Skip to content

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

docs: add Atlas Cloud as a custom OpenAI-compatible provider (refs #332)

Sergey Kozyrenkoebe0618dee4b
diff --git a/README.md b/README.md
index 06d1f4f0..fbf70109 100644
--- a/README.md
+++ b/README.md
@@ -72,7 +72,7 @@ You can watch the video **PentAGI overview**:
- Persistent Storage. All commands and outputs are stored in PostgreSQL with [pgvector](https://hub.docker.com/r/vxcontrol/pgvector) extension.
- Scalable Architecture. Microservices-based design supporting horizontal scaling.
- Self-Hosted Solution. Complete control over your deployment and data.
-- Flexible Authentication. Support for 10+ LLM providers ([OpenAI](https://platform.openai.com/), [Anthropic](https://www.anthropic.com/), [Google AI/Gemini](https://ai.google.dev/), [AWS Bedrock](https://aws.amazon.com/bedrock/), [Ollama](https://ollama.com/), [DeepSeek](https://www.deepseek.com/en/), [GLM](https://z.ai/), [Kimi](https://platform.moonshot.ai/), [Qwen](https://www.alibabacloud.com/en/), Custom) plus aggregators ([OpenRouter](https://openrouter.ai/), [DeepInfra](https://deepinfra.com/)). For production local deployments, see our [vLLM + Qwen3.5-27B-FP8 guide](examples/guides/vllm-qwen35-27b-fp8.md).
+- Flexible Authentication. Support for 10+ LLM providers ([OpenAI](https://platform.openai.com/), [Anthropic](https://www.anthropic.com/), [Google AI/Gemini](https://ai.google.dev/), [AWS Bedrock](https://aws.amazon.com/bedrock/), [Ollama](https://ollama.com/), [DeepSeek](https://www.deepseek.com/en/), [GLM](https://z.ai/), [Kimi](https://platform.moonshot.ai/), [Qwen](https://www.alibabacloud.com/en/), Custom) plus aggregators ([OpenRouter](https://openrouter.ai/), [DeepInfra](https://deepinfra.com/), [Atlas Cloud](https://www.atlascloud.ai/)). For production local deployments, see our [vLLM + Qwen3.5-27B-FP8 guide](examples/guides/vllm-qwen35-27b-fp8.md).
- API Token Authentication. Secure Bearer token system for programmatic access to REST and GraphQL APIs.
- Quick Deployment. Easy setup through [Docker Compose](https://docs.docker.com/compose/) with comprehensive environment configuration.
@@ -3000,10 +3000,10 @@ docker exec -it pentagi /opt/pentagi/bin/ctester -config /opt/pentagi/conf/ollam
To use these configurations, your `.env` file only needs to contain:
```
-LLM_SERVER_URL=https://openrouter.ai/api/v1 # or https://api.deepinfra.com/v1/openai or https://api.openai.com/v1 or https://api.novita.ai/openai
+LLM_SERVER_URL=https://openrouter.ai/api/v1 # or https://api.deepinfra.com/v1/openai or https://api.openai.com/v1 or https://api.novita.ai/openai or https://api.atlascloud.ai/v1
LLM_SERVER_KEY=your_api_key
LLM_SERVER_MODEL= # Leave empty, as models are specified in the config
-LLM_SERVER_CONFIG_PATH=/opt/pentagi/conf/openrouter.provider.yml # or deepinfra.provider.ymll or custom-openai.provider.yml or novita.provider.yml
+LLM_SERVER_CONFIG_PATH=/opt/pentagi/conf/openrouter.provider.yml # or deepinfra.provider.yml or custom-openai.provider.yml or novita.provider.yml or atlas.provider.yml
LLM_SERVER_PROVIDER= # Provider name for LiteLLM proxy (e.g., openrouter, deepseek, moonshot, novita)
LLM_SERVER_LEGACY_REASONING=false # Controls reasoning format, for OpenAI must be true (default: false)
LLM_SERVER_PRESERVE_REASONING=false # Preserve reasoning content in multi-turn conversations (required by Moonshot, default: false)
diff --git a/examples/configs/atlas.provider.yml b/examples/configs/atlas.provider.yml
new file mode 100644
index 00000000..eca5e52e
--- /dev/null
+++ b/examples/configs/atlas.provider.yml
@@ -0,0 +1,119 @@
+simple:
+ model: "Qwen/Qwen3-Next-80B-A3B-Instruct"
+ temperature: 0.7
+ top_p: 0.95
+ n: 1
+ max_tokens: 4000
+ price:
+ input: 0.14
+ output: 1.4
+
+simple_json:
+ model: "Qwen/Qwen3-Next-80B-A3B-Instruct"
+ temperature: 0.7
+ top_p: 1.0
+ n: 1
+ max_tokens: 4000
+ json: true
+ price:
+ input: 0.14
+ output: 1.4
+
+primary_agent:
+ model: "moonshotai/kimi-k2.6"
+ temperature: 1.0
+ n: 1
+ max_tokens: 6000
+ price:
+ input: 0.4
+ output: 2.0
+
+assistant:
+ model: "moonshotai/kimi-k2.6"
+ temperature: 1.0
+ n: 1
+ max_tokens: 8000
+ price:
+ input: 0.4
+ output: 2.0
+
+generator:
+ model: "deepseek-ai/deepseek-v4-pro"
+ temperature: 1.0
+ n: 1
+ max_tokens: 8000
+ price:
+ input: 1.0
+ output: 3.0
+
+refiner:
+ model: "deepseek-ai/deepseek-r1-0528"
+ temperature: 1.0
+ n: 1
+ max_tokens: 8000
+ price:
+ input: 1.0
+ output: 3.0
+
+adviser:
+ model: "deepseek-ai/deepseek-v4-pro"
+ temperature: 1.0
+ n: 1
+ max_tokens: 4000
+ price:
+ input: 1.0
+ output: 3.0
+
+reflector:
+ model: "Qwen/Qwen3-Next-80B-A3B-Instruct"
+ temperature: 1.0
+ n: 1
+ max_tokens: 4000
+ price:
+ input: 0.14
+ output: 1.4
+
+searcher:
+ model: "qwen/qwen3-32b"
+ temperature: 1.0
+ n: 1
+ max_tokens: 4000
+ price:
+ input: 0.1
+ output: 0.3
+
+enricher:
+ model: "qwen/qwen3-32b"
+ temperature: 1.0
+ n: 1
+ max_tokens: 6000
+ price:
+ input: 0.1
+ output: 0.3
+
+coder:
+ model: "anthropic/claude-sonnet-4.6"
+ temperature: 1.0
+ n: 1
+ max_tokens: 8000
+ price:
+ input: 3.3
+ output: 16.5
+
+installer:
+ model: "google/gemini-3.5-flash"
+ temperature: 1.0
+ n: 1
+ max_tokens: 6000
+ price:
+ input: 0.3
+ output: 2.5
+
+pentester:
+ model: "moonshotai/kimi-k2.6"
+ temperature: 1.0
+ n: 1
+ max_tokens: 6000
+ price:
+ input: 0.4
+ output: 2.0