, logs, or machine-specific configuration.
+Providers are **auto-discovered from environment variables**. Set any of these keys in your `.env` and restart — the provider and its models appear automatically.
-### Repository boundary
+| Provider | Env var | Default models |
+|----------|---------|----------------|
+| OpenAI | `OPENAI_API_KEY` | `gpt-4o`, `gpt-4o-mini` |
+| Anthropic | `ANTHROPIC_API_KEY` | `claude-sonnet-4`, `claude-opus-4` |
+| Google Gemini | `GEMINI_API_KEY` | `gemini-2.5-pro`, `gemini-2.5-flash` |
+| Groq | `GROQ_API_KEY` | `llama-3.3-70b`, `qwen3-32b`, `whisper` |
+| DeepSeek | `DEEPSEEK_API_KEY` | `deepseek-chat`, `deepseek-reasoner` |
+| OpenRouter | `OPENROUTER_API_KEY` | 300+ models |
+| xAI | `XAI_API_KEY` | `grok-3`, `grok-3-mini` |
+| Z.ai | `ZAI_API_KEY` | `glm-4.5` |
+| MiniMax | `MINIMAX_API_KEY` | `minimax-m1` |
+| Azure OpenAI | `AZURE_API_KEY` + `AZURE_BASE_URL` | Your deployments |
+| Oracle | `ORACLE_API_KEY` + `ORACLE_BASE_URL` | `cohere.command-r-plus` |
+| Ollama | `OLLAMA_BASE_URL` | Any local model |
+| vLLM | `VLLM_BASE_URL` | Any served model |
-Included in the OSS boundary:
+**Custom base URL?** Set `OPENAI_BASE_URL`, `GROQ_BASE_URL`, etc. in `.env`.
-- Gateway source under `apps/`, `internal/`, `configuration/`, and supporting packages.
-- Dashboard source under `dashboard-ui/` and minimal embedded dashboard placeholders needed by Go builds.
-- Public config examples under `configs/`, `configuration/`, `helm/`, `.env.template`, and docs.
-- Tests under `test/` and public fixtures with dummy credentials only.
-- CI, release, Docker, Helm, and packaging scripts.
+**Multiple instances of the same provider?** Use suffix notation: `OPENAI_EAST_API_KEY`, `OPENAI_EAST_BASE_URL`, `OPENAI_WEST_API_KEY`, etc.
-Excluded from the OSS boundary:
+---
-- Local environment files: `.env`, `.env.*`, `.aurora.local/`.
-- Runtime data: `data/`, logs, caches, SQLite files, benchmark output, and temporary files.
-- Build/package output: `bin/`, `dist/`, `release/`, `npm/`, `*.exe`, `*.tgz`, archives.
-- User/editor/agent config that may contain private paths or endpoints: `.vscode/`, `.idea/`, `opencode.json`, `.claude/settings.local.json`.
-- Any provider API key, database URL, Redis URL, vector DB token, private certificate/key, or managed API key.
+## Using the admin dashboard
-### Leakage review summary
+Open `http://localhost:8080/admin/dashboard` to:
-The publish tree was checked for common leakage classes:
+- **Manage API keys** — Create and revoke gateway-level API keys with usage limits
+- **Toggle models** — Enable/disable specific models per provider
+- **Override pricing** — Set custom input/output token costs per model
+- **View analytics** — Request volume, token usage, latency, error rates
+- **Browse audit logs** — Every request, who made it, what model, how many tokens
+- **Configure guardrails** — Add content safety rules
+- **Create combos** — Multi-model comparison and fallback groups
+- **Monitor cache** — Hit rates for exact and semantic caches
-- Hardcoded provider keys and service tokens.
-- Live Redis/PostgreSQL/Qdrant connection strings.
-- Private certificates and key material.
-- Local absolute paths and machine-specific `.aurora.local` files.
-- Generated binaries and package archives.
+---
-Local secret-bearing files and generated binaries/package artifacts were removed from the publish tree. Remaining credential-like strings found by the review are dummy examples in docs/tests, such as `sk-test-key-12345`, `postgres://user:pass@localhost/...`, or placeholders in `.env.template`.
+## Combo models
-### Security posture
+Combos let you send one prompt to multiple models simultaneously. The primary model responds; if it fails, fallback models are tried automatically.
