### Quick Install Manifest

Source: https://manifest.build/docs/self-hosted

Use this command for a fast, recommended installation. It downloads the compose file, generates a secret, and starts the stack.

```bash
bash <(curl -sSL https://raw.githubusercontent.com/mnfst/manifest/main/docker/install.sh)
```

--------------------------------

### Review and Install Manifest Script

Source: https://manifest.build/docs/self-hosted

Download the install script to review it before execution. Useful for understanding the installation process or making modifications.

```bash
curl -sSLO https://raw.githubusercontent.com/mnfst/manifest/main/docker/install.sh
less install.sh
bash install.sh
```

--------------------------------

### Start LM Studio Server

Source: https://manifest.build/docs/providers/local-models

Command to start the LM Studio local LLM server. Alternatively, the server can be started from the LM Studio application's Developer tab.

```bash
lms server start
```

--------------------------------

### Start llama.cpp Server with Model

Source: https://manifest.build/docs/providers/local-models

Starts the llama.cpp server, requiring a path to a GGUF model file and an optional port specification.

```bash
llama-server -m <your-model>.gguf --port 8080
```

--------------------------------

### Manifest Error M003 Example

Source: https://manifest.build/docs/errors/M003

This is an example of the error message displayed when the Manifest key format is invalid. It indicates that keys should start with 'mnfst_'.

```text
[🦚 Manifest M003] That doesn't look right. Manifest keys start with "mnfst_". Grab yours from the dashboard.
See https://manifest.build/docs/errors/M003
```

--------------------------------

### Download Docker Compose and Environment Files

Source: https://manifest.build/docs/self-hosted

Obtain the necessary Docker Compose configuration and environment template files for manual setup.

```bash
curl -O https://raw.githubusercontent.com/mnfst/manifest/main/docker/docker-compose.yml
curl -O https://raw.githubusercontent.com/mnfst/manifest/main/docker/.env.example
cp .env.example .env
```

--------------------------------

### Start llama.cpp Server on Local Network

Source: https://manifest.build/docs/providers/local-models

Starts the llama.cpp server, explicitly binding to all network interfaces. This is required for Manifest running in Docker to connect.

```bash
llama-server -m <your-model>.gguf --host 0.0.0.0 --port 8080
```

--------------------------------

### Start LM Studio Server on Local Network

Source: https://manifest.build/docs/providers/local-models

Starts the LM Studio server, binding to all network interfaces and enabling CORS. This is necessary for Manifest running in Docker to connect.

```bash
lms server start --bind 0.0.0.0 --port 1234 --cors
```

--------------------------------

### Upgrade Manifest Installation

Source: https://manifest.build/docs/self-hosted

Upgrade an existing self-hosted Manifest installation to the latest version by pulling the new image and restarting the services.

```bash
docker compose pull
docker compose up -d
```

--------------------------------

### Run Manifest with BYO PostgreSQL (CMD)

Source: https://manifest.build/docs/self-hosted

Start Manifest using Docker on Windows with the Command Prompt. Requires manual generation of a 64-character secret.

```cmd
docker run -d ^
  -p 2099:2099 ^
  -e DATABASE_URL=postgresql://user:pass@host:5432/manifest ^
  -e BETTER_AUTH_SECRET=<your-64-char-secret> ^
  -e BETTER_AUTH_URL=http://localhost:2099 ^
  manifestdotbuild/manifest
```

--------------------------------

### Run Manifest with BYO PostgreSQL (PowerShell)

Source: https://manifest.build/docs/self-hosted

Start Manifest using Docker on Windows with PowerShell. Generates a random secret for BETTER_AUTH_SECRET.

```powershell
$secret = -join ((48..57 + 97..122) | Get-Random -Count 64 | ForEach-Object { [char]$_ })

docker run -d `
  -p 2099:2099 `
  -e DATABASE_URL=postgresql://user:pass@host:5432/manifest `
  -e BETTER_AUTH_SECRET=$secret `
  -e BETTER_AUTH_URL=http://localhost:2099 `
  manifestdotbuild/manifest
```

--------------------------------

### Pull and Serve Ollama Model

Source: https://manifest.build/docs/providers/local-models

Use this command to download a specific model with Ollama and then start the Ollama server.

```bash
ollama pull llama3.1:8b   # then:
ollama serve
```

--------------------------------

### Start Docker Compose Stack

Source: https://manifest.build/docs/self-hosted

Launch the Manifest services defined in the docker-compose.yml file in detached mode.

```bash
docker compose up -d
```

