feat: add Atlas Cloud as an OpenAI-compatible LLM provider (#2362)

lucaszhu-hue · claude · web-flow · commit f8d277697dc3 · 2026-06-23T13:03:16.000+02:00
Atlas Cloud (https://www.atlascloud.ai) exposes an OpenAI-compatible chat/completions endpoint, so it slots into the existing OpenAICompatibleLLM path exactly like deepseek / zai / opencode-go. Set `HINDSIGHT_API_LLM_PROVIDER=atlas` to route fact extraction, reflection and consolidation through Atlas Cloud. The base URL defaults to https://api.atlascloud.ai/v1 and the default model is deepseek-ai/deepseek-v4-pro (a reasoning model — give it enough max_tokens, >= 512). Changes: - engine/llm_wrapper.py: register "atlas" in create_llm_provider(), LLMProvider.valid_providers, and the default base_url map - engine/providers/openai_compatible_llm.py: register "atlas" in valid_providers, default base_url, and the API-key-required check - config.py: PROVIDER_DEFAULT_MODELS["atlas"] = deepseek-ai/deepseek-v4-pro - hindsight-embed control center: add Atlas Cloud to the provider wizard - docs: add Atlas Cloud to llmProviders.json (drives the providers grid and table) and a config example in developer/models.mdx - README + .env.example: document the new provider Verified end-to-end: instantiated the atlas provider through Hindsight's own create_llm_provider() and made a live call() to deepseek-ai/deepseek-v4-pro (HTTP 200, valid content + token usage). Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
diff --git a/.env.example b/.env.example
@@ -2,7 +2,7 @@
 # Copy this file to .env and fill in your values
 
 # LLM Configuration (Required)
-# Supported providers: openai, groq, ollama, gemini, anthropic, lmstudio, vertexai, minimax, deepseek, zai, volcano
+# Supported providers: openai, groq, ollama, gemini, anthropic, lmstudio, vertexai, minimax, deepseek, zai, atlas, volcano
 HINDSIGHT_API_LLM_PROVIDER=openai
 HINDSIGHT_API_LLM_API_KEY=your-api-key-here
 HINDSIGHT_API_LLM_MODEL=gpt-4o-mini
@@ -37,6 +37,11 @@ HINDSIGHT_API_LLM_BASE_URL=https://api.openai.com/v1
 # HINDSIGHT_API_LLM_API_KEY=your-zai-api-key
 # HINDSIGHT_API_LLM_MODEL=glm-4.5-flash  # or glm-4.5-air for the paid tier
 
+# Example: Atlas Cloud configuration (OpenAI-compatible, https://www.atlascloud.ai)
+# HINDSIGHT_API_LLM_PROVIDER=atlas
+# HINDSIGHT_API_LLM_API_KEY=your-atlascloud-api-key
+# HINDSIGHT_API_LLM_MODEL=deepseek-ai/deepseek-v4-pro  # reasoning model; also Qwen / GLM / Kimi / MiniMax, etc.
+
 # Example: LM Studio local configuration (Qwen 2.5 32B recommended)
 # HINDSIGHT_API_LLM_PROVIDER=lmstudio
 # HINDSIGHT_API_LLM_API_KEY=lmstudio
diff --git a/README.md b/README.md
@@ -16,6 +16,42 @@
 
