iaurora 1.0.30 → 1.0.32

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 (4) hide show
  1. package/.env.example +1 -1
  2. package/README.md +400 -207
  3. package/bin/aurora.exe +0 -0
  4. package/package.json +1 -1
package/.env.example CHANGED
@@ -123,7 +123,7 @@
123
123
  # =============================================================================
124
124
 
125
125
  # External model metadata registry. Leave empty to disable upstream fetch.
126
- # MODEL_LIST_URL=https://aurorallm.github.io/aurora/assets/models.json
126
+ # MODEL_LIST_URL=https://github.com/aurorallm/aurora/blob/main/docs-assets/assets/models.json
127
127
 
128
128
  # Local model registry snapshot and user pricing overrides
129
129
  # MODEL_LIST_LOCAL_PATH=data/models.local.json
package/README.md CHANGED
@@ -1,34 +1,109 @@
1
1
  <p align="center">
2
- <img src="https://raw.githubusercontent.com/aurorallm/aurora/main/docs/assets/aurora-logo-animated.svg" width="96" height="96" alt="Aurora Logo">
2
+ <img src="https://raw.githubusercontent.com/aurorallm/aurora/main/docs-assets/assets/aurora-logo-animated.svg" width="96" height="96" alt="Aurora Logo">
3
3
  </p>
4
4
 
5
- <h1 align="center">Aurora Gateway OSS — Open-Source AI Gateway | OpenAI &amp; Anthropic Compatible API</h1>
5
+ <h1 align="center">Aurora — Open-Source AI Gateway</h1>
6
6
 
7
7
  <p align="center">
8
8
  <a href="LICENSE"><img src="https://img.shields.io/github/license/aurorallm/aurora" alt="License" height="20"></a>
9
9
  <a href="https://www.npmjs.com/package/iaurora"><img src="https://img.shields.io/npm/v/iaurora" alt="npm" height="20"></a>
10
- <a href="https://codecov.io/gh/aurorallm/aurora"><img src="https://codecov.io/gh/aurorallm/aurora/branch/main/graph/badge.svg" alt="codecov" height="20"></a>
11
10
  <a href="https://github.com/aurorallm/aurora"><img src="https://img.shields.io/github/stars/aurorallm/aurora" alt="GitHub Stars" height="20"></a>
12
- <a href="https://discord.gg/YJPrfR9uh"><img src="https://dcbadge.limes.pink/api/server/https://discord.gg/YJPrfR9uh?style=flat" alt="Discord" height="20"></a>
11
+ <a href="https://discord.gg/AfaFBSU2km"><img src="https://dcbadge.limes.pink/api/server/https://discord.gg/AfaFBSU2km?style=flat" alt="Discord" height="20"></a>
13
12
  <img src="https://img.shields.io/docker/pulls/aurorahq/aurora" alt="Docker Pulls" height="20">
14
- <a href="https://artifacthub.io/packages/search?repo=aurora-gateway"><img src="https://artifacthub.io/badge/repository/aurora-gateway" alt="Artifact Hub" height="20"></a>
13
+ <a href="https://artifacthub.io/packages/search?repo=aurora-gateway"><img src="https://img.shields.io/endpoint?url=https://artifacthub.io/badge/repository/aurora-gateway" alt="Artifact Hub" height="20"></a>
15
14
  </p>
16
15
 
17
- <p align="center"><b>Open-source LLM gateway (OSS edition). One API for every AI provider.</b></p>
16
+ <p align="center"><b>One API for every AI provider. Self-hosted. No vendor lock-in.</b></p>
18
17
 
19
- <p align="center">Self-hosted. No vendor lock-in. 14 provider types, 30+ LLM providers supported.</p>
18
+ <p align="center">14 provider types &bull; OpenAI &amp; Anthropic compatible &bull; Built in Go &bull; Apache 2.0</p>
20
19
 
21
- <a href="https://raw.githubusercontent.com/aurorallm/aurora/main/docs/assets/dashboard-overview.png">
22
- <img src="https://raw.githubusercontent.com/aurorallm/aurora/main/docs/assets/dashboard-overview.png" alt="Aurora open-source AI gateway admin dashboard showing provider stats and usage metrics" width="100%">
20
+ <a href="https://raw.githubusercontent.com/aurorallm/aurora/main/docs-assets/assets/dashboard-overview.png">
21
+ <img src="https://raw.githubusercontent.com/aurorallm/aurora/main/docs-assets/assets/dashboard-overview.png" alt="Aurora admin dashboard showing provider stats and usage metrics" width="100%">
23
22
  </a>
24
23
 