--------------------------------

### Example M200 Error Message

Source: https://manifest.build/docs/errors/M200

This is an example of the text output when the M200 error is triggered, showing the specific limit that was exceeded and a link to adjust it.

```text
[🦚 Manifest M200] You hit your cost limit: $12.50 used, $10.00/day allowed. Adjust it here: https://app.manifest.build/...
See https://manifest.build/docs/errors/M200
```

--------------------------------

### Run Manifest with BYO PostgreSQL

Source: https://manifest.build/docs/self-hosted

Start Manifest in a Docker container, connecting to an existing PostgreSQL instance. Ensure BETTER_AUTH_SECRET is a strong, random string.

```bash
docker run -d \
  -p 2099:2099 \
  -e DATABASE_URL=postgresql://user:pass@host:5432/manifest \
  -e BETTER_AUTH_SECRET=$(openssl rand -hex 32) \
  -e BETTER_AUTH_URL=http://localhost:2099 \
  manifestdotbuild/manifest
```

--------------------------------

### Manifest Error M002 Example

Source: https://manifest.build/docs/errors/M002

This is an example of the error message displayed when the Bearer token is empty. It indicates that the Manifest key needs to be pasted into the token.

```text
[🦚 Manifest M002] The Bearer token is empty. Paste your Manifest key into it.
See https://manifest.build/docs/errors/M002
```

--------------------------------

### Manifest Error M301 Example

Source: https://manifest.build/docs/errors/M301

This is an example of the error message displayed when the 'messages' array exceeds the maximum length of 1000.

```text
[🦚 Manifest M301] `messages` array exceeds maximum length of 1000.
See https://manifest.build/docs/errors/M301
```

--------------------------------

### Example M100 Error Message

Source: https://manifest.build/docs/errors/M100

This is an example of the error message displayed when the M100 error occurs. The provider name will vary based on the selected provider.

```text
[🦚 Manifest M100] No anthropic API key yet. Add one here: https://app.manifest.build/...
See https://manifest.build/docs/errors/M100
```

--------------------------------

### M203 Error Message Example

Source: https://manifest.build/docs/errors/M203

This is an example of the error message displayed when the concurrency limit is exceeded. It indicates too many concurrent requests and provides a link for more information.

```text
[🦚 Manifest M203] Too many concurrent requests. Give it a moment.
See https://manifest.build/docs/errors/M203
```

--------------------------------

### Example Error Message for M001

Source: https://manifest.build/docs/errors/M001

This is the error message displayed when the Authorization header is missing. It indicates the problem and provides a link to relevant documentation.

```text
[🦚 Manifest M001] Missing the Authorization header. Set it to "Bearer mnfst_<your-key>".
See https://manifest.build/docs/errors/M001
```

--------------------------------

### Restore Manifest Database

Source: https://manifest.build/docs/self-hosted

Restore the Manifest database from a SQL backup file. This involves starting the postgres service, piping the backup file into psql, and then restarting the full stack.

```bash
docker compose up -d postgres
cat manifest-backup.sql | docker compose exec -T postgres psql -U manifest manifest
docker compose up -d
```

--------------------------------

### POST Request to OpenAI Chat Completions Endpoint

Source: https://manifest.build/docs/reference/api

This example demonstrates how to send a POST request to the `/v1/chat/completions` endpoint using cURL. The request includes the 'manifest/auto' model and a user message. The body is forwarded verbatim to the provider.

```bash
curl -X POST http://localhost:2099/v1/chat/completions \
  -H "Authorization: Bearer mnfst_YOUR_KEY_HERE" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "manifest/auto",
    "messages": [
      {"role": "user", "content": "What is the capital of France?"}
    ]
  }'
```

--------------------------------

### Manifest Error M202 Example

Source: https://manifest.build/docs/errors/M202

This snippet shows the typical text output when the Manifest M202 error is encountered, indicating a per-IP rate limit has been exceeded.

```text
[🦚 Manifest M202] Too many requests from this IP — wait a few seconds and retry.
See https://manifest.build/docs/errors/M202
```

--------------------------------

### Manifest M004 Error Message

Source: https://manifest.build/docs/errors/M004

This is an example of the error message displayed when an API key has expired. It provides a link to generate a new key.

```text
[🦚 Manifest M004] This key has expired. Generate a new one here
See https://manifest.build/docs/errors/M004
```

--------------------------------

### Correct Chat Completions Request Body

Source: https://manifest.build/docs/errors/M300

Example of a correctly formatted request body for the chat completions API, including the required 'messages' array.

```json
{
  "model": "auto",
  "messages": [
    { "role": "user", "content": "Hello" }
  ]
}
```

