feat: add Atomic Chat provider support (#60)

* feat: add support for Atomic Chat provider

- Introduced new provider 'Atomic Chat' with associated logo and configuration.
- Updated onboarding and settings components to include Atomic Chat.
- Added necessary files for provider integration, including images and configuration files.
- Updated provider catalog to include details for Atomic Chat.

This enhances the application by allowing users to utilize local LLMs via the Atomic Chat desktop app.

* refactor: remove deprecated configuration files and update README for Atomic Chat

- Deleted obsolete `.pnpm-approved-builds.json` and `mise.toml` files.
- Updated README to reflect the addition of Atomic Chat, including new usage instructions and configuration examples.
- Enhanced onboarding component to support Atomic Chat provider.
- Adjusted provider wizard description to include Atomic Chat alongside Ollama.

---------

Co-authored-by: SankaManka <rita@bagoodex.com>

README.md

@@ -106,13 +106,24 @@ ANTHROPIC_API_KEY=your-key-here
 
 ---
 
-## 🧠 Local Models (Ollama, LM Studio, vLLM)
+## 🧠 Local Models (Ollama, Atomic Chat, LM Studio, vLLM)
 
 Hermes Workspace supports two modes with local models:
 
 ### Portable Mode (Easiest)
 
-Point the workspace directly at your local server — no Hermes gateway needed:
+Point the workspace directly at your local server — no Hermes gateway needed.
+
+### Atomic Chat
+
+```bash
+# Start workspace pointed at Atomic Chat
+HERMES_API_URL=http://127.0.0.1:1337/v1 pnpm dev
+```
+
+Download [Atomic Chat](https://atomic.chat/), launch the desktop app, and make sure a model is loaded before starting Hermes Workspace.
+
+### Ollama
 
 ```bash
 # Start Ollama
@@ -126,13 +137,27 @@ Chat works immediately. Sessions, memory, and skills show "Not Available" — th
 
 ### Enhanced Mode (Full Features)
 
-Route through the Hermes gateway for sessions, memory, skills, jobs, and tools:
+Route through the Hermes gateway for sessions, memory, skills, jobs, and tools.
 
-**1. Configure your local model in `~/.hermes/config.yaml`:**
+Here are two explicit `~/.hermes/config.yaml` examples for the local providers we support directly in the workspace:
+
+**Atomic Chat**
+
+```yaml
+provider: atomic-chat
+model: your-model-name
+custom_providers:
+  - name: atomic-chat
+    base_url: http://127.0.0.1:1337/v1
+    api_key: atomic-chat
+    api_mode: chat_completions
+```
+
+**Ollama**
 
 ```yaml
 provider: ollama
-model: qwen2.5:7b # or any model you have pulled
+model: qwen3:32b
 custom_providers:
   - name: ollama
     base_url: http://127.0.0.1:11434/v1
@@ -140,6 +165,8 @@ custom_providers:
     api_mode: chat_completions
 ```
 
+You can adapt the same shape for other OpenAI-compatible local runners, but `Atomic Chat` and `Ollama` are the two built-in local paths documented in the workspace UI.
+
 **2. Enable the API server in `~/.hermes/.env`:**
 
 ```env
@@ -155,7 +182,7 @@ HERMES_API_URL=http://127.0.0.1:8642 pnpm dev
 
 All workspace features unlock automatically — sessions persist, memory saves across chats, skills are available, and the dashboard shows real usage data.
 
-> **Works with any OpenAI-compatible server** — Ollama, LM Studio, vLLM, llama.cpp, LocalAI, etc. Just change the `base_url` and `model` in the config above.
+> **Works with any OpenAI-compatible server** — Atomic Chat, Ollama, LM Studio, vLLM, llama.cpp, LocalAI, etc. Just change the `base_url` and `model` in the config above.
 
 ---
 

src/components/onboarding/hermes-onboarding.tsx

@@ -12,6 +12,7 @@ const KNOWN_PROVIDER_PREFIXES = [
   'openai-codex',
   'nous',
   'ollama',
+  'atomic-chat',
   'zai',
   'kimi-coding',
   'minimax',
@@ -86,6 +87,13 @@ const PROVIDERS = [
     desc: 'Local models, no key needed',
     authType: 'none',
   },
+  {
+    id: 'atomic-chat',
+    name: 'Atomic Chat',
+    logo: '/providers/atomic-chat.png',
+    desc: 'Local LLMs via Atomic Chat desktop app',
+    authType: 'none',
+  },
   {
     id: 'custom',
     name: 'Custom (OpenAI-compat)',
@@ -147,7 +155,9 @@ export function HermesOnboarding() {
   const needsApiKey =
     provider?.authType === 'api_key' || provider?.authType === 'custom'
   const needsBaseUrl =
-    provider?.id === 'ollama' || provider?.authType === 'custom'
+    provider?.id === 'ollama' ||
+    provider?.id === 'atomic-chat' ||
+    provider?.authType === 'custom'
   const isOAuth = provider?.authType === 'oauth'
   const capabilities = backendInfo?.capabilities
   const canEditConfig = Boolean(capabilities?.config)
@@ -257,7 +267,9 @@ export function HermesOnboarding() {
         body.env = { [prov.envKey]: apiKey }
       }
       if (baseUrl) {
-        body.config = { model: { provider: selectedProvider, baseUrl } }
+        body.config = {
+          model: { provider: selectedProvider, base_url: baseUrl },
+        }
       }
 
       const res = await fetch('/api/hermes-config', {
@@ -334,7 +346,7 @@ export function HermesOnboarding() {
       const decoder = new TextDecoder()
       let text = ''
 
