Skip to content

Commit b02da38

Browse files
akanksha-choudhary-8akanksha-choudhary-8
authored
Document self-hosted system requirements
Adds tier based system requirements for self hosted ai architect.
2 parents 712ee15 + 01e16e4 commit b02da38

1 file changed

Lines changed: 37 additions & 32 deletions

File tree

‎README.md‎

Lines changed: 37 additions & 32 deletions
Original file line numberDiff line numberDiff line change
@@ -47,7 +47,7 @@
4747
<a href="#1-overview">Overview</a>
4848
</li>
4949
<li>
50-
<a href="#2-prerequisites">Prerequisites</a>
50+
<a href="#2-installation-requirements">Installation requirements</a>
5151
</li>
5252
<li>
5353
<a href="#3-installation-instructions">Installation instructions</a>
@@ -132,29 +132,29 @@ Please contact us at [support@bito.ai](mailto:support@bito.ai) for a **free Ente
132132

133133
<br />
134134

135-
<!-- Prerequisites -->
135+
<!-- Installation requirements -->
136136

137-
## 2. Prerequisites
137+
## 2. Installation requirements
138138

139-
Before you start the AI Architect setup in your environment, make sure you have the following ready:
139+
Before you start the AI Architect setup in your environment, make sure your environment meets the following requirements.
140140

141-
### **LLM API Keys**
142-
Required for personal use of AI Architect. An **Anthropic (Claude)** API key is mandatory; you can optionally also provide an **OpenAI (GPT)** API key. AI Architect also supports **[Portkey](https://portkey.ai)** integration for custom proxy configurations.
141+
### **System requirements**
143142

144-
### **Bito Access Key**
145-
You'll need a **Bito account** and a **Bito Access Key** to authenticate AI Architect. You can sign up for a Bito account at https://alpha.bito.ai, and create an access key from Settings -> Advanced Settings **[Link](https://alpha.bito.ai/home/advanced)**.
143+
| Tier | Repositories | vCPU | Memory | Storage |
144+
|------|--------------|------|--------|---------|
145+
| **Minimum** | up to 25 | 12 cores | 24 GB | 500 GB |
146+
| **Ideal** | 25 – 100 | 16 cores | 48 GB | 1.5 TB |
147+
| **Enterprise** | 100+ | 32+ cores | 128+ GB | 2 – 4 TB+ |
146148

147-
### **Git Access Token**
148-
Used by AI Architect to read and index your repositories. Bito supports **GitHub**, **GitLab**, and **Bitbucket**.
149-
- **GitHub classic Token with `repo` access** Fine-grained tokens are not supported. [Learn more](https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/managing-your-personal-access-tokens#creating-a-personal-access-token-classic)
150-
- **GitLab token with `api` scope)** [Learn more](https://docs.gitlab.com/user/profile/personal_access_tokens/#create-a-personal-access-token)
151-
- **Bitbucket Access Token:** Depending on your Bitbucket setup, you may need one of the following:
152-
- For **Bitbucket Cloud** use **API Token**. [Learn more](https://support.atlassian.com/bitbucket-cloud/docs/create-an-api-token/)
153-
- For **Bitbucket Enterprise (Self-Hosted)** use **HTTP Access Token**. [Learn more](https://confluence.atlassian.com/bitbucketserver/personal-access-tokens-939515499.html)
149+
> **Notes**
150+
> - **Large repositories:** Increase memory and storage by 50% above the tier baseline when any single repository exceeds 5 GB.
151+
> - **Indexing workload:** Indexing generates transient CPU and memory peaks above steady-state usage. The resources listed above include the headroom required to absorb these peaks; do not size below the tier minimums.
152+
> - **Persistent storage:** Automatically configured during installation using Docker volumes or Kubernetes PersistentVolumeClaims.
153+
> - **Production security:** Restrict access via firewall rules and front the deployment with a reverse proxy (e.g., Nginx) with HTTPS enabled.
154154
155155
---
156156

157-
### System requirements
157+
### **Supported operating systems**
158158

159159
The AI Architect supports the following operating systems:
160160

@@ -164,7 +164,7 @@ The AI Architect supports the following operating systems:
164164

165165
---
166166

167-
### WSL2 is required for Windows users
167+
### **WSL2 is required for Windows users**
168168