25
24
  ---
26
25
 
26
+ ## What Aurora Does
27
+
28
+ Aurora sits between your app and LLM providers. Your app sends requests using the standard OpenAI or Anthropic SDK — Aurora routes them to whichever provider you've configured.
29
+
30
+ ```python
31
+ # Before: hardcoded provider
32
+ client = OpenAI(base_url="https://api.openai.com/v1", api_key="sk-...")
33
+
34
+ # After: Aurora Gateway
35
+ client = OpenAI(base_url="http://localhost:8080/v1", api_key="your-aurora-key")
36
+ ```
37
+
38
+ No SDK changes. No format changes. Just swap the `base_url`.
39
+
40
+ ---
41
+
42
+ ## Features
43
+
44
+ ### Routing & Providers
45
+
46
+ - **14 provider types** — OpenAI, Anthropic, Gemini, Groq, DeepSeek, OpenRouter, xAI, Z.ai, MiniMax, Azure OpenAI, Oracle, Ollama, vLLM, Jina
47
+ - **Auto-discovery** — set an API key as an env var, restart, provider + all its models appear automatically
48
+ - **Provider pools** — group multiple keys/endpoints, load-balance with round-robin, health-aware failover
49
+ - **Fallback** — automatic failover on 5xx/429, or manual rules mapping failed provider+model to backups
50
+ - **Resilience** — exponential backoff with jitter, circuit breaker per provider (closed → open → half-open)
51
+ - **Multiple instances** — run `OPENAI_EAST_API_KEY` and `OPENAI_WEST_API_KEY` as separate providers
52
+ - **Custom base URLs** — override any provider's endpoint (corporate proxies, regional endpoints)
53
+ - **Passthrough** — `/p/{provider}/*` for full upstream API access (not just chat completions)
54
+
55
+ ### API Surface
56
+
57
+ - **OpenAI-compatible** — `/v1/chat/completions`, `/v1/embeddings`, `/v1/rerank`, `/v1/models`, `/v1/files`, `/v1/batches`
58
+ - **Responses API** — `/v1/responses` with full CRUD, cancel, input items, compact
59
+ - **Anthropic-compatible** — `/v1/messages`, `/v1/messages/count_tokens` (native Anthropic wire format)
60
+ - **Streaming** — SSE streaming for all endpoints, preserved end-to-end
61
+
62
+ ### Caching
63
+
64
+ - **Exact cache** — SHA-256 hash match on request, Redis-backed, async writes
65
+ - **Semantic cache** — vector similarity with configurable threshold, supports Qdrant, pgvector, Pinecone, Weaviate
66
+ - **Prompt cache** — forwards `cache_control` to Anthropic/OpenAI/Gemini native prompt caching
67
+ - **Model registry cache** — local filesystem + Redis, offline-safe
68
+
69
+ ### Security & Guardrails
70
+
71
+ - **Master key** — top-level gateway auth
72
+ - **Managed API keys** — scoped, rate-limited, per-key model authorization, usage stats
73
+ - **PII redaction** — email, phone, SSN, credit card detection and masking
74
+ - **Prompt injection blocking** — detects and blocks injection attempts
75
+ - **System prompt protection** — inject, override, or decorate system prompts
76
+ - **Regex blocking** — custom pattern matching with block or sanitize actions
77
+ - **Length limits** — character/token count enforcement on requests
78
+
79
+ ### Observability
80
+
81
+ - **Audit logging** — full request/response capture, buffered writes, configurable retention, live SSE stream
82
+ - **Usage analytics** — per-model token counting, cost tracking, daily aggregation by model/user-path
83
+ - **Prometheus metrics** — `aurora_requests_total`, `aurora_request_duration_seconds`, `aurora_requests_in_flight`, plus gateway phase timing
84
+ - **Admin dashboard** — React SPA built into the Go binary: providers, pools, models, aliases, guardrails, cache, usage, audit, auth keys, workflows, console, playground
85
+
86
+ ### Cost Control
87
+
88
+ - **Token saver** — policy-driven output compression (profiles: concise, caveman, ultra, wenyan)
89
+ - **Pricing management** — per-model pricing overrides, recalculation, import/export
90
+ - **Usage budgets** — per-key usage tracking and limits
91
+
92
+ ### Developer Experience
93
+
94
+ - **Single binary** — `npm install -g iaurora` or `docker pull aurorahq/aurora`
95
+ - **CLI** — `aurora init`, `aurora models sync/diff/show`, `aurora update`, `aurora uninstall`
96
+ - **Swagger docs** — `/swagger/index.html` (build-tag gated)
97
+ - **Config profiles** — pre-built configs for local, local-power, and team deployments
98
+ - **3-layer config** — code defaults → config.yaml → env vars (env vars win)
99
+
100
+ ---
101
+
27
102
  ## Quick Start
28
103
 
29
- Start routing AI traffic in 60 seconds using any of these deployment methods:
104
+ Start routing AI traffic in 60 seconds.
30
105
 
31
- ### CLI (npm)
106
+ ### Option A — CLI (npm)
32
107
 
33
108
  ```bash
34
109
  npm install -g iaurora
@@ -36,93 +111,164 @@ mkdir my-gateway && cd my-gateway
36
111
  aurora init # creates config.yaml, .env, data/
37
112
  ```
38
113
 
39
- **Option A — via `.env` file** (recommended):
114
+ Set your provider keys in `.env`:
40
115
 
41
116
  ```env
42
- AURORA_MASTER_KEY=your-secure-key
43
- GROQ_API_KEY=gsk_...
117
+ # ── REQUIRED ──────────────────────────────────────────────
118
+ AURORA_MASTER_KEY="your-secure-key"
119
+
120
+ # ── PROVIDER API KEYS (at least one) ─────────────────────
121
+ OPENAI_API_KEY="sk-..."
122
+ ANTHROPIC_API_KEY="sk-ant-..."
123
+ GEMINI_API_KEY="..."
124
+ GROQ_API_KEY="gsk_..."
125
+ DEEPSEEK_API_KEY="..."
126
+ OPENROUTER_API_KEY="..."
127
+ XAI_API_KEY="..."
128
+ ZAI_API_KEY="..."
129
+ MINIMAX_API_KEY="..."
130
+ AZURE_API_KEY="..."
131
+ ORACLE_API_KEY="..."
132
+ OLLAMA_API_KEY="..."
133
+ VLLM_API_KEY="..."
134
+ JINA_API_KEY="..."
135
+
136
+ # ── OPTIONAL FEATURE TOGGLES (set true to enable) ────────
137
+ LOGGING_ENABLED=true # Audit logging to storage
138
+ METRICS_ENABLED=true # Prometheus /metrics endpoint
139
+ GUARDRAILS_ENABLED=true # Content safety filters
140
+ TOKEN_SAVER_ENABLED=true # Output compression to cut token use
141
+
142
+ # ── PRODUCTION STORAGE ───────────────────────────────────
143
+ # STORAGE_TYPE=postgresql
144
+ # POSTGRES_URL=postgres://user:pass@localhost:5432/aurora
145
+
146
+ # ── REDIS CACHE (model cache + response cache) ──────────
147
+ # REDIS_URL=redis://localhost:6379
148
+ # RESPONSE_CACHE_SIMPLE_ENABLED=true
44
149
  ```
45
150
 
46
151
  ```bash
47
152
  aurora
48
153
  ```
49
154
 
50
- **Option B — via inline env vars** (no `.env` needed):
155
+ ### Option B — inline env vars (no `.env` needed)
51
156
 