-      while (true) {
+      for (;;) {
         const { done, value } = await reader.read()
         if (done) break
         const chunk = decoder.decode(value)
@@ -796,7 +808,9 @@ export function HermesOnboarding() {
                       >
                         {selectedProvider === 'ollama'
                           ? 'Ollama URL'
-                          : 'Base URL'}
+                          : selectedProvider === 'atomic-chat'
+                            ? 'Atomic Chat URL'
+                            : 'Base URL'}
                       </label>
                       <input
                         type="text"
@@ -805,7 +819,9 @@ export function HermesOnboarding() {
                         placeholder={
                           selectedProvider === 'ollama'
                             ? 'http://localhost:11434'
-                            : 'https://api.example.com/v1'
+                            : selectedProvider === 'atomic-chat'
+                              ? 'http://127.0.0.1:1337/v1'
+                              : 'https://api.example.com/v1'
                         }
                         className="w-full rounded-lg px-3 py-2 text-sm outline-none focus:ring-2 focus:ring-accent-500"
                         style={inputStyle}

src/components/provider-logo.tsx

@@ -46,6 +46,7 @@ export function ProviderLogo({
     anthropic: 'anthropic.png',
     openrouter: 'openrouter.png',
     ollama: 'ollama.png',
+    'atomic-chat': 'atomic-chat.png',
     kimi: 'kimi.png',
     'kimi-coding': 'kimi.png',
     minimax: 'minimax.png',

src/components/settings-dialog/settings-dialog.tsx

@@ -226,6 +226,13 @@ const PROVIDER_CARDS: Array<{
     models: ['llama3.1:70b', 'qwen3:32b', 'deepseek-r1:32b'],
     authType: 'none',
   },
+  {
+    id: 'atomic-chat',
+    name: 'Atomic Chat',
+    logo: '/providers/atomic-chat.png',
+    models: ['llama-3.2-3b', 'qwen2.5-7b', 'gemma-3-4b'],
+    authType: 'none',
+  },
   { id: 'custom', name: 'Custom', logo: '', models: [], authType: 'api_key' },
 ]
 

src/lib/provider-catalog.ts

@@ -137,6 +137,26 @@ export const PROVIDER_CATALOG: Array<ProviderInfo> = [
       2,
     ),
   },
+  {
+    id: 'atomic-chat',
+    name: 'Atomic Chat',
+    description: 'Local LLMs via Atomic Chat — run Llama, Gemma, Qwen and more on your machine.',
+    authTypes: ['local'],
+    docsUrl: 'https://atomic.chat',
+    configExample: JSON.stringify(
+      {
+        auth: {
+          profiles: {
+            'atomic-chat:local': {
+              provider: 'atomic-chat',
+            },
+          },
+        },
+      },
+      null,
+      2,
+    ),
+  },
 ]
 
 export function normalizeProviderId(value: string): string {

src/routes/api/hermes-config.ts

@@ -67,6 +67,12 @@ const PROVIDERS = [
     envKeys: ['XIAOMI_API_KEY'],
   },
   { id: 'ollama', name: 'Ollama (Local)', authType: 'none', envKeys: [] },
+  {
+    id: 'atomic-chat',
+    name: 'Atomic Chat (Local)',
+    authType: 'none',
+    envKeys: [],
+  },
   {
     id: 'custom',
     name: 'Custom OpenAI-compatible',
@@ -78,7 +84,10 @@ const PROVIDERS = [
 function readConfig(): Record<string, unknown> {
   try {
     const raw = fs.readFileSync(CONFIG_PATH, 'utf-8')
-    return (YAML.parse(raw) as Record<string, unknown>) || {}
+    const parsed = YAML.parse(raw)
+    return parsed && typeof parsed === 'object' && !Array.isArray(parsed)
+      ? (parsed as Record<string, unknown>)
+      : {}
   } catch {
     return {}
   }
@@ -296,7 +305,7 @@ export const Route = createFileRoute('/api/hermes-config')({
         // Handle env var updates
         if (body.env && typeof body.env === 'object') {
           const currentEnv = readEnv()
-          const envUpdates = body.env as Record<string, string>
+          const envUpdates = body.env as Record<string, string | null>
           for (const [key, value] of Object.entries(envUpdates)) {
             if (value === '' || value === null) {
               delete currentEnv[key]

src/screens/settings/components/provider-wizard.tsx

@@ -93,7 +93,7 @@ function getAuthTypeMeta(authType: ProviderAuthType): AuthTypeMeta {
 
   return {
     title: 'Local',
-    description: 'No auth needed (Ollama)',
+    description: 'No auth needed for local backends like Ollama or Atomic Chat',
   }
 }
 

src/screens/settings/providers-screen.tsx

@@ -59,6 +59,7 @@ const KNOWN_PROVIDER_PREFIXES = [
   'openai-codex',
   'nous',
   'ollama',
+  'atomic-chat',
   'zai',
   'kimi-coding',
   'minimax',
@@ -787,6 +788,12 @@ const MODEL_PROVIDER_OPTIONS: Array<SelectOption> = [
 ]
 
 const MODEL_PRESETS = [
+  {
+    id: 'atomic-chat',
+    label: 'Atomic Chat',
+    provider: 'custom' as const,
+    baseUrl: 'http://127.0.0.1:1337/v1',
+  },
   {
     id: 'ollama',
     label: 'Ollama',