Add guides for 7 merged Eden AI integrations

README.md

@@ -15,6 +15,13 @@ Each guide walks through installation, configuration, and model selection so you
 | OpenClaw | [openclaw.md](./openclaw.md) | [YouTube](https://youtu.be/HxIAYOQT90Q) | [edenai.co/integrations/openclaw](https://www.edenai.co/integrations/openclaw) |
 | OpenCode | [opencode.md](./opencode.md) | [YouTube](https://youtu.be/OYHRY5rblz0) | [edenai.co/integrations/opencode](https://www.edenai.co/integrations/opencode) |
 | Cline | [cline.md](./cline.md) | [YouTube](https://youtu.be/_M8PwHSwgMQ) | [edenai.co/integrations/cline](https://www.edenai.co/integrations/cline) |
+| aisuite | [aisuite.md](./aisuite.md) | — | — |
+| any-llm | [any-llm.md](./any-llm.md) | — | — |
+| Atomic Agents | [atomic-agents.md](./atomic-agents.md) | — | — |
+| Haystack | [haystack.md](./haystack.md) | — | — |
+| Lynkr | [lynkr.md](./lynkr.md) | — | — |
+| Open Code Review | [open-code-review.md](./open-code-review.md) | — | — |
+| open-connector | [open-connector.md](./open-connector.md) | — | — |
 
 More integrations are added regularly. Open an issue if there's a tool you'd like us to cover.
 

aisuite.md

@@ -0,0 +1,95 @@
+# aisuite + Eden AI
+
+[aisuite](https://github.com/andrewyng/aisuite) ships with a built-in **Eden AI** provider, so you can route any aisuite call through **500+ models** with smart routing, automatic fallbacks, and a single API key.
+
+> Get your Eden AI key at [app.edenai.run](https://app.edenai.run/) → **API Keys**.
+
+---
+
+## 1. Install
+
+The Eden AI provider is OpenAI-compatible and reuses the `openai` client, so install aisuite with the OpenAI extra:
+
+```bash
+pip install aisuite openai
+```
+
+## 2. Set your Eden AI key
+
+The provider reads the key from the `EDENAI_API_KEY` environment variable:
+
+```bash
+export EDENAI_API_KEY="your-eden-ai-key"
+```
+
+Never hardcode the key in your source. The base URL (`https://api.edenai.run/v3`) is built into the provider — you don't need to set it.
+
+## 3. Call Eden AI through aisuite
+
+Select Eden AI with the `edenai:` provider prefix, followed by a `provider/model` string:
+
+```python
+import aisuite as ai
+
+client = ai.Client()
+
+provider = "edenai"
+model_id = "anthropic/claude-sonnet-4-5"
+
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "What's the weather like in San Francisco?"},
+]
+
+response = client.chat.completions.create(
+    model=f"{provider}:{model_id}",
+    messages=messages,
+)
+
+print(response.choices[0].message.content)
+```
+
+The provider is auto-discovered — no manual registration needed.
+
+---
+
+## Choosing a model
+
+The aisuite model string nests Eden AI's own `provider/model` after the `edenai:` prefix:
+
+| aisuite model string | Best for |
+|---|---|
+| `edenai:@edenai` | **Default** — smart routing across all providers |
+| `edenai:anthropic/claude-sonnet-4-5` | Balanced reasoning |
+| `edenai:openai/gpt-4o-mini` | Fast and cheap |
+| `edenai:mistral/mistral-small-latest` | European, cost-efficient |
+
+`@edenai` is Eden AI's **smart router** — it picks the best-performing model per request based on quality, latency, cost and live provider health. [How smart routing works →](https://www.edenai.co/docs/v3/llms/smart-routing)
+
+Browse the full catalog at [app.edenai.run/models](https://app.edenai.run/models).
+
+## Troubleshooting
+
+### `ValueError: ... API key`
+Make sure `EDENAI_API_KEY` is exported in the environment where your script runs.
+
+### `401 Unauthorized`
+Verify your Eden AI key — grab a fresh one at [app.edenai.run → API Keys](https://app.edenai.run/).
+
+### `model not found`
+The Eden AI part of the string must use the `provider/model` format (or `@edenai` for the smart router). No bare model names.
+
+## Uninstall
+
+```bash
+pip uninstall aisuite
+```
+
+---
+
+## Next steps
+
+- [Smart routing](https://www.edenai.co/docs/v3/llms/smart-routing)
+- [Fallbacks](https://www.edenai.co/docs/v3/llms/fallback)
+- [Eden AI pricing](https://www.edenai.co/pricing)
+- [aisuite GitHub](https://github.com/andrewyng/aisuite)