-- Keep `AURORA_MASTER_KEY` unset only for isolated local testing. Set a high-entropy value before exposing the gateway outside localhost.
-- Keep `LOGGING_LOG_BODIES=false` and `LOGGING_LOG_HEADERS=false` unless you explicitly need request debugging and understand the privacy impact.
-- Use `.env.template` as documentation only. Put real values in untracked `.env` files, deployment secrets, or your hosting provider's secret manager.
-- Rotate any credential that was ever present in a local `.env`, `.aurora.local`, package artifact, shell history, or shared archive before public release.
-- Audit logs hash API keys for identification and redact sensitive headers in reader paths, but request/response body logging can still capture sensitive prompts if enabled.
+### Create via dashboard
-### Pre-publish checklist
+1. Open `http://localhost:8080/admin/dashboard`
+2. Go to **Combos** → **Add Combo**
+3. Name it, select 2+ models, save
-Run these from the repository root before creating a fresh GitHub repository:
+### Create via API
 ```bash
-# Verify no local runtime secrets or build artifacts are present
-find . -maxdepth 3 \( -name .env -o -name '.env.*' -o -name '.aurora.local' -o -name '*.exe' -o -name '*.tgz' -o -name '*.pem' -o -name '*.db' \) -print
+curl -X POST http://localhost:8080/admin/api/v1/combos \
+  -H "Authorization: Bearer $AURORA_MASTER_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{"name":"my-combo","models":["groq/llama-3.3-70b-versatile","groq/qwen/qwen3-32b"],"enabled":true}'
+```
-# Search for common secret patterns. Review every match manually.
-rg -n --hidden -g '!node_modules' -g '!dashboard-ui/node_modules' -g '!*.png' -g '!*.jpg' -g '!*.lock' \
-  '(rediss://|postgres://[^[:space:]"'"'']+:[^[:space:]"'"'']+@|BEGIN (RSA |EC |OPENSSH |)PRIVATE KEY|[A-Z0-9_]*API_KEY\s*=\s*(sk-|gsk_|jina_|eyJ|[A-Za-z0-9_-]{20,}))'
+### Use a combo
-# Build and test source
-pnpm --dir dashboard-ui install
-pnpm --dir dashboard-ui run build
-go test ./apps/... ./internal/...
+```bash
+curl http://localhost:8080/v1/chat/completions \
+  -H "Authorization: Bearer $AURORA_MASTER_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{"model":"my-combo","messages":[{"role":"user","content":"Hello!"}]}'
 ```
-Expected result for the first command is no output, except intentionally kept public templates. Expected result for the secret search is only placeholders, dummy test keys, or documentation examples.
+---
-### If a secret was exposed
+## Configuration
-If a real key was committed locally, copied into a package artifact, or shared outside your machine, deleting the file is not enough. Revoke and rotate the credential at the provider, purge generated artifacts, and create the public GitHub repository from a clean tree with no inherited history.
+The gateway loads settings in this order (later wins):
----
+```
+code defaults → config.yaml → .env / env vars
+```
-## Providers
+### config.yaml
-| Provider | Key | Chat | Embeddings | Files | Batches | Passthrough |
-|---|---|:---:|:---:|:---:|:---:|:---:|
-| OpenAI | `OPENAI_API_KEY` | ✅ | ✅ | ✅ | ✅ | ✅ |
-| Anthropic | `ANTHROPIC_API_KEY` | ✅ | | | ✅ | ✅ |
-| Google Gemini | `GEMINI_API_KEY` | ✅ | ✅ | ✅ | ✅ | |
-| DeepSeek | `DEEPSEEK_API_KEY` | ✅ | | | | |
-| Groq | `GROQ_API_KEY` | ✅ | ✅ | ✅ | ✅ | |
-| OpenRouter | `OPENROUTER_API_KEY` | ✅ | ✅ | ✅ | ✅ | ✅ |
-| Z.ai | `ZAI_API_KEY` | ✅ | ✅ | | | ✅ |
-| xAI | `XAI_API_KEY` | ✅ | ✅ | ✅ | ✅ | |
-| Azure OpenAI | `AZURE_API_KEY` + `AZURE_BASE_URL` | ✅ | ✅ | ✅ | ✅ | ✅ |
-| Oracle | `ORACLE_API_KEY` + `ORACLE_BASE_URL` | ✅ | | | | |
-| Ollama | `OLLAMA_BASE_URL` | ✅ | ✅ | | | |