--------------------------------

### POST Request to Anthropic Messages Endpoint

Source: https://manifest.build/docs/reference/api

This example shows how to send a POST request to the `/v1/messages` endpoint using cURL for Anthropic compatibility. It includes the 'manifest/auto' model, max tokens, and a user message. The 'anthropic-version' header is also required.

```bash
curl -X POST http://localhost:2099/v1/messages \
  -H "Authorization: Bearer mnfst_YOUR_KEY_HERE" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "manifest/auto",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'
```

--------------------------------

### Manifest M201 Error Message

Source: https://manifest.build/docs/errors/M201

This is an example of the error message displayed when the per-user rate limit is exceeded. SDKs that respect the 'retry-after' header will automatically back off.

```text
[🦚 Manifest M201] Too many requests — wait a few seconds and retry.
See https://manifest.build/docs/errors/M201
```

--------------------------------

### Manifest M005 Error Message

Source: https://manifest.build/docs/errors/M005

This is an example of the error message displayed by Manifest when error M005 occurs. It indicates an unrecognized key and suggests obtaining the current key from the dashboard.

```text
[🦚 Manifest M005] I don't recognize this key. It might have been rotated or deleted. Grab the current one from the dashboard.
See https://manifest.build/docs/errors/M005
```

--------------------------------

### HTTP Authentication Header

Source: https://manifest.build/docs/reference/api

Every request to the Manifest API requires an 'Authorization' header with a Bearer token. Generate your key from the dashboard's Agents page; keys start with 'mnfst_'.

```http
Authorization: Bearer mnfst_YOUR_KEY_HERE
```

--------------------------------

### Backup Manifest Database

Source: https://manifest.build/docs/self-hosted

Create a SQL backup of the Manifest database using pg_dump. This command should be run from the host machine while the stack is running.

```bash
docker compose exec -T postgres pg_dump -U manifest manifest > manifest-backup-$(date +%F).sql
```

--------------------------------

### Verify Manifest API Key

Source: https://manifest.build/docs/self-hosted

Send a test request to the Manifest API to verify your connection and API key. Ensure you replace the placeholder with your actual Manifest API key.

```bash
curl -X POST http://localhost:2099/v1/chat/completions \
  -H "Authorization: Bearer mnfst_YOUR_KEY_HERE" \
  -H "Content-Type: application/json" \
  -d '{"model": "manifest/auto", "messages": [{"role": "user", "content": "Hello"}]}'
```

--------------------------------

### POST /v1/chat/completions

Source: https://manifest.build/docs/reference/api

Handles chat completions using the OpenAI format. This endpoint is compatible with most clients, including the OpenAI SDK, LangChain, and Vercel AI SDK.

```APIDOC
## POST /v1/chat/completions

### Description
This endpoint allows you to send chat messages and receive completions in the OpenAI format. It supports various OpenAI-specific fields for customization.

### Method
POST

### Endpoint
/v1/chat/completions

### Parameters
#### Query Parameters
None

#### Request Body
- **model** (string) - Required - The model to use for generation. Use `manifest/auto` for automatic routing.
- **messages** (array) - Required - An array of message objects representing the conversation history.
- **temperature** (number) - Optional - Controls randomness. Lower values make output more focused and deterministic.
- **max_tokens** (integer) - Optional - The maximum number of tokens to generate in the response.
- **tools** (array) - Optional - A list of tools the model may call.
- **tool_choice** (object) - Optional - Controls how the model selects a tool.
- **response_format** (object) - Optional - Specifies the desired format for the response.
- **stream** (boolean) - Optional - If true, returns a streaming response.

### Request Example
```json
{
  "model": "manifest/auto",
  "messages": [
    {"role": "user", "content": "What is the capital of France?"}
  ]
}
```

### Response
#### Success Response (200)
- **id** (string) - Unique identifier for the completion.
- **object** (string) - Type of object returned, e.g., `chat.completion`.
- **created** (integer) - Unix timestamp of when the completion was created.
- **model** (string) - The actual model ID used for generation.
- **choices** (array) - A list of completion choices.
- **usage** (object) - Information about token usage.

#### Response Example
```json
{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-3.5-turbo",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 7,
    "total_tokens": 17
  }
}
```
```

