@@ -162,18 +162,19 @@ All messages (web UI chat, Telegram, trigger-initiated chats) flow through the s
162162``` bash
163163git clone https://github.com/ownpilot/ownpilot.git
164164cd ownpilot
165- cp .env.example .env
166165
167- # Start OwnPilot + PostgreSQL
166+ # Start OwnPilot + PostgreSQL (uses defaults, no .env needed)
168167docker compose --profile postgres up -d
169168
170169# UI + API: http://localhost:8080
171170```
172171
173- Or use the pre-built image :
172+ To customize settings (auth, Telegram, etc.), copy and edit ` .env ` before starting :
174173
175174``` bash
176- docker pull ghcr.io/ownpilot/ownpilot:latest
175+ cp .env.example .env
176+ # Edit .env — docker-compose.yml defaults match .env.example
177+ docker compose --profile postgres up -d
177178```
178179
179180### From Source
@@ -182,7 +183,7 @@ docker pull ghcr.io/ownpilot/ownpilot:latest
182183
183184- ** Node.js** >= 22.0.0
184185- ** pnpm** >= 10.0.0
185- - ** PostgreSQL** (via Docker or native)
186+ - ** PostgreSQL** 16+ (via Docker Compose or native install )
186187
187188#### Setup
188189
@@ -194,8 +195,10 @@ pnpm install
194195
195196# Configure
196197cp .env.example .env
197- # Edit .env with database connection details
198- # AI provider API keys are configured via the Config Center UI after setup
198+ # Edit .env if needed (defaults work with docker compose PostgreSQL)
199+
200+ # Start PostgreSQL (if you don't have one already)
201+ docker compose --profile postgres up -d
199202
200203# Start development (gateway + ui)
201204pnpm dev
@@ -204,6 +207,8 @@ pnpm dev
204207# API: http://localhost:8080
205208```
206209
210+ AI provider API keys are configured via the ** Config Center UI** (Settings page) after setup.
211+
207212### Configuration via CLI
208213
209214``` bash
@@ -448,23 +453,35 @@ All API keys are managed via the **Config Center UI** (Settings page) or the `ow
448453
449454### Supported Providers
450455
451- | Provider | Integration Type | Key Models |
452- | ------------------ | ------------------------------ | --------------------------------------------------------------------- |
453- | ** OpenAI** | Native | GPT-4o, GPT-4o-mini, o1, o3-mini |
454- | ** Anthropic** | Native (with prompt caching) | Claude Sonnet 4.6, Claude Opus 4.6, Claude 3.7 Sonnet, Claude 3 Haiku |
455- | ** Google** | Native (with OAuth) | Gemini 2.0 Flash, Gemini 1.5 Pro |
456- | ** Zhipu AI** | Native | GLM-4 |
457- | ** Together AI** | Aggregator (OpenAI-compatible) | Llama 3.3 70B, DeepSeek R1/V3, Qwen 2.5 Coder |
458- | ** Groq** | Aggregator (ultra-fast LPU) | Llama 3.3 70B, Mixtral 8x7B, Gemma 2 9B |
459- | ** Fireworks AI** | Aggregator | Llama 3.3 70B, Qwen 2.5, FLUX image models |
460- | ** DeepInfra** | Aggregator | Serverless open-source inference |
461- | ** OpenRouter** | Aggregator | Unified API for all providers |
462- | ** Perplexity** | Aggregator | Sonar Pro, Sonar Reasoning (with citations) |
463- | ** Cerebras** | Aggregator (fastest inference) | Llama 3.3 70B, Llama 3.1 8B |