52
- ```bash
53
- # Linux / macOS
54
- AURORA_MASTER_KEY=your-secure-key GROQ_API_KEY=gsk_... aurora
55
-
56
- # Windows PowerShell
57
- $env:AURORA_MASTER_KEY="your-secure-key"; $env:GROQ_API_KEY="gsk_..."; aurora
157
+ <details>
158
+ <summary>Linux / macOS</summary>
58
159
 
59
- # Windows CMD
60
- set AURORA_MASTER_KEY=your-secure-key && set GROQ_API_KEY=gsk_... && aurora
160
+ ```bash
161
+ AURORA_MASTER_KEY=your-secure-key \
162
+ OPENAI_API_KEY=sk-... \
163
+ ANTHROPIC_API_KEY=sk-ant-... \
164
+ GEMINI_API_KEY=... \
165
+ GROQ_API_KEY=gsk_... \
166
+ DEEPSEEK_API_KEY=... \
167
+ OPENROUTER_API_KEY=... \
168
+ XAI_API_KEY=... \
169
+ ZAI_API_KEY=... \
170
+ MINIMAX_API_KEY=... \
171
+ AZURE_API_KEY=... \
172
+ ORACLE_API_KEY=... \
173
+ OLLAMA_API_KEY=... \
174
+ VLLM_API_KEY=... \
175
+ JINA_API_KEY=... \
176
+ LOGGING_ENABLED=true \
177
+ METRICS_ENABLED=true \
178
+ GUARDRAILS_ENABLED=true \
179
+ TOKEN_SAVER_ENABLED=true \
180
+ aurora
181
+ ```
182
+ </details>
183
+
184
+ <details>
185
+ <summary>Windows PowerShell</summary>
186
+
187
+ ```powershell
188
+ $env:AURORA_MASTER_KEY="your-secure-key"; `
189
+ $env:OPENAI_API_KEY="sk-..."; `
190
+ $env:ANTHROPIC_API_KEY="sk-ant-..."; `
191
+ $env:GEMINI_API_KEY="..."; `
192
+ $env:GROQ_API_KEY="gsk_..."; `
193
+ $env:DEEPSEEK_API_KEY="..."; `
194
+ $env:OPENROUTER_API_KEY="..."; `
195
+ $env:XAI_API_KEY="..."; `
196
+ $env:ZAI_API_KEY="..."; `
197
+ $env:MINIMAX_API_KEY="..."; `
198
+ $env:AZURE_API_KEY="..."; `
199
+ $env:ORACLE_API_KEY="..."; `
200
+ $env:OLLAMA_API_KEY="..."; `
201
+ $env:VLLM_API_KEY="..."; `
202
+ $env:JINA_API_KEY="..."; `
203
+ $env:LOGGING_ENABLED="true"; `
204
+ $env:METRICS_ENABLED="true"; `
205
+ $env:GUARDRAILS_ENABLED="true"; `
206
+ $env:TOKEN_SAVER_ENABLED="true"; `
207
+ aurora
61
208
  ```
209
+ </details>
210
+
211
+ <details>
212
+ <summary>Windows CMD</summary>
213
+
214
+ ```cmd
215
+ set AURORA_MASTER_KEY=your-secure-key ^
216
+ && set OPENAI_API_KEY=sk-... ^
217
+ && set ANTHROPIC_API_KEY=sk-ant-... ^
218
+ && set GEMINI_API_KEY=... ^
219
+ && set GROQ_API_KEY=gsk_... ^
220
+ && set DEEPSEEK_API_KEY=... ^
221
+ && set OPENROUTER_API_KEY=... ^
222
+ && set XAI_API_KEY=... ^
223
+ && set ZAI_API_KEY=... ^
224
+ && set MINIMAX_API_KEY=... ^
225
+ && set AZURE_API_KEY=... ^
226
+ && set ORACLE_API_KEY=... ^
227
+ && set OLLAMA_API_KEY=... ^
228
+ && set VLLM_API_KEY=... ^
229
+ && set JINA_API_KEY=... ^
230
+ && set LOGGING_ENABLED=true ^
231
+ && set METRICS_ENABLED=true ^
232
+ && set GUARDRAILS_ENABLED=true ^
233
+ && set TOKEN_SAVER_ENABLED=true ^
234
+ && aurora
235
+ ```
236
+ </details>
62
237
 
63
- ### Docker
238
+ ### Option C — Docker
64
239
 
65
240
  ```bash
66
241
  docker run -d --name aurora -p 8080:8080 \
67
242
  -e AURORA_MASTER_KEY="your-secure-key" \
243
+ -e OPENAI_API_KEY="sk-..." \
244
+ -e ANTHROPIC_API_KEY="sk-ant-..." \
245
+ -e GEMINI_API_KEY="..." \
68
246
  -e GROQ_API_KEY="gsk_..." \
247
+ -e DEEPSEEK_API_KEY="..." \
248
+ -e OPENROUTER_API_KEY="..." \
249
+ -e XAI_API_KEY="..." \
250
+ -e ZAI_API_KEY="..." \
251
+ -e MINIMAX_API_KEY="..." \
252
+ -e AZURE_API_KEY="..." \
253
+ -e ORACLE_API_KEY="..." \
254
+ -e OLLAMA_API_KEY="..." \
255
+ -e VLLM_API_KEY="..." \
256
+ -e JINA_API_KEY="..." \
257
+ -e LOGGING_ENABLED=true \
258
+ -e METRICS_ENABLED=true \
259
+ -e GUARDRAILS_ENABLED=true \
260
+ -e TOKEN_SAVER_ENABLED=true \
69
261
  aurorahq/aurora
70
262
  ```
71
263
 
72
- ### Kubernetes (Helm)
73
-
74
- ```bash
75
- helm install aurora ./helm \
76
- --namespace aurora --create-namespace \
77
- --set auth.masterKey="your-secure-key" \
78
- --set providers.groq.apiKey="gsk_..." \
79
- --set providers.groq.enabled=true \
80
- --set redis.enabled=false
81
- ```
82
-
83
- ### Test your gateway
84
-
85
- ```bash
86
- curl http://localhost:8080/v1/chat/completions \
87
- -H "Content-Type: application/json" \
88
- -H "Authorization: Bearer $(grep AURORA_MASTER_KEY .env | cut -d= -f2)" \
89
- -d '{"model":"groq/llama-3.3-70b-versatile","messages":[{"role":"user","content":"Hello!"}]}'
90
- ```
91
-
92
- Dashboard: `http://localhost:8080/admin/dashboard`
93
-
94
- **Setup guides:** [npm](https://www.npmjs.com/package/iaurora) · [Docker](https://hub.docker.com/r/aurorahq/aurora) · [Helm/Kubernetes](https://github.com/aurorallm/aurora/tree/main/helm) · [Source](https://github.com/aurorallm/aurora)
95
-
96
- ---
97
-
98
- ## Enterprise Deployments
99
-
100
- Aurora supports enterprise-grade deployments for teams running production AI systems at scale.
101
- In addition to private networking, custom security controls, and governance, **Aurora Enterprise** unlocks advanced capabilities including SSO, RBAC, tenant isolation, budget enforcement, compliance workflows, and production support.
102
-
103
- The Enterprise edition is a separate distribution with a signed license.
104
-
105
- <a href="https://raw.githubusercontent.com/aurorallm/aurora/main/docs/assets/comparison.png">
106
- <img src="https://raw.githubusercontent.com/aurorallm/aurora/main/docs/assets/comparison.png" alt="OSS vs Enterprise comparison" width="100%" style="border-radius:12px;margin:16px 0;">
107
- </a>
108
-
109
- <div align="center">
110
- <a href="mailto:team.auroragate@gmail.com?subject=Aurora%20Enterprise%20Inquiry" style="display:block;margin-top:5px;">
111
- <img src="https://img.shields.io/badge/Email%20Us-Enterprise-5865F2?style=for-the-badge&logo=gmail&logoColor=white" alt="Email Aurora Enterprise" width="200"/>
112
- </a>
113
- </div>
114
-
115
- ---
116
-
117
- ## Kubernetes (Helm)
118
-
119
- Deploy on any Kubernetes cluster with the [Helm chart](https://github.com/aurorallm/aurora/tree/main/helm).
264
+ ### Option D — Kubernetes (Helm)
120
265
 
121
266
  ```bash
122
267
  # Quick dev — Groq, no Redis, no auth
123
268
  helm install aurora ./helm \
124
269
  --namespace aurora --create-namespace \
125
- --set image.tag=1.0.25 \
270
+ --set image.repository=aurorahq/aurora \
271
+ --set image.tag=latest \
126
272
  --set providers.groq.apiKey="gsk_your_key_here" \
127
273
  --set providers.groq.enabled=true \
128
274
  --set redis.enabled=false \
@@ -133,85 +279,125 @@ helm install aurora ./helm \
133
279
  # Production — multiple providers, auth, Redis
134
280
  helm upgrade --install aurora ./helm \
135
281
  --namespace aurora --create-namespace \
136
- --set image.tag=1.0.25 \
282
+ --set image.repository=aurorahq/aurora \
283
+ --set image.tag=latest \
137
284
  --set auth.masterKey="your-secure-key" \
138
285
  --set providers.openai.apiKey="sk-..." \
139
286
  --set providers.openai.enabled=true \
140
287
  --set providers.anthropic.apiKey="sk-ant-..." \
141
288
  --set providers.anthropic.enabled=true \
289
+ --set providers.gemini.apiKey="..." \
290
+ --set providers.gemini.enabled=true \
291
+ --set providers.groq.apiKey="gsk_..." \
292
+ --set providers.groq.enabled=true \
293
+ --set providers.deepseek.apiKey="..." \
294
+ --set providers.deepseek.enabled=true \
142
295
  --set redis.enabled=true
143
296
  ```
144
297
 
145
298
  **Full Helm docs:** [helm/README.md](./helm/README.md)
146
299
 
300
+ ### Test your gateway
301
+
302
+ ```bash
303
+ # OpenAI format
304
+ curl http://localhost:8080/v1/chat/completions \
305
+ -H "Content-Type: application/json" \
306
+ -H "Authorization: Bearer your-master-key" \
307