any-llm.md

@@ -0,0 +1,87 @@
+# any-llm + Eden AI
+
+[any-llm](https://github.com/mozilla-ai/any-llm) ships with a built-in **Eden AI** provider, so you can route any-llm calls through **500+ models** with smart routing, automatic fallbacks, and a single API key.
+
+> Get your Eden AI key at [app.edenai.run](https://app.edenai.run/) → **API Keys**.
+
+---
+
+## 1. Install
+
+Install any-llm with the `edenai` extra:
+
+```bash
+pip install 'any-llm-sdk[edenai]'
+```
+
+## 2. Set your Eden AI key
+
+The provider reads the key from the `EDENAI_API_KEY` environment variable:
+
+```bash
+export EDENAI_API_KEY="your-eden-ai-key"
+```
+
+Never hardcode the key. The base URL defaults to `https://api.edenai.run/v3`; override it with `EDENAI_API_BASE` only if you use a regional endpoint.
+
+## 3. Call Eden AI through any-llm
+
+Prefix the model with the `edenai/` provider id, followed by Eden AI's `provider/model` string:
+
+```python
+from any_llm import completion
+
+response = completion(
+    model="edenai/openai/gpt-4o-mini",
+    messages=[{"role": "user", "content": "Hello"}],
+)
+
+print(response.choices[0].message.content)
+```
+
+Streaming, embeddings, and moderation are supported through the same provider.
+
+---
+
+## Choosing a model
+
+The any-llm model string nests Eden AI's own `provider/model` after the `edenai/` prefix:
+
+| any-llm model string | Best for |
+|---|---|
+| `edenai/@edenai` | **Default** — smart routing across all providers |
+| `edenai/anthropic/claude-sonnet-4-5` | Balanced reasoning |
+| `edenai/openai/gpt-4o-mini` | Fast and cheap |
+| `edenai/mistral/mistral-small-latest` | European, cost-efficient |
+
+For embeddings, use an embedding model such as `edenai/openai/text-embedding-3-small`.
+
+`@edenai` is Eden AI's **smart router** — it picks the best model per request based on quality, latency, cost and live provider health. [How smart routing works →](https://www.edenai.co/docs/v3/llms/smart-routing)
+
+Browse the full catalog at [app.edenai.run/models](https://app.edenai.run/models).
+
+## Troubleshooting
+
+### `401 Unauthorized`
+Verify your Eden AI key — grab a fresh one at [app.edenai.run → API Keys](https://app.edenai.run/).
+
+### `model not found`
+The Eden AI part of the string must use the `provider/model` format (or `@edenai` for the smart router). No bare model names.
+
+### Reasoning field is empty
+Eden AI inlines reasoning into the message content rather than a separate field, so any-llm's dedicated reasoning output is not populated for this provider.
+
+## Uninstall
+
+```bash
+pip uninstall any-llm-sdk
+```
+
+---
+
+## Next steps
+
+- [Smart routing](https://www.edenai.co/docs/v3/llms/smart-routing)
+- [Fallbacks](https://www.edenai.co/docs/v3/llms/fallback)
+- [Eden AI pricing](https://www.edenai.co/pricing)
+- [any-llm GitHub](https://github.com/mozilla-ai/any-llm)

atomic-agents.md

@@ -0,0 +1,85 @@
+# Atomic Agents + Eden AI
+
+[Atomic Agents](https://github.com/Eigenwise/atomic-agents) works with **Eden AI** out of the box through its OpenAI-compatible client, so you can build agents on top of **500+ models** with smart routing, automatic fallbacks, and a single API key.
+
+> Get your Eden AI key at [app.edenai.run](https://app.edenai.run/) → **API Keys**.
+
+---
+
+## 1. Install
+
+Eden AI reuses the OpenAI client and Instructor that Atomic Agents already relies on:
+
+```bash
+pip install atomic-agents openai instructor
+```
+
+## 2. Set your Eden AI key
+
+```bash
+export EDENAI_API_KEY="your-eden-ai-key"
+```
+
+Never hardcode the key.
+
+## 3. Point the client at Eden AI
+
+Create an OpenAI client with Eden AI's base URL and wrap it with Instructor — exactly the pattern used for other OpenAI-compatible providers:
+
+```python
+import os
+import instructor
+from openai import OpenAI
+
+client = instructor.from_openai(
+    OpenAI(
+        base_url="https://api.edenai.run/v3",
+        api_key=os.getenv("EDENAI_API_KEY"),
+    )
+)
+
+model = "openai/gpt-4o-mini"
+model_api_parameters = {"max_tokens": 2048}
+```
+
+Pass this `client` and `model` to your `BaseAgent` (or agent config) as usual. Both Instructor `TOOLS` and `JSON` modes work.
+
+---
+
+## Choosing a model
+
+Eden AI model ids use the `provider/model` format:
+
+| Model | Best for |
+|---|---|
+| `@edenai` | **Default** — smart routing across all providers |
+| `anthropic/claude-sonnet-4-5` | Balanced reasoning |
+| `anthropic/claude-haiku-4-5` | Fast and cheap |
+| `mistral/mistral-small-latest` | European, cost-efficient |
+
+`@edenai` is Eden AI's **smart router** — it picks the best model per request based on quality, latency, cost and live provider health. [How smart routing works →](https://www.edenai.co/docs/v3/llms/smart-routing)
+
+Browse the full catalog at [app.edenai.run/models](https://app.edenai.run/models).
+
+## Troubleshooting
+
+### `api_key` is `None`
+Make sure `EDENAI_API_KEY` is exported in the environment where your script runs.
+
+### `401 Unauthorized`
+Verify your Eden AI key — grab a fresh one at [app.edenai.run → API Keys](https://app.edenai.run/).
+
+### `model not found`
+Use the `provider/model` format (or `@edenai` for the smart router). No bare model names.
+
+### Connection issues
+Confirm the base URL is exactly `https://api.edenai.run/v3` and check Eden AI status at [app-edenai.instatus.com](https://app-edenai.instatus.com/).
+
+---
+
+## Next steps
+
+- [Smart routing](https://www.edenai.co/docs/v3/llms/smart-routing)
+- [Fallbacks](https://www.edenai.co/docs/v3/llms/fallback)
+- [Eden AI pricing](https://www.edenai.co/pricing)
+- [Atomic Agents GitHub](https://github.com/Eigenwise/atomic-agents)