 ---
 
+### Powered by Atlas Cloud (OpenAI-compatible)
+
+<p align="center">
+  <a href="https://www.atlascloud.ai/?utm_source=github&utm_medium=link&utm_campaign=hindsight">
+    <img src="./hindsight-docs/static/img/atlas-cloud-logo.png" alt="Atlas Cloud" width="200">
+  </a>
+</p>
+
+> 🎁 **[Atlas Cloud](https://www.atlascloud.ai/?utm_source=github&utm_medium=link&utm_campaign=hindsight)** is a full-modal, OpenAI-compatible AI inference platform — plug it in as a drop-in LLM backend for Hindsight's fact extraction, reflection and consolidation, with one API for DeepSeek, Qwen, GLM, Kimi, MiniMax and more. No multi-vendor setup needed.
+> Budget-friendly: [coding plan](https://www.atlascloud.ai/console/coding-plan)
+
+```bash
+export HINDSIGHT_API_LLM_PROVIDER=atlas
+export HINDSIGHT_API_LLM_API_KEY=your-atlascloud-api-key   # base_url defaults to https://api.atlascloud.ai/v1
+export HINDSIGHT_API_LLM_MODEL=deepseek-ai/deepseek-v4-pro
+```
+
+`deepseek-ai/deepseek-v4-pro` is a reasoning model — give it enough `max_tokens` (>= 512).
+
+<details>
+<summary>All Atlas Cloud chat models (59)</summary>
+
+- **Anthropic (Claude):** `anthropic/claude-haiku-4.5-20251001`, `anthropic/claude-opus-4.8`, `anthropic/claude-sonnet-4.6`
+- **OpenAI (GPT):** `openai/gpt-5.4`, `openai/gpt-5.5`
+- **Google (Gemini):** `google/gemini-3.1-flash-lite`, `google/gemini-3.1-pro-preview`, `google/gemini-3.5-flash`
+- **Alibaba Qwen:** `qwen/qwen2.5-7b-instruct`, `Qwen/Qwen3-235B-A22B-Instruct-2507`, `qwen/qwen3-235b-a22b-thinking-2507`, `qwen/qwen3-30b-a3b`, `Qwen/Qwen3-30B-A3B-Instruct-2507`, `qwen/qwen3-30b-a3b-thinking-2507`, `qwen/qwen3-32b`, `qwen/qwen3-8b`, `Qwen/Qwen3-Coder`, `qwen/qwen3-coder-next`, `qwen/qwen3-max-2026-01-23`, `Qwen/Qwen3-Next-80B-A3B-Instruct`, `Qwen/Qwen3-Next-80B-A3B-Thinking`, `Qwen/Qwen3-VL-235B-A22B-Instruct`, `qwen/qwen3-vl-235b-a22b-thinking`, `qwen/qwen3-vl-30b-a3b-instruct`, `qwen/qwen3-vl-30b-a3b-thinking`, `qwen/qwen3-vl-8b-instruct`, `qwen/qwen3.5-122b-a10b`, `qwen/qwen3.5-27b`, `qwen/qwen3.5-35b-a3b`, `qwen/qwen3.5-397b-a17b`, `qwen/qwen3.6-35b-a3b`, `qwen/qwen3.6-plus`
+- **DeepSeek:** `deepseek-ai/deepseek-ocr`, `deepseek-ai/deepseek-r1-0528`, `deepseek-ai/DeepSeek-V3-0324`, `deepseek-ai/DeepSeek-V3.1`, `deepseek-ai/DeepSeek-V3.1-Terminus`, `deepseek-ai/deepseek-v3.2`, `deepseek-ai/DeepSeek-V3.2-Exp`, `deepseek-ai/deepseek-v4-flash`, `deepseek-ai/deepseek-v4-pro`
+- **Moonshot (Kimi):** `moonshotai/Kimi-K2-Instruct`, `moonshotai/Kimi-K2-Instruct-0905`, `moonshotai/Kimi-K2-Thinking`, `moonshotai/kimi-k2.5`, `moonshotai/kimi-k2.6`
+- **Zhipu GLM:** `zai-org/GLM-4.6`, `zai-org/glm-4.7`, `zai-org/glm-5`, `zai-org/glm-5-turbo`, `zai-org/glm-5.1`, `zai-org/glm-5v-turbo`
+- **MiniMax:** `MiniMaxAI/MiniMax-M2`, `minimaxai/minimax-m2.1`, `minimaxai/minimax-m2.5`, `minimaxai/minimax-m2.7`
+- **xAI:** `xai/grok-4.3`
+- **Kuaishou KAT:** `kwaipilot/kat-coder-pro-v2`
+- **Other:** `owl`
+
+</details>
+
 ## What is Hindsight?
 