+ -d '{"model":"groq/llama-4-scout-17b-16e-instruct","messages":[{"role":"user","content":"Hello!"}]}'
308
+
309
+ # Anthropic format with streaming
310
+ curl http://localhost:8080/v1/messages \
311
+ -H "Content-Type: application/json" \
312
+ -H "Authorization: Bearer your-master-key" \
313
+ -H "anthropic-version: 2023-06-01" \
314
+ -d '{
315
+ "model": "anthropic/claude-sonnet-5-20260630",
316
+ "max_tokens": 1024,
317
+ "stream": true,
318
+ "messages": [{"role": "user", "content": "Hello!"}]
319
+ }'
320
+
321
+ # Embeddings
322
+ curl http://localhost:8080/v1/embeddings \
323
+ -H "Content-Type: application/json" \
324
+ -H "Authorization: Bearer your-master-key" \
325
+ -d '{"model":"openai/text-embedding-3-small","input":"Hello world"}'
326
+
327
+ # Reranking (Jina)
328
+ curl http://localhost:8080/v1/rerank \
329
+ -H "Content-Type: application/json" \
330
+ -H "Authorization: Bearer your-master-key" \
331
+ -d '{"model":"jina/jina-reranker-v2-base-multilingual","query":"test","documents":["doc1","doc2"]}'
332
+ ```
333
+
334
+ Dashboard: `http://localhost:8080/admin/dashboard`
335
+
336
+ **Docs:** [aurorallm.online/docs](https://aurorallm.online/docs) · [Website](https://aurorallm.online) · [npm](https://www.npmjs.com/package/iaurora) · [Docker](https://hub.docker.com/r/aurorahq/aurora) · [GitHub](https://github.com/aurorallm/aurora)
337
+
147
338
  ---
148
339
 
149
340
  ## Providers
150
341
 
151
342
  Providers are **auto-discovered from environment variables**. Set any provider's `_API_KEY` and restart — the provider and its default models appear automatically.
152
343
 
153
- > **Security note for public docs:** The env var names listed below are documentation references. Actual secrets go into your **`.env` file** (in `.gitignore`) or your **deployment secrets manager** — never commit them.
154
-
155
- ### All supported providers
344
+ > **Security note:** The env var names below are documentation references. Actual secrets go into your **`.env` file** (in `.gitignore`) or your **deployment secrets manager** — never commit them.
156
345
 
157
346
  | Provider | Env var | Default base URL | Requires base URL | API key required | Default models |
158
347
  |----------|---------|-----------------|-------------------|-----------------|----------------|
159
- | OpenAI | `OPENAI_API_KEY` | `https://api.openai.com/v1` | No | Yes | `gpt-4o`, `gpt-4o-mini` |
160
- | Anthropic | `ANTHROPIC_API_KEY` | `https://api.anthropic.com/v1` | No | Yes | `claude-sonnet-4`, `claude-opus-4` |
161
- | Google Gemini | `GEMINI_API_KEY` | `https://generativelanguage.googleapis.com/v1beta/openai` | No | Yes | `gemini-2.5-pro`, `gemini-2.5-flash` |
162
- | Groq | `GROQ_API_KEY` | `https://api.groq.com/openai/v1` | No | Yes | `llama-3.3-70b`, `qwen3-32b`, `whisper` |
163
- | DeepSeek | `DEEPSEEK_API_KEY` | `https://api.deepseek.com` | No | Yes | `deepseek-chat`, `deepseek-reasoner` |
348
+ | OpenAI | `OPENAI_API_KEY` | `https://api.openai.com/v1` | No | Yes | `gpt-5.6-sol`, `gpt-5.6-luna` |
349
+ | Anthropic | `ANTHROPIC_API_KEY` | `https://api.anthropic.com/v1` | No | Yes | `claude-sonnet-5`, `claude-fable-5` |
350
+ | Google Gemini | `GEMINI_API_KEY` | `https://generativelanguage.googleapis.com/v1beta/openai` | No | Yes | `gemini-3.1-pro`, `gemini-3.5-flash` |
351
+ | Groq | `GROQ_API_KEY` | `https://api.groq.com/openai/v1` | No | Yes | `llama-4-scout-17b`, `llama-4-maverick-17b`, `qwen3-32b` |
352
+ | DeepSeek | `DEEPSEEK_API_KEY` | `https://api.deepseek.com` | No | Yes | `deepseek-v4-pro`, `deepseek-v4-flash` |
164
353
  | OpenRouter | `OPENROUTER_API_KEY` | `https://openrouter.ai/api/v1` | No | Yes | 300+ models |
165
- | xAI (Grok) | `XAI_API_KEY` | `https://api.x.ai/v1` | No | Yes | `grok-3`, `grok-3-mini` |
166
- | Z.ai | `ZAI_API_KEY` | `https://api.z.ai/api/paas/v4` | No | Yes | `glm-4.5` |
167
- | MiniMax | `MINIMAX_API_KEY` | `https://api.minimax.io/v1` | No | Yes | `minimax-m1` |
354
+ | xAI (Grok) | `XAI_API_KEY` | `https://api.x.ai/v1` | No | Yes | `grok-4.5`, `grok-4.3` |
355
+ | Z.ai | `ZAI_API_KEY` | `https://api.z.ai/api/paas/v4` | No | Yes | `glm-5.2` |
356
+ | MiniMax | `MINIMAX_API_KEY` | `https://api.minimax.io/v1` | No | Yes | `minimax-m3` |
168
357
  | Azure OpenAI | `AZURE_API_KEY` | — | **Yes** | Yes | Your deployments |
169
358
  | Oracle | `ORACLE_API_KEY` | — | **Yes** | Yes | `cohere.command-r-plus` |
170
359
  | Ollama | `OLLAMA_API_KEY` | `http://localhost:11434/v1` | No | **No** (optional) | Any local model |
171
360
  | vLLM | `VLLM_API_KEY` | `http://localhost:8000/v1` | No | **No** (optional) | Any served model |
172
361
  | Jina (reranker) | `JINA_API_KEY` | — | **Yes** | Yes | `jina-embeddings-v3` |
173
362
 
174
- ### Per-provider extras
363
+ ### Per-provider configuration
175
364
 
176
365
  Every provider supports `*_MODELS` to override auto-discovered models:
177
366
 
178
367
  ```env
179
- OPENAI_MODELS=gpt-4o,gpt-4o-mini,gpt-4-turbo
368
+ OPENAI_MODELS=gpt-5.6-sol,gpt-5.6-terra,gpt-5.6-luna
180
369
  ```
181
370
 
182
- OpenRouter extras:
371
+ Custom base URL:
183
372
 
184
373
  ```env
185
- OPENROUTER_SITE_URL=https://github.com/aurorallm/aurora
186
- OPENROUTER_APP_NAME=Aurora Gateway
374
+ OPENAI_BASE_URL=https://my-corp-openai-proxy.example.com/v1
187
375
  ```
188
376
 
189
- Azure requires API version:
377
+ Multiple instances of the same provider (underscores become hyphens in the provider name):
190
378
 
191
379
  ```env
192
- AZURE_API_VERSION=2024-10-21
380
+ OPENAI_EAST_API_KEY=sk-... # → provider: openai-east
381
+ OPENAI_WEST_API_KEY=sk-... # → provider: openai-west
193
382
  ```
194
383
 
195
- ### Custom base URL
196
-
197
- Override any provider's endpoint:
384
+ Azure requires API version:
198
385
 
199
386
  ```env
200
- OPENAI_BASE_URL=https://my-corp-openai-proxy.example.com/v1
387
+ AZURE_API_VERSION=2024-10-21
201
388
  ```
202
389
 
203
- ### Multiple instances of the same provider
204
-
205
- Use suffix notation (underscores become hyphens in the provider name):
390
+ OpenRouter extras:
206
391
 
207
392
  ```env
208
- OPENAI_EAST_API_KEY=sk-... # → provider: openai-east
209
- OPENAI_WEST_API_KEY=sk-... # → provider: openai-west
210
- JINA_API_KEY1=... # → provider: jina-1
393
+ OPENROUTER_SITE_URL=https://github.com/aurorallm/aurora
394
+ OPENROUTER_APP_NAME=Aurora Gateway
211
395
  ```
212
396
 
213
397
  ---
214
398
 
399
+ ---
400
+
215
401
  ## Configuration
216
402
 
217
403
  The gateway loads settings in this priority order (later wins):
@@ -237,54 +423,33 @@ Generated by `aurora init`, every section of `config.yaml` is documented inline:
237
423
  | `token_saver` | Output compression |
238
424
  | `fallback` | Provider failover rules |
239
425
  | `resilience` | Retry + circuit breaker |
426
+ | `workflows` | Policy-based request routing |
240
427
 
241
- > The tables below document every supported env var for reference. In practice you configure these in your **`.env` file** (CLI deployments), **`-e` flags** (Docker), or **`--set` values** (Helm). Never commit secrets to version control.
242
-
243
- ### Essential `.env` variables
244
-
245
- Minimal set to get the gateway running:
428
+ ### Config profiles
246
429
 
247
- ```env
248
- # ── REQUIRED ──────────────────────────────────────────────
249
- AURORA_MASTER_KEY=replace-with-secure-random-key
430
+ Pre-built configs in `configs/editions/`:
250
431
 