464- | ** fal.ai** | Aggregator (image/video) | FLUX Pro/Dev/Schnell, Stable Diffusion, Recraft v3 |
465- | ** Ollama** | Local (auto-discovered) | Any GGUF model |
466- | ** LM Studio** | Local (auto-discovered) | Any loaded model |
467- | ** LocalAI / vLLM** | Local | Self-hosted models |
456+ ** 96 providers** with auto-synced model catalogs from [ models.dev] ( https://models.dev ) . Key providers:
457+
458+ | Provider | Integration Type | Key Models |
459+ | --- | --- | --- |
460+ | ** OpenAI** | Native | GPT-5.3 Codex, GPT-5.2, GPT-5.1, o4-mini, o3 |
461+ | ** Anthropic** | Native (prompt caching) | Claude Sonnet 4.6, Claude Opus 4.6, Claude Sonnet 4.5, Claude Haiku 4.5 |
462+ | ** Google** | Native | Gemini 3.1 Pro, Gemini 3 Flash, Gemini 2.5 Flash/Pro |
463+ | ** xAI** | Native | Grok 4.1 Fast, Grok 4, Grok 3 |
464+ | ** DeepSeek** | Native | DeepSeek Chat, DeepSeek Reasoner |
465+ | ** Mistral** | Native | Devstral 2, Mistral Medium 3.1, Mistral Large 3, Codestral |
466+ | ** Zhipu AI** | Native | GLM-5, GLM-4.7, GLM-4.6 |
467+ | ** Cohere** | Native | Command A, Command A Reasoning, Command R+ |
468+ | ** Together AI** | Aggregator | Qwen3.5 397B, GLM-5, Kimi K2.5, DeepSeek V3.1 |
469+ | ** Groq** | Aggregator (LPU) | Kimi K2, GPT OSS 120B, Llama 4 Scout, Qwen3 32B |
470+ | ** Fireworks AI** | Aggregator | MiniMax-M2.5, GLM 5, Kimi K2.5, DeepSeek V3.2 |
471+ | ** DeepInfra** | Aggregator | Kimi K2.5, GLM-4.7, DeepSeek-V3.2, Qwen3 Coder |
472+ | ** OpenRouter** | Aggregator (161+ models) | Unified API for all providers |
473+ | ** Perplexity** | Aggregator | Sonar Deep Research, Sonar Pro, Sonar Reasoning Pro |
474+ | ** Cerebras** | Aggregator (fastest) | GLM-4.7, GPT OSS 120B, Qwen 3 235B |
475+ | ** NVIDIA** | Aggregator (65+ models) | GLM5, Kimi K2.5, DeepSeek V3.2, Nemotron |
476+ | ** Amazon Bedrock** | Cloud (96+ models) | Claude 4.6, DeepSeek-V3.2, Kimi K2.5, Nova Pro |
477+ | ** Azure** | Cloud (85+ models) | GPT-5.2, Claude 4.6, DeepSeek-V3.2, Grok 4 |
478+ | ** GitHub Models** | Cloud | GPT-4.1, DeepSeek-R1, Llama 4, Mistral |
479+ | ** Hugging Face** | Aggregator | MiniMax-M2.5, GLM-5, Qwen3.5, DeepSeek-V3.2 |
480+ | ** SiliconFlow** | Aggregator (66+ models) | GLM-5, Kimi K2.5, DeepSeek V3.2, Qwen3 VL |
481+ | ** Novita AI** | Aggregator (80+ models) | Qwen3.5, GLM-5, Kimi K2.5, ERNIE-4.5 |
482+ | ** Nebius** | Aggregator (45+ models) | DeepSeek-V3.2, GLM-4.7, Qwen3, FLUX |
483+ | ** Ollama** | Local | qwen3.5, minimax-m2.5, glm-5, kimi-k2.5 |
484+ | ** LM Studio** | Local | GPT OSS 20B, Qwen3 30B, Qwen3 Coder 30B |
468485
469486Any OpenAI-compatible endpoint can be added as a custom provider.
470487
@@ -1015,7 +1032,7 @@ NODE_ENV=development
10151032POSTGRES_HOST=localhost
10161033POSTGRES_PORT=25432
10171034POSTGRES_USER=ownpilot
1018- POSTGRES_PASSWORD=ownpilot_secret
1035+ POSTGRES_PASSWORD=ownpilot_secret # Change in production
10191036POSTGRES_DB=ownpilot
10201037# POSTGRES_POOL_SIZE=10
10211038# DB_VERBOSE=false
0 commit comments