--------------------------------

### Verify Image Signature with Cosign

Source: https://manifest.build/docs/self-hosted

Verify the signature of a published Manifest image using cosign keyless signing before pulling. This ensures the image integrity and origin.

```bash
cosign verify manifestdotbuild/manifest:<version> \
  --certificate-identity-regexp="^https://github.com/mnfst/manifest/" \
  --certificate-oidc-issuer="https://token.actions.githubusercontent.com"
```

--------------------------------

### Manage Manifest Data Volume

Source: https://manifest.build/docs/self-hosted

List or remove the 'pgdata' named volume used for Manifest persistence. Use 'docker compose down -v' with caution as it destroys all data.

```bash
docker volume ls | grep pgdata
docker compose down -v    # destroys all data
```

--------------------------------

### Chat Completions Endpoint

Source: https://manifest.build/docs/llms.txt

The Manifest proxy speaks both OpenAI and Anthropic APIs. This endpoint is used for chat completions.

```APIDOC
## POST /v1/chat/completions

### Description
Sends a request to the chat completions endpoint. This endpoint is compatible with both OpenAI and Anthropic API specifications.

### Method
POST

### Endpoint
/v1/chat/completions

### Parameters
#### Request Body
- **messages** (array) - Required - An array of message objects representing the conversation history. Must not be empty.

### Request Example
{
  "messages": [
    {"role": "user", "content": "Hello!"}
  ]
}

### Response
#### Success Response (200)
- **content** (string) - The response from the language model.

#### Response Example
{
  "content": "Hello! How can I help you today?"
}

### Error Handling
- **M300**: Missing messages array.
- **M301**: Messages array too long (more than 1000 messages).
- **M001**: Missing Authorization header.
- **M002**: Empty Bearer token.
- **M003**: Invalid key format.
- **M004**: Key expired.
- **M005**: Key not recognized.
- **M100**: Provider API key missing.
- **M101**: No providers configured.
- **M200**: Usage limit exceeded.
- **M201**: Per-user rate limit exceeded.
- **M202**: Per-IP rate limit exceeded.
- **M203**: Concurrency limit exceeded.
- **M500**: Internal server error.
```

--------------------------------

### POST /v1/responses

Source: https://manifest.build/docs/reference/api

Handles responses for specific models like Codex and deep-research models, using an OpenAI-compatible format.

```APIDOC
## POST /v1/responses

### Description
This endpoint is designed for specific models such as Codex and deep-research models, providing responses in an OpenAI-compatible format.

### Method
POST

### Endpoint
/v1/responses

### Parameters
#### Query Parameters
None

#### Request Body
- **model** (string) - Required - The model to use for generation. Use `manifest/auto` for automatic routing.
- **messages** (array) - Required - An array of message objects representing the conversation history.
- **temperature** (number) - Optional - Controls randomness. Lower values make output more focused and deterministic.
- **max_tokens** (integer) - Optional - The maximum number of tokens to generate in the response.

### Request Example
```json
{
  "model": "manifest/auto",
  "messages": [
    {"role": "user", "content": "Explain the concept of recursion."}
  ]
}
```

### Response
#### Success Response (200)
- **id** (string) - Unique identifier for the response.
- **object** (string) - Type of object returned, e.g., `text_completion`.
- **created** (integer) - Unix timestamp of when the response was created.
- **model** (string) - The actual model ID used for generation.
- **choices** (array) - A list of response choices.
- **usage** (object) - Information about token usage.

#### Response Example
```json
{
  "id": "resp-abc",
  "object": "text_completion",
  "created": 1677652289,
  "model": "codex-davinci",
  "choices": [
    {
      "index": 0,
      "text": "Recursion is a method where the solution to a problem depends on smaller instances of the same problem.",
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 20,
    "total_tokens": 35
  }
}
```
```

--------------------------------

### Reading Response Headers with Fetch

Source: https://manifest.build/docs/reference/headers

This snippet shows how to make a POST request and then retrieve specific headers from the response. Header names are case-insensitive, but fetch often lowercases them.

```javascript
const response = await fetch("http://localhost:2099/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.MANIFEST_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "manifest/auto",
    messages: [{ role: "user", content: "Hello" }],
  }),
});

console.log(response.headers.get("x-manifest-tier")); // 	→ "simple"
console.log(response.headers.get("x-manifest-model")); // 	→ "gpt-5-mini"
console.log(response.headers.get("x-manifest-provider")); // 	→ "openai"
```

--------------------------------

### Generate Secret for .env File

Source: https://manifest.build/docs/self-hosted

Generate a secure random string to use as your BETTER_AUTH_SECRET in the .env file.

```bash
openssl rand -hex 32
```