251
- # ── AT LEAST ONE PROVIDER ────────────────────────────────
252
- OPENAI_API_KEY=sk-...
253
- # or: GROQ_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, etc.
432
+ | Profile | File | Use case |
433
+ |---------|------|----------|
434
+ | OSS | `oss.env.example` | Minimal local — SQLite, no Redis |
435
+ | OSS Local Power | `oss.local-power.env.example` | SQLite + Redis exact cache |
436
+ | OSS Team | `oss.team.env.example` | Postgres + Redis + Qdrant — full team deployment |
254
437
 
255
- # ── OPTIONAL BUT RECOMMENDED ─────────────────────────────
256
- PORT=8080 # Listening port (default: 8080)
257
- STORAGE_TYPE=sqlite # sqlite (default), postgresql, mongodb
258
- LOG_LEVEL=info # debug, info, warn, error
259
- LOG_FORMAT=text # text or json
438
+ ```bash
439
+ export AURORA_CONFIG_PATH=configs/editions/oss.team.example.yaml
260
440
  ```
261
441
 
262
- ### Configuring the same variable across all deployment methods
263
-
264
- Each env var below works in all three deploy modes — here is an example:
265
-
266
- | Variable | `.env` file | Docker `-e` flag | Helm `--set` value |
267
- |----------|-------------|------------------|---------------------|
268
- | `PORT` | `PORT=9090` | `-e PORT=9090` | `--set server.port=9090` |
269
- | `AURORA_MASTER_KEY` | `AURORA_MASTER_KEY=...` | `-e AURORA_MASTER_KEY=...` | `--set auth.masterKey=...` |
270
- | `OPENAI_API_KEY` | `OPENAI_API_KEY=sk-...` | `-e OPENAI_API_KEY=sk-...` | `--set providers.openai.apiKey=...` |
271
- | `STORAGE_TYPE` | `STORAGE_TYPE=postgresql` | `-e STORAGE_TYPE=postgresql` | `--set storage.type=postgresql` |
272
- | `REDIS_URL` | `REDIS_URL=redis://...` | `-e REDIS_URL=redis://...` | `--set cache.redis.url=...` |
273
-
274
- ---
275
-
276
442
  ### Complete env var reference
277
443
 