haystack.md

@@ -0,0 +1,105 @@
+# Haystack + Eden AI
+
+The [Haystack](https://haystack.deepset.ai/) Eden AI integration adds native chat and embedding components, so you can build pipelines on top of **500+ models** with smart routing, automatic fallbacks, and a single API key.
+
+> Get your Eden AI key at [app.edenai.run](https://app.edenai.run/) → **API Keys**.
+
+---
+
+## 1. Install
+
+```bash
+pip install edenai-haystack
+```
+
+Requires Haystack 2.14.0 or newer.
+
+## 2. Set your Eden AI key
+
+The components read the key from the `EDENAI_API_KEY` environment variable (via Haystack's `Secret.from_env_var`):
+
+```bash
+export EDENAI_API_KEY="your-eden-ai-key"
+```
+
+Never hardcode the key.
+
+## 3. Generate a chat response
+
+```python
+from haystack_integrations.components.generators.edenai import EdenAIChatGenerator
+from haystack.dataclasses import ChatMessage
+
+generator = EdenAIChatGenerator(model="mistral/mistral-large-latest")
+result = generator.run([ChatMessage.from_user("What's the capital of France?")])
+print(result["replies"][0].text)
+```
+
+The chat generator supports streaming (`streaming_callback`), async (`run_async`), and tool/function calling. Pass generation parameters via `generation_kwargs`, e.g. `{"temperature": 0.2, "max_tokens": 512}`.
+
+## 4. Embed text and documents
+
+```python
+from haystack import Document
+from haystack_integrations.components.embedders.edenai import (
+    EdenAIDocumentEmbedder,
+    EdenAITextEmbedder,
+)
+
+doc_embedder = EdenAIDocumentEmbedder(model="mistral/mistral-embed")
+docs = doc_embedder.run([Document(content="I love pizza!")])["documents"]
+
+text_embedder = EdenAITextEmbedder(model="mistral/mistral-embed")
+query_embedding = text_embedder.run("What food do I love?")["embedding"]
+```
+
+---
+
+## Choosing a model
+
+Eden AI model ids use the `provider/model` format.
+
+**Chat**
+
+| Model | Best for |
+|---|---|
+| `openai/gpt-4o-mini` | **Default** — fast and cheap |
+| `anthropic/claude-sonnet-4-5` | Balanced reasoning |
+| `mistral/mistral-large-latest` | European, strong general model |
+| `google/gemini-2.5-flash` | Long context, multimodal |
+
+**Embeddings**
+
+| Model | Best for |
+|---|---|
+| `openai/text-embedding-3-small` | **Default** — cost-efficient |
+| `openai/text-embedding-3-large` | Higher accuracy |
+| `mistral/mistral-embed` | European embeddings |
+
+Browse the full catalog at [app.edenai.run/models](https://app.edenai.run/models).
+
+## Troubleshooting
+
+### `401 Unauthorized`
+Verify your Eden AI key — grab a fresh one at [app.edenai.run → API Keys](https://app.edenai.run/).
+
+### `400 Model(s) not found or inactive`
+The model must be active on your Eden AI account and use the `provider/model` format. No bare model names.
+
+### Connection issues
+The components target `https://api.edenai.run/v3`. Check Eden AI status at [app-edenai.instatus.com](https://app-edenai.instatus.com/).
+
+## Uninstall
+
+```bash
+pip uninstall edenai-haystack
+```
+
+---
+
+## Next steps
+
+- [Smart routing](https://www.edenai.co/docs/v3/llms/smart-routing)
+- [Fallbacks](https://www.edenai.co/docs/v3/llms/fallback)
+- [Eden AI pricing](https://www.edenai.co/pricing)
+- [Haystack integration on GitHub](https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/edenai)