--------------------------------

### Configure Custom Port for Manifest

Source: https://manifest.build/docs/self-hosted

Change the default port binding for Manifest if port 2099 is already in use. Update both the Docker port mapping and the BETTER_AUTH_URL environment variable.

```bash
docker run -d \
  -p 8080:2099 \
  -e BETTER_AUTH_URL=http://localhost:8080 \
  ...
```

```yaml
ports:
  - '127.0.0.1:8080:2099'
```

```dotenv
BETTER_AUTH_URL=http://localhost:8080
```

--------------------------------

### Redirect Telemetry Endpoint

Source: https://manifest.build/docs/self-hosted

Configure the TELEMETRY_ENDPOINT environment variable to point to a custom URL for receiving telemetry data. This allows for self-hosted dashboarding.

```env
TELEMETRY_ENDPOINT=https://telemetry.mycompany.internal/v1/report
```

--------------------------------

### Stop Docker Compose Services

Source: https://manifest.build/docs/self-hosted

Use `docker compose down` to stop services while preserving data. Use `docker compose down -v` to stop services and delete all associated data.

```bash
docker compose down       # Stop services (keeps data)
docker compose down -v    # Stop and delete all data
```

--------------------------------

### Manifest M500 Error Message

Source: https://manifest.build/docs/errors/M500

This is the text output displayed to the user when a Manifest M500 error occurs. It indicates a problem on Manifest's end and suggests retrying.

```text
[🦚 Manifest M500] Something broke on our end. Try again in a moment.
See https://manifest.build/docs/errors/M500
```

--------------------------------

### POST /v1/messages

Source: https://manifest.build/docs/reference/api

Handles chat messages using the Anthropic format. This endpoint is compatible with the Anthropic SDK and other tools that use the Messages API.

```APIDOC
## POST /v1/messages

### Description
This endpoint allows you to interact with models using the Anthropic Messages API format. It's suitable for the Anthropic SDK and similar clients.

### Method
POST

### Endpoint
/v1/messages

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Headers
- **anthropic-version** (string) - Required - The version of the Anthropic API to use, e.g., `2023-06-01`.

#### Request Body
- **model** (string) - Required - The model to use for generation. Use `manifest/auto` for automatic routing.
- **max_tokens** (integer) - Required - The maximum number of tokens to generate in the response.
- **messages** (array) - Required - An array of message objects representing the conversation history.

### Request Example
```bash
curl -X POST http://localhost:2099/v1/messages \
  -H "Authorization: Bearer mnfst_YOUR_KEY_HERE" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "manifest/auto",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'
```

### Response
#### Success Response (200)
- **id** (string) - Unique identifier for the message.
- **type** (string) - Type of the response, e.g., `message`.
- **role** (string) - The role of the sender, e.g., `assistant`.
- **content** (array) - The content of the message.
- **model** (string) - The actual model ID used for generation.
- **stop_reason** (string) - The reason the model stopped generating tokens.
- **usage** (object) - Information about token usage.

#### Response Example
```json
{
  "id": "msg_abc123",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hi there! How can I help you today?"
    }
  ],
  "model": "claude-3-opus-20240229",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 10,
    "output_tokens": 18
  }
}
```
```

--------------------------------

### Manifest M300 Error Message

Source: https://manifest.build/docs/errors/M300

This is the error message displayed by Manifest when the 'messages' array is missing or invalid.

```text
[🦚 Manifest M300] `messages` array is required.
See https://manifest.build/docs/errors/M300
```

--------------------------------

### Disable Telemetry

Source: https://manifest.build/docs/self-hosted

Set the MANIFEST_TELEMETRY_DISABLED environment variable to 1 to turn off telemetry reporting. This prevents any telemetry data from being sent.

```env
MANIFEST_TELEMETRY_DISABLED=1
```

--------------------------------

### JSON Error Response Format

Source: https://manifest.build/docs/reference/api

The Manifest proxy returns a standard JSON error envelope when an issue occurs. This format includes a message, type, and code for the error. Common status codes include 401, 402, 424, and 429.

```json
{
  "error": {
    "message": "Limit exceeded: cost usage ($1.23) exceeds $1.00 per day",
    "type": "limit_exceeded",
    "code": 429
  }
}
```

--------------------------------

### Hard Limit Exceeded Message

Source: https://manifest.build/docs/set-limits

This message is returned when a Hard Limit rule triggers, indicating that the cost usage has exceeded the defined threshold for the current period.

```text
Limit exceeded: cost usage ($X) exceeds $Y per day
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.