278
- All configurable environment variables, organized by subsystem:
279
-
280
- #### Server & Security
444
+ <details>
445
+ <summary>Server & Security</summary>
281
446
 
282
447
  | Env var | Default | Description |
283
448
  |---------|---------|-------------|
284
449
  | `PORT` | `8080` | HTTP listening port |
285
450
  | `BASE_PATH` | `/` | URL path prefix to mount under |
286
451
  | `AURORA_MASTER_KEY` | `""` | Master API key for auth |
287
- | `BODY_SIZE_LIMIT` | `10M` | Max request body size (e.g. `10M`, `1G`, `500K`) |
452
+ | `BODY_SIZE_LIMIT` | `10M` | Max request body size |
288
453
  | `SWAGGER_ENABLED` | `false` | Enable Swagger UI at `/swagger/index.html` |
289
454
  | `PPROF_ENABLED` | `false` | Enable pprof at `/debug/pprof/` |
290
455
  | `ENABLE_PASSTHROUGH_ROUTES` | `true` | Provider-native passthrough at `/p/{provider}` |
@@ -294,18 +459,22 @@ All configurable environment variables, organized by subsystem:
294
459
  | `DISABLE_REQUEST_LOGGING` | `false` | Turn off request logging |
295
460
  | `DISABLE_REQUEST_BODY_SNAPSHOT` | `false` | Don't snapshot request bodies |
296
461
  | `DISABLE_PASSTHROUGH_SEMANTIC_ENRICHMENT` | `false` | Disable semantic enrichment on passthrough |
462
+ </details>
297
463
 
298
- #### HTTP Client & Proxy
464
+ <details>
465
+ <summary>HTTP Client & Proxy</summary>
299
466
 
300
467
  | Env var | Default | Description |
301
468
  |---------|---------|-------------|
302
469
  | `HTTP_TIMEOUT` | `600` | Upstream request timeout (seconds) |
303
- | `HTTP_RESPONSE_HEADER_TIMEOUT` | `600` | Timeout for upstream response headers (seconds) |
470
+ | `HTTP_RESPONSE_HEADER_TIMEOUT` | `600` | Timeout for upstream response headers |
304
471
  | `HTTP_PROXY` | — | HTTP proxy URL for upstream calls |
305
472
  | `HTTPS_PROXY` | — | HTTPS proxy URL |
306
473
  | `NO_PROXY` | — | Hosts to exclude from proxy |
474
+ </details>
307
475
 
308
- #### Storage
476
+ <details>
477
+ <summary>Storage</summary>
309
478
 
310
479
  | Env var | Default | Description |
311
480
  |---------|---------|-------------|
@@ -315,20 +484,24 @@ All configurable environment variables, organized by subsystem:
315
484
  | `POSTGRES_MAX_CONNS` | `10` | PostgreSQL connection pool max |
316
485
  | `MONGODB_URL` | — | MongoDB connection string |
317
486
  | `MONGODB_DATABASE` | `aurora` | MongoDB database name |
487
+ </details>
318
488
 
319
- #### Model Registry
489
+ <details>
490
+ <summary>Model Registry</summary>
320
491
 
321
492
  | Env var | Default | Description |
322
493
  |---------|---------|-------------|
323
- | `MODEL_LIST_URL` | `https://aurorallm.github.io/aurora/assets/models.json` | External model metadata registry (empty = disabled) |
494
+ | `MODEL_LIST_URL` | `https://github.com/aurorallm/aurora/blob/main/docs-assets/assets/models.json` | External model metadata registry |
324
495
  | `MODEL_LIST_LOCAL_PATH` | `data/models.local.json` | Local model registry snapshot path |
325
496
  | `MODEL_LIST_USER_OVERRIDES_PATH` | `data/user_pricing.yaml` | User pricing override file |
326
497
  | `MODELS_ENABLED_BY_DEFAULT` | `true` | Default enabled state for provider models |
327
- | `MODEL_OVERRIDES_ENABLED` | `true` | Allow per-model overrides (dashboard editing) |
328
- | `KEEP_ONLY_ALIASES_AT_MODELS_ENDPOINT` | `false` | Hide provider models from `GET /v1/models`, show only aliases |
329
- | `CONFIGURED_PROVIDER_MODELS_MODE` | `fallback` | `fallback` or `allowlist` — how configured model lists affect inventory |
498
+ | `MODEL_OVERRIDES_ENABLED` | `true` | Allow per-model overrides |
499
+ | `KEEP_ONLY_ALIASES_AT_MODELS_ENDPOINT` | `false` | Hide provider models, show only aliases |
500
+ | `CONFIGURED_PROVIDER_MODELS_MODE` | `fallback` | `fallback` or `allowlist` |
501
+ </details>
330
502
 
331
- #### Caching
503
+ <details>
504
+ <summary>Caching</summary>
332
505
 
333
506
  **Model cache:**
334
507
 
@@ -354,7 +527,7 @@ All configurable environment variables, organized by subsystem:
354
527
  |---------|---------|-------------|
355
528
  | `SEMANTIC_CACHE_ENABLED` | `false` | Enable semantic cache |
356
529
  | `SEMANTIC_CACHE_THRESHOLD` | `0.92` | Similarity threshold (0-1) |
357
- | `SEMANTIC_CACHE_PROMPT_SIMILARITY` | `0.90` | Prompt similarity threshold (0-1) |
530
+ | `SEMANTIC_CACHE_PROMPT_SIMILARITY` | `0.90` | Prompt similarity threshold |
358
531
  | `SEMANTIC_CACHE_TTL` | `3600` | Entry TTL (seconds) |
359
532
  | `SEMANTIC_CACHE_MAX_CONV_MESSAGES` | `3` | Recent conversation messages to embed |
360
533
  | `SEMANTIC_CACHE_EXCLUDE_SYSTEM_PROMPT` | `false` | Exclude system prompt from cache key |
@@ -374,20 +547,24 @@ All configurable environment variables, organized by subsystem:
374
547
  | `SEMANTIC_CACHE_WEAVIATE_URL` | — | Weaviate URL |
375
548
  | `SEMANTIC_CACHE_WEAVIATE_CLASS` | `AuroraSemanticCache` | Weaviate class name |
376
549
  | `SEMANTIC_CACHE_WEAVIATE_API_KEY` | — | Weaviate API key |
550
+ </details>
377
551
 
378
- #### Audit Logging
552
+ <details>
553
+ <summary>Audit Logging</summary>
379
554
 