169169
If you're running Windows, Windows Subsystem for Linux 2 (WSL2) must be installed before proceeding.
170170

@@ -177,32 +177,37 @@ If you're running Windows, Windows Subsystem for Linux 2 (WSL2) must be installe
177177
```
178178
3. Set up your Ubuntu username and password when prompted
179179

180-
### Docker Desktop / Docker Service (required)
180+
---
181181

182-
**Docker Compose** is required to run AI Architect. The easiest and recommended way to get Docker Compose is to install **Docker Desktop**.
182+
### **Supported deployment modes**
183183

184-
Docker Desktop includes Docker Compose along with Docker Engine and Docker CLI which are Compose prerequisites.
184+
AI Architect supports two deployment modes. Choose the option that fits your infrastructure:
185185

186-
[Install Docker Desktop](https://docs.docker.com/compose/install)
186+
| Mode | Use case | Requirements |
187+
|------|----------|--------------|
188+
| **Docker (Compose)** | Single-host deployments, evaluation, smaller teams | Docker Engine and Docker Compose. [Install Docker Desktop](https://docs.docker.com/compose/install) — includes both. |
189+
| **Kubernetes (Helm)** | Production deployments requiring high availability and horizontal scaling | A pre-configured Kubernetes cluster on your infrastructure. For testing in a single laptop or local machine, create a local cluster using KIND (Kubernetes in Docker) — see the [Kubernetes Deployment Guide](https://github.com/gitbito/ai-architect/blob/main/docs/KUBERNETES_DEPLOYMENT.md). |
187190

188-
**Configuration for Windows (WSL2):**
191+
---
189192

190-
If you're using Windows with WSL2, you need to enable Docker integration with your WSL distribution:
193+
### **Bito Access Key**
191194

192-
1. Open **Docker Desktop**
193-
2. Go to **Settings > Resources > WSL Integration**
194-
3. Enable integration for your WSL distribution (e.g., Ubuntu)
195-
4. Click **Apply**
195+
You'll need a **Bito account** and a **Bito Access Key** to authenticate AI Architect. You can sign up for a Bito account at https://alpha.bito.ai, and create an access key from Settings -> Advanced Settings **[Link](https://alpha.bito.ai/home/advanced)**.
196196

197-
---
197+
### **Git Access Token**
198198

199-
### Kubernetes cluster (optional)
199+
Required for AI Architect to read and index your repositories. Bito supports **GitHub**, **GitLab**, and **Bitbucket**.
200+
- **GitHub classic Token with `repo` access** Fine-grained tokens are not supported. [Learn more](https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/managing-your-personal-access-tokens#creating-a-personal-access-token-classic)
201+
- **GitLab token with `api` scope)** [Learn more](https://docs.gitlab.com/user/profile/personal_access_tokens/#create-a-personal-access-token)
202+
- **Bitbucket Access Token:** Depending on your Bitbucket setup, you may need one of the following:
203+
- For **Bitbucket Cloud** use **API Token**. [Learn more](https://support.atlassian.com/bitbucket-cloud/docs/create-an-api-token/)
204+
- For **Bitbucket Enterprise (Self-Hosted)** use **HTTP Access Token**. [Learn more](https://confluence.atlassian.com/bitbucketserver/personal-access-tokens-939515499.html)
200205

201-
AI Architect supports Kubernetes as an alternative deployment option. For production deployments, a Kubernetes cluster must be pre-configured on your infrastructure.
206+
### **LLM API Keys**
202207

203-
For testing and development purposes, you can create a local cluster using KIND (Kubernetes in Docker). Refer to the [Kubernetes Deployment Guide](https://github.com/gitbito/ai-architect/blob/main/docs/KUBERNETES_DEPLOYMENT.md) for detailed instructions.
208+
Required for self-managed AI Architect deployments. An **Anthropic (Claude)** API key is mandatory; you can optionally also provide an **OpenAI (GPT)** API key. AI Architect also supports **[Portkey](https://portkey.ai)** integration for custom proxy configurations.
204209

205-
> **Note:** Kubernetes deployment support is available from version 1.3.0 onwards.
210+
To use Bito-hosted LLM instead (no LLM keys required from you), contact **[support@bito.ai](mailto:support@bito.ai)** about the [Bito Enterprise Plan](https://bito.ai/pricing/).
206211

207212
---
208213

0 commit comments

Comments
 (0)