 Hindsight™ is an agent memory system built to create smarter agents that learn over time. Most agent memory systems focus on recalling conversation history. Hindsight is focused on making agents that learn, not just remember.
@@ -70,7 +106,7 @@ docker run -it --pull always --name hindsight --restart unless-stopped -p 8888:8
 >API: http://localhost:8888
 >UI: http://localhost:9999
 
-You can modify the LLM provider by setting `HINDSIGHT_API_LLM_PROVIDER`. Valid options are `openai`, `anthropic`, `gemini`, `groq`, `ollama`, `lmstudio`, and `minimax`. The documentation provides more details on [supported models](https://hindsight.vectorize.io/developer/models).
+You can modify the LLM provider by setting `HINDSIGHT_API_LLM_PROVIDER`. Valid options are `openai`, `anthropic`, `gemini`, `groq`, `ollama`, `lmstudio`, `minimax`, and `atlas` ([Atlas Cloud](https://www.atlascloud.ai/?utm_source=github&utm_medium=link&utm_campaign=hindsight)). The documentation provides more details on [supported models](https://hindsight.vectorize.io/developer/models).
 
 
 
diff --git a/hindsight-api-slim/hindsight_api/config.py b/hindsight-api-slim/hindsight_api/config.py
@@ -618,6 +618,7 @@ def parse_gemini_service_tier(value: str | None) -> str | None:
     "deepseek": "deepseek-v4-flash",
     "zai": "glm-4.5-flash",
     "opencode-go": "deepseek-v4-flash",
+    "atlas": "deepseek-ai/deepseek-v4-pro",
     "ollama": "gemma3:12b",
     "ollama-cloud": "gemma3:12b",
     "llamacpp": "gemma-4-e2b-it",
diff --git a/hindsight-api-slim/hindsight_api/engine/llm_wrapper.py b/hindsight-api-slim/hindsight_api/engine/llm_wrapper.py
@@ -466,6 +466,7 @@ def create_llm_provider(
         "openrouter",
         "zai",
         "opencode-go",
+        "atlas",
     ):
         return OpenAICompatibleLLM(
             provider=provider,
@@ -588,6 +589,7 @@ def __init__(
             "openrouter",
             "zai",
             "opencode-go",
+            "atlas",
             "fireworks",
             "nous",
         ]
@@ -614,6 +616,8 @@ def __init__(
                 self.base_url = "https://api.z.ai/api/coding/paas/v4"
             elif self.provider == "opencode-go":
                 self.base_url = "https://opencode.ai/zen/go/v1"
+            elif self.provider == "atlas":
+                self.base_url = "https://api.atlascloud.ai/v1"
             elif self.provider == "nous":
                 self.base_url = "https://inference-api.nousresearch.com/v1"
 
diff --git a/hindsight-api-slim/hindsight_api/engine/providers/openai_compatible_llm.py b/hindsight-api-slim/hindsight_api/engine/providers/openai_compatible_llm.py
@@ -451,6 +451,7 @@ def __init__(
             "openrouter",
             "zai",
             "opencode-go",
+            "atlas",
             "fireworks",
         ]
         if self.provider not in valid_providers:
@@ -476,6 +477,8 @@ def __init__(
                 self.base_url = "https://api.z.ai/api/coding/paas/v4"
             elif self.provider == "opencode-go":
                 self.base_url = "https://opencode.ai/zen/go/v1"
+            elif self.provider == "atlas":
+                self.base_url = "https://api.atlascloud.ai/v1"
             elif self.provider == "fireworks":
                 # OpenAI-compatible inference host (online path). The batch API
                 # lives on a separate control-plane host — see FireworksLLM.
@@ -496,6 +499,7 @@ def __init__(
                 "openrouter",
                 "zai",
                 "opencode-go",
+                "atlas",
                 "ollama-cloud",
             )
             and not self.api_key
diff --git a/hindsight-docs/docs/developer/models.mdx b/hindsight-docs/docs/developer/models.mdx
@@ -208,6 +208,11 @@ export HINDSIGHT_API_LLM_PROVIDER=opencode-go
 export HINDSIGHT_API_LLM_API_KEY=your-opencode-go-api-key
 export HINDSIGHT_API_LLM_MODEL=deepseek-v4-flash
 