380
555
  | Env var | Default | Description |
381
556
  |---------|---------|-------------|
382
557
  | `LOGGING_ENABLED` | `false` | Enable audit log to storage |
383
- | `LOGGING_LOG_BODIES` | `true` | Log request/response bodies (may contain PII) |
558
+ | `LOGGING_LOG_BODIES` | `true` | Log request/response bodies |
384
559
  | `LOGGING_LOG_HEADERS` | `true` | Log headers (sensitive headers redacted) |
385
560
  | `LOGGING_ONLY_MODEL_INTERACTIONS` | `true` | Skip health/metrics/admin endpoints |
386
561
  | `LOGGING_BUFFER_SIZE` | `1000` | In-memory queue capacity |
387
562
  | `LOGGING_FLUSH_INTERVAL` | `5` | Flush interval (seconds) |
388
563
  | `LOGGING_RETENTION_DAYS` | `30` | Auto-delete after N days (0 = forever) |
564
+ </details>
389
565
 
390
- #### Usage Tracking
566
+ <details>
567
+ <summary>Usage Tracking</summary>
391
568
 
392
569
  | Env var | Default | Description |
393
570
  |---------|---------|-------------|
@@ -397,30 +574,36 @@ All configurable environment variables, organized by subsystem:
397
574
  | `USAGE_BUFFER_SIZE` | `1000` | In-memory queue capacity |
398
575
  | `USAGE_FLUSH_INTERVAL` | `5` | Flush interval (seconds) |
399
576
  | `USAGE_RETENTION_DAYS` | `90` | Auto-delete after N days (0 = forever) |
577
+ </details>
400
578
 
401
- #### Guardrails
579
+ <details>
580
+ <summary>Guardrails</summary>
402
581
 
403
582
  | Env var | Default | Description |
404
583
  |---------|---------|-------------|
405
584
  | `GUARDRAILS_ENABLED` | `false` | Enable content safety filters globally |
406
585
  | `ENABLE_GUARDRAILS_FOR_BATCH_PROCESSING` | `false` | Apply guardrails to `/v1/batches` items |
586
+ </details>
407
587
 
408
- #### Metrics
588
+ <details>
589
+ <summary>Metrics</summary>
409
590
 
410
591
  | Env var | Default | Description |
411
592
  |---------|---------|-------------|
412
593
  | `METRICS_ENABLED` | `false` | Enable Prometheus `/metrics` endpoint |
413
594
  | `METRICS_ENDPOINT` | `/metrics` | Metrics endpoint path |
595
+ </details>
414
596
 
415
- #### Token Saver (output compression)
597
+ <details>
598
+ <summary>Token Saver</summary>
416
599
 
417
600
  | Env var | Default | Description |
418
601
  |---------|---------|-------------|
419
- | `TOKEN_SAVER_ENABLED` | `false` | Enable caveman-style output compression |
602
+ | `TOKEN_SAVER_ENABLED` | `false` | Enable output compression |
420
603
  | `TOKEN_SAVER_ENDPOINTS` | `chat_completions` | Endpoints to apply it to |
421
604
  | `TOKEN_SAVER_APPLY_STREAMING` | `true` | Apply to streaming responses |
422
605
  | `TOKEN_SAVER_OUTPUT_ENABLED` | `false` | Enable output style/profile |
423
- | `TOKEN_SAVER_OUTPUT_PROFILE` | `concise` | Output profile name |
606
+ | `TOKEN_SAVER_OUTPUT_PROFILE` | `concise` | Profile: `concise`, `caveman`, `ultra`, `wenyan` |
424
607
  | `TOKEN_SAVER_MODELS_INCLUDE` | — | Models to include (comma-separated) |
425
608
  | `TOKEN_SAVER_MODELS_EXCLUDE` | — | Models to exclude |
426
609
  | `TOKEN_SAVER_PROVIDERS_INCLUDE` | — | Providers to include |
@@ -428,8 +611,10 @@ All configurable environment variables, organized by subsystem:
428
611
  | `TOKEN_SAVER_ON_ERROR` | `allow` | Behavior on error: `allow` or `block` |
429
612
  | `TOKEN_SAVER_EMIT_HEADERS` | `true` | Emit token-saver headers in response |
430
613
  | `TOKEN_SAVER_AUDIT_ENABLED` | `true` | Log token-saver actions |
614
+ </details>
431
615
 
432
- #### Resilience (retry + circuit breaker)
616
+ <details>
617
+ <summary>Resilience</summary>
433
618
 
434
619
  | Env var | Default | Description |
435
620
  |---------|---------|-------------|
@@ -441,15 +626,19 @@ All configurable environment variables, organized by subsystem:
441
626
  | `CIRCUIT_BREAKER_FAILURE_THRESHOLD` | `5` | Failures before circuit opens |
442
627
  | `CIRCUIT_BREAKER_SUCCESS_THRESHOLD` | `2` | Successes before circuit closes |
443
628
  | `CIRCUIT_BREAKER_TIMEOUT` | `30s` | Time before half-open retry |
629
+ </details>
444
630
 
445
- #### Fallback
631
+ <details>
632
+ <summary>Fallback</summary>
446
633
 
447
634
  | Env var | Default | Description |
448
635
  |---------|---------|-------------|
449
636
  | `FEATURE_FALLBACK_MODE` | `manual` | Fallback mode: `auto`, `manual`, or `off` |
450
637
  | `FALLBACK_MANUAL_RULES_PATH` | — | Path to manual fallback rules JSON |
638
+ </details>
451
639
 
452
- #### Admin & Features
640
+ <details>
641
+ <summary>Admin & Features</summary>
453
642
 
454
643
  | Env var | Default | Description |
455
644
  |---------|---------|-------------|
@@ -460,47 +649,34 @@ All configurable environment variables, organized by subsystem:
460
649
  | `CLI_TOOLS_APPLY_ENABLED` | `false` | Allow admin/API to apply tool changes |
461
650
  | `WORKFLOW_REFRESH_INTERVAL` | `1m` | Workflow refresh interval from storage |
462
651
  | `EDITION` | — | Edition identifier (Enterprise use) |
652
+ </details>
463
653
 
464
- #### Config file path
654
+ <details>
655
+ <summary>Config file path</summary>
465
656
 
466
657
  | Env var | Default | Description |
467
658
  |---------|---------|-------------|
468
659
  | `AURORA_CONFIG_PATH` | `configs/config.yaml` | Override path to config YAML |
469
-
470
- ---
471
-
472
- ### Quick config profiles
473
-
474
- Aurora ships pre-built config profiles in `configs/editions/`:
475
-
476
- | Profile | File | Use case |
477
- |---------|------|----------|
478
- | OSS | `oss.env.example` | Minimal local — SQLite, no Redis |
479
- | OSS Local Power | `oss.local-power.env.example` | SQLite + Redis exact cache |
480
- | OSS Team | `oss.team.env.example` | Postgres + Redis + Qdrant — full team deployment |
481
-
482
- ```bash
483
- export AURORA_CONFIG_PATH=configs/editions/oss.team.example.yaml
484
- ```
660
+ </details>
485
661
 