-| vLLM | `VLLM_BASE_URL` | ✅ | ✅ | | | ✅ |
-> **Z.ai GLM Coding Plan:** set `ZAI_BASE_URL=https://api.z.ai/api/coding/paas/v4`
->
-> **Multiple instances of one provider?** Use suffixed env vars: `OPENAI_EAST_API_KEY`, `OPENAI_EAST_BASE_URL`, `OPENAI_EAST_MODELS`
+Generated by `aurora init`. Every section is documented inline:
----
+| Section | What it controls |
+|---------|-----------------|
+| `server` | Port, base path, master key, passthrough, Anthropic ingress |
+| `admin` | Dashboard API and UI |
+| `models` | Discovery, overrides, allowlisting |
+| `storage` | SQLite (default), PostgreSQL, or MongoDB |
+| `logging` | Audit logging of requests/responses |
+| `usage` | Token tracking, pricing, retention |
+| `metrics` | Prometheus endpoint |
+| `guardrails` | Content safety filters |
+| `cache` | Model cache, response cache (exact + semantic) |
+| `combos` | Multi-model combo definitions |
+| `cli_tools` | Admin CLI integration |
+| `token_saver` | Output compression |
+| `fallback` | Provider failover rules |
+| `resilience` | Retry + circuit breaker |
+| `workflows` | Workflow refresh cadence |
-## Configuration
+### .env
-Aurora loads config in order: **defaults → YAML → env vars** (env vars win).
+Every environment variable is listed with its purpose and default value. Free features are uncommented (set to their default or `true`). Features needing external infrastructure (Redis, PostgreSQL, vector stores) are commented out with instructions.
-```bash
-# Copy the env template for secrets/runtime values
-cp .env.template .env
+### Using a different config profile
-# Pick a config profile. Env vars in .env override YAML values.
-export AURORA_CONFIG_PATH=configs/editions/oss.example.yaml
+```bash
+export AURORA_CONFIG_PATH=configs/editions/oss.team.example.yaml
+aurora
 ```
 | Profile | Best for | External services |
-|---|---|---|
-| [`oss.example.yaml`](configs/editions/oss.example.yaml) | First run, individual devs | None |
-| [`oss.local-power.example.yaml`](configs/editions/oss.local-power.example.yaml) | Local power users with audit, usage, metrics, exact cache, guardrail examples, token saver examples | Redis |
-| [`oss.team.example.yaml`](configs/editions/oss.team.example.yaml) | Full OSS team profile with Postgres storage, Redis model/exact cache, semantic cache, provider examples, pools, fallback, resilience | PostgreSQL, Redis, Qdrant or another vector store |
-**Key settings:**
-| Setting | Default | What it does |
-|---|---|---|
-| `PORT` | `8080` | Listen port |
-| `AURORA_MASTER_KEY` | -- | Gateway/admin API key (set before exposing outside localhost) |
-| `STORAGE_TYPE` | `sqlite` | `sqlite`, `postgresql`, or `mongodb` |
-| `LOGGING_ENABLED` | `false` | Audit logging |
-| `METRICS_ENABLED` | `false` | Prometheus metrics |
-| `GUARDRAILS_ENABLED` | `false` | Guardrail workflows |
-| `ENABLE_PASSTHROUGH_ROUTES` | `true` | `/p/{provider}/...` passthrough |
-| `TOKEN_SAVER_ENABLED` | `false` | Optional concise-output/token-saving transforms |
-| `RESPONSE_CACHE_SIMPLE_ENABLED` | `false` unless configured in YAML | Redis exact response cache |
-| `SEMANTIC_CACHE_ENABLED` | `false` unless configured in YAML | Embedding + vector-store semantic response cache |
-Full reference: [`configs/config.example.yaml`](configs/config.example.yaml)
+|---------|----------|-------------------|
+| `aurora init` (default) | First run, individual devs | None |
+| `oss.local-power.example.yaml` | Local power users with caching | Redis |
+| `oss.team.example.yaml` | Team deployment | PostgreSQL, Redis, Qdrant |
 ---
 ## Response caching
-Two layers, both optional:
+Two optional layers. Both need Redis.