+# Atlas Cloud (OpenAI-compatible, https://www.atlascloud.ai)
+export HINDSIGHT_API_LLM_PROVIDER=atlas
+export HINDSIGHT_API_LLM_API_KEY=your-atlascloud-api-key  # base_url defaults to https://api.atlascloud.ai/v1
+export HINDSIGHT_API_LLM_MODEL=deepseek-ai/deepseek-v4-pro  # reasoning model; also Qwen / GLM / Kimi / MiniMax, etc.
+
 # Nous Portal (OpenAI-compatible; no API key — uses your `hermes portal` login)
 export HINDSIGHT_API_LLM_PROVIDER=nous
 export HINDSIGHT_API_LLM_MODEL=deepseek/deepseek-v4-flash  # any Nous-hosted slug
diff --git a/hindsight-docs/src/data/llmProviders.json b/hindsight-docs/src/data/llmProviders.json
@@ -12,6 +12,7 @@
   {"id": "deepseek",      "label": "DeepSeek",          "iconKey": "brain",              "defaultModel": "deepseek-v4-flash"},
   {"id": "zai",           "label": "z.ai",              "iconKey": "sparkles",           "defaultModel": "glm-4.5-flash"},
   {"id": "opencode-go",   "label": "opencode-go",       "iconKey": "openai-compatible",  "defaultModel": "deepseek-v4-flash"},
+  {"id": "atlas",         "label": "Atlas Cloud",       "iconKey": "openai-compatible",  "defaultModel": "deepseek-ai/deepseek-v4-pro"},
   {"id": "volcano",       "label": "Volcano Engine",    "iconKey": "zap",                "defaultModel": "doubao-pro-32k"},
   {"id": "openrouter",    "label": "OpenRouter",        "iconKey": "globe",              "defaultModel": "qwen/qwen3.5-9b"},
   {"id": "openai-codex",  "label": "OpenAI Codex",      "iconKey": "openai",             "defaultModel": "gpt-5.4-mini"},
diff --git a/hindsight-docs/static/img/atlas-cloud-logo.png b/hindsight-docs/static/img/atlas-cloud-logo.png
diff --git a/hindsight-embed/hindsight_embed/control_center/providers.py b/hindsight-embed/hindsight_embed/control_center/providers.py
@@ -30,5 +30,6 @@ class ProviderInfo:
     ProviderInfo("deepseek", "DeepSeek", needs_api_key=True),
     ProviderInfo("minimax", "MiniMax", needs_api_key=True),
     ProviderInfo("zai", "Z.ai", needs_api_key=True),
+    ProviderInfo("atlas", "Atlas Cloud", needs_api_key=True, default_base_url="https://api.atlascloud.ai/v1"),
     ProviderInfo("volcano", "Volcano", needs_api_key=True),
 )

Original file line number	Diff line number	Diff line change
`@@ -30,5 +30,6 @@ class ProviderInfo:`
`30`	`30`	`ProviderInfo("deepseek", "DeepSeek", needs_api_key=True),`
`31`	`31`	`ProviderInfo("minimax", "MiniMax", needs_api_key=True),`
`32`	`32`	`ProviderInfo("zai", "Z.ai", needs_api_key=True),`
	`33`	`+ ProviderInfo("atlas", "Atlas Cloud", needs_api_key=True, default_base_url="https://api.atlascloud.ai/v1"),`
`33`	`34`	`ProviderInfo("volcano", "Volcano", needs_api_key=True),`
`34`	`35`	`)`