486
662
  ---
487
663
 
488
664
  ## CLI Reference
489
665
 
490
- The `aurora` CLI is installed via `npm install -g iaurora`.
666
+ Installed via `npm install -g iaurora`.
491
667
 
492
668
  | Command | Description |
493
669
  |---------|-------------|
494
- | `aurora init` | Scaffolds `config.yaml`, `.env`, `data/` in the current directory |
495
- | `aurora` | Starts the gateway server (default port 8080) |
496
- | `aurora --help` | Show all CLI options |
497
-
498
- `aurora init` generates:
499
- - **`config.yaml`** — Full gateway configuration with inline docs for every section
500
- - **`.env`** — Environment file for secrets and runtime overrides (based on `.env.template`)
501
- - **`data/`** — Directory for SQLite database and local model cache
502
-
503
- The gateway merges `config.yaml` + `.env`/env vars at startup. Use `config.yaml` for structure and `.env` for secrets/keys.
670
+ | `aurora` | Start the gateway server (default port 8080) |
671
+ | `aurora init` | Scaffold `config.yaml`, `.env`, `data/` in current directory |
672
+ | `aurora update` | Self-update via `npm install -g iaurora@latest` |
673
+ | `aurora uninstall` | Remove via `npm uninstall -g iaurora` |
674
+ | `aurora models sync` | Download upstream model registry to local file |
675
+ | `aurora models diff` | Show pricing diff between upstream and local snapshot |
676
+ | `aurora models show` | Print effective pricing for a model after merging overrides |
677
+ | `aurora -version` | Print version information |
678
+ | `aurora -help` | Show all CLI options and config reference |
679
+ | `aurora -help-json` | Dump env var schema as JSON |
504
680
 
505
681
  ---
506
682
 
@@ -508,36 +684,53 @@ The gateway merges `config.yaml` + `.env`/env vars at startup. Use `config.yaml`
508
684
 
509
685
  ```text
510
686
  aurora/
511
- ├── apps/ # Application entrypoints
512
- │ └── aurora/ # Main gateway binary
513
- ├── internal/ # Internal packages
514
- │ ├── api/ # HTTP handlers, middleware
515
- │ ├── config/ # Configuration loading and validation
516
- │ ├── providers/ # Provider implementations (OpenAI, Anthropic, etc.)
517
- │ ├── storage/ # SQLite, PostgreSQL, MongoDB backends
518
- │ ├── guardrails/ # Content safety filters
519
- │ ├── cache/ # Exact and semantic caching
520
- │ └── analytics/ # Usage tracking and metrics
521
- ├── dashboard-ui/ # React admin dashboard frontend
522
- ├── configs/ # Configuration profiles and examples
523
- ├── docs/ # Documentation and assets
524
- ├── scripts/ # Build and release scripts
525
- ├── test/ # Test suites
526
- └── helm/ # Kubernetes Helm charts
687
+ ├── apps/ # Application entrypoints
688
+ ├── internal/ # Core packages (providers, gateway, storage, guardrails, etc.)
689
+ ├── dashboard-ui/ # React admin dashboard (Vite)
690
+ ├── configs/ # Configuration profiles and examples
691
+ ├── docs-assets/ # Images, models.json, assets
692
+ ├── helm/ # Kubernetes Helm charts
693
+ ├── monitoring/ # Prometheus + Grafana configs
694
+ ├── npm/ # npm CLI wrapper
695
+ ├── bench-results/ # Benchmark data
696
+ ├── release/ # Release scripts
697
+ └── scripts/ # Build and utility scripts
527
698
  ```
528
699
 
529
700
  ---
530
701
 
702
+ ## Enterprise Deployments
703
+
704
+ Aurora supports enterprise-grade deployments for teams running production AI systems at scale.
705
+ In addition to private networking, custom security controls, and governance, **Aurora Enterprise** unlocks advanced capabilities including SSO, RBAC, tenant isolation, budget enforcement, compliance workflows, and production support.
706
+
707
+ The Enterprise edition is a separate distribution with a signed license.
708
+
709
+ <a href="https://raw.githubusercontent.com/aurorallm/aurora/main/docs-assets/assets/comparison.png">
710
+ <img src="https://raw.githubusercontent.com/aurorallm/aurora/main/docs-assets/assets/comparison.png" alt="OSS vs Enterprise comparison" width="100%" style="border-radius:12px;margin:16px 0;">
711
+ </a>
712
+
713
+ <div align="center">
714
+ <a href="mailto:team.auroragate@gmail.com?subject=Aurora%20Enterprise%20Inquiry" style="display:block;margin-top:5px;">
715
+ <img src="https://img.shields.io/badge/Email%20Us-Enterprise-5865F2?style=for-the-badge&logo=gmail&logoColor=white" alt="Email Aurora Enterprise" width="200"/>
716
+ </a>
717
+ </div>
718
+
719
+ ---
720
+
531
721
  ## Documentation
532
722
 
533
- - [CLI Reference](https://github.com/aurorallm/aurora)
534
- - [Provider Configuration](https://github.com/aurorallm/aurora)
535
- - [Admin Dashboard](https://github.com/aurorallm/aurora)
536
- - [Docker Compose & Helm](https://github.com/aurorallm/aurora)
723
+ - [aurorallm.online/docs](https://aurorallm.online/docs) — full documentation
724
+ - [aurorallm.online/docs/getting-started/quickstart](https://aurorallm.online/docs/getting-started/quickstart) — quickstart guide
725
+ - [aurorallm.online/docs/guides](https://aurorallm.online/docs/guides) — provider and integration guides
726
+ - [aurorallm.online/docs/api/overview](https://aurorallm.online/docs/api/overview) — API reference
727
+ - [aurorallm.online/benchmarks](https://aurorallm.online/benchmarks) — performance benchmarks
728
+
729
+ ---
537
730
 
538
731
  ## Need Help?
539
732
 
540
- [Join our Discord](https://discord.com/invite/YJPrfR9uh) for community support, setup help, and discussions.
733
+ [Join our Discord](https://discord.gg/AfaFBSU2km) for community support, setup help, and discussions.
541
734
 
542
735
  ---
543
736
 
@@ -556,4 +749,4 @@ We welcome contributions of all kinds! Check out the repository to get started:
556
749
 
557
750
  This project is licensed under the Apache 2.0 License — see the [LICENSE](LICENSE) file for details.
558
751
 
559
- Built with ❤️ by the Aurora team.
752
+ Built by the Aurora team.
package/bin/aurora.exe CHANGED
Binary file
package/package.json CHANGED
@@ -1,5 +1,5 @@
1
1
  {
2
- "version": "1.0.30",
2
+ "version": "1.0.32",
3
3
  "author": "Aurora Gateway",
4
4
  "license": "Apache-2.0",
5
5
  "files": [