-- **Exact cache** -- hashes request path + body, returns `X-Cache: HIT (exact)` on identical requests. Enable with `RESPONSE_CACHE_SIMPLE_ENABLED` + Redis.
-- **Semantic cache** -- embeds prompts, searches vector store for similar requests. Returns `X-Cache: HIT (semantic)`. Supports `qdrant`, `pgvector`, `pinecone`, `weaviate`.
+- **Exact cache** — Hashes the request body and returns cached response on identical requests. Header: `X-Cache: HIT (exact)`.
+- **Semantic cache** — Embeds prompts, searches a vector store for semantically similar requests. Supports Qdrant, pgvector, Pinecone, Weaviate. Header: `X-Cache: HIT (semantic)`.
-Per-request bypass: `Cache-Control: no-cache` or `Cache-Control: no-store`.
+Bypass per-request: `Cache-Control: no-cache`
 ---
@@ -257,48 +327,50 @@ Per-request bypass: `Cache-Control: no-cache` or `Cache-Control: no-store`.
 docker compose up -d
 # Full stack (Aurora + infra)
-cp .env.template .env
 docker compose --profile app up -d
-# Local image build
-docker build -t aurora-oss .
-docker run --rm -p 8080:8080 --env-file .env aurora-oss
 ```
 ---
 ## Build from source
-**Prerequisites:** Go 1.26.2+, Node.js + pnpm
+**Prerequisites:** Go 1.26.2+, Node.js ≥18, pnpm
 ```bash
-# Dashboard
-pnpm --dir dashboard-ui install
-pnpm --dir dashboard-ui run build
+git clone https://github.com/gurveeer/Aurora.git && cd Aurora
+# Dashboard UI (required for admin dashboard)
+pnpm --dir dashboard-ui install && pnpm --dir dashboard-ui run build
 # Binary
-go build -o bin/aurora-oss.exe ./apps/aurora
+go build -o bin/aurora ./apps/aurora
-# Packaged release
-.\scripts\release\build-editions.ps1 -Package
+# Test
+go test ./apps/... ./internal/...
 ```
-Outputs: `bin/aurora-oss.exe`, `release/aurora-oss-windows-amd64.zip`
+After building, use `aurora init` to scaffold a project, or run directly with env vars:
-**Tests:**
+```bash
+export AURORA_MASTER_KEY="my-key"
+export GROQ_API_KEY="gsk_..."
+./bin/aurora
+```
+---
+## Self-update & uninstall
 ```bash
-go test ./apps/... ./internal/...
-pnpm --dir dashboard-ui run build
+aurora update       # Updates iaurora npm package to latest version
+aurora uninstall    # Removes iaurora npm package from your system
 ```
 ---
 ## Enterprise
-Aurora OSS covers gateway routing, analytics, and provider operations. **Aurora Enterprise** adds SSO, RBAC, tenant isolation, budget enforcement, compliance workflows, and production support.
-The Enterprise edition is a separate distribution. It cannot be enabled by editing files in this OSS tree.
+Aurora OSS covers gateway routing, analytics, and provider operations. **Aurora Enterprise** adds SSO, RBAC, tenant isolation, budget enforcement, compliance workflows, and production support. The Enterprise edition is a separate distribution — it cannot be enabled by editing files in this tree.
 ---
@@ -306,8 +378,6 @@ The Enterprise edition is a separate distribution. It cannot be enabled by editi
 | | |
 |---|---|
-| [Discord](https://discord.gg/YJPrfR9uh) | Deployment questions, provider setup, roadmap |
+| [Discord](https://discord.gg/YJPrfR9uh) | Questions, provider setup, roadmap |
 | [GitHub Issues](https://github.com/gurveeer/Aurora/issues) | Bug reports, feature requests |
 | [GitHub Stars](https://github.com/gurveeer/Aurora/stargazers) | Support the project |
-If Aurora saves your team time, a star helps others find it.

package/bin/aurora.exe CHANGED Viewed

Binary file

package/package.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-    "version":  "1.0.16",
+    "version":  "1.0.18",
     "author":  "SantiagoDePolonia",
     "license":  "Apache-2.0",
     "files":  [