raycast_api_proxy

This is a simple Raycast AI API proxy.

Stars: 317

Visit

The Raycast AI Proxy is a tool that acts as a proxy for the Raycast AI application, allowing users to utilize the application without subscribing. It intercepts and forwards Raycast requests to various AI APIs, then reformats the responses for Raycast. The tool supports multiple AI providers and allows for custom model configurations. Users can generate self-signed certificates, add them to the system keychain, and modify DNS settings to redirect requests to the proxy. The tool is designed to work with providers like OpenAI, Azure OpenAI, Google, and more, enabling tasks such as AI chat completions, translations, and image generation.

README:

Raycast AI Proxy

This is a simple Raycast AI API proxy. It allows you to use the Raycast AI application without subscribing. The proxy converts requests from Raycast into a format to send to AI model providers (e.g., OpenAI), and then converts the responses back into Raycast’s format.

English | 中文 | 日本語

Introduction

This project uses a man-in-the-middle approach to intercept and forward Raycast requests to various AI APIs, then returns the responses after reformatting them for Raycast. It primarily maps:

GET /api/v1/me: Modifies the flag indicating user support for AI.
POST /api/v1/translations: Translation interface.
POST /api/v1/ai/chat_completions: Common AI interface.
GET /api/v1/ai/models: AI model list interface.

How It Works (Man-in-the-Middle)

Modify DNS or /etc/hosts to point backend.raycast.com to this proxy instead of the official server.
The proxy receives the HTTPS requests from Raycast.
A self-signed certificate is used to decrypt and forward these requests to the configured AI endpoints (e.g., OpenAI, Anthropic).
The responses are re-encrypted and returned to Raycast.

Because Raycast and its API communicate via HTTPS, you need to trust the self-signed certificate for this interception to work. More details on man-in-the-middle proxies can be found at mitmproxy documentation.

YAML-Based Model Configuration

Environment variables are becoming deprecated. Now you can define multiple models in config.yml, allowing providers to coexist:

models:
  - provider_name: "openai"
    api_type: "openai"
    params:
      api_key: "sk-xxxx"
      allow_model_patterns:
        - "gpt-\\d+"
  - provider_name: "azure openai"
    api_type: "openai"
    params:
      api_key: "xxxxxx"
      base_url: "https://your-resource.openai.azure.com"
      # ...
  - provider_name: "google"
    api_type: "gemini"
    params:
      api_key: "xxxxxx"
  - provider_name: "anthropic"
    api_type: "anthropic"
    params:
      api_key: "sk-ant-xxx"
  - provider_name: "deepseek"
    api_type: "openai"   # openai-compatible
    params:
      api_key: "sk-deepseek-xxx"
default_model: "gpt-4"

Each provider entry specifies the provider name, API type, and parameters.

provider_name: The provider name. used for identification.
api_type: The API type. For example, openai, gemini, or anthropic.
params: base_url, api_key, and other parameters required by the provider.

Supported providers: you can combine multiple models, Common options include:

Provider	Model	Test Status	Image Generation
`openai`	from api	Tested	Supported
`azure openai`	Same as above	Tested	Supported
`google`	from api	Tested	Not supported
`anthropic`	claude-3-sonnet, claude-3-opus, claude-3-5-opus	Tested	Not supported
`deepseek`	from api	Tested	Not supported
`ollama`	from api	Tested	Not Supported

Refer to the config.yml.example file for more details.

Ai chat

Translate

Image Generation

Only OpenAI API supports image generation.

Usage

Installation and Configuration

1. Generate Certificate

pip3 install mitmproxy
python -c "$(curl -fsSL https://raw.githubusercontent.com/yufeikang/raycast_api_proxy/main/scripts/cert_gen.py)"  --domain backend.raycast.com  --out ./cert

Clone this repository and run:

pdm run cert_gen

2. Add Certificate to System Keychain

Open the CA certificate in the cert folder and add it to the system keychain and trust it. This is mandatory, as the Raycast AI proxy uses a self-signed certificate, and it must be trusted to work correctly.

Note:

When using on macOS with Apple Silicon, if you encounter application hanging issues when manually adding the CA certificate to the "Keychain Access", you can use the following command in the terminal as an alternative:

(https://docs.mitmproxy.org/stable/concepts-certificates/#installing-the-mitmproxy-ca-certificate-manually)

sudo security add-trusted-cert -d -p ssl -p basic -k /Library/Keychains/System.keychain ~/.mitmproxy/mitmproxy-ca-cert.pem

3. Modify `/etc/host` to add the following lines

127.0.0.1 backend.raycast.com
::1 backend.raycast.com

The purpose of this modification is to redirect backend.raycast.com to the local machine, rather than the real backend.raycast.com. You can also add this record in your DNS server.

Alternatively, you can add this record to your DNS server. The ultimate goal is to make backend.raycast.com point to the address where this project is deployed. The 127.0.0.1 can be replaced with your deployment address. If you deploy this project in the cloud or in your local network, you can point this address to your deployment address.

4. Launch the service

docker run --name raycast \
    -e OPENAI_API_KEY=$OPENAI_API_KEY \
    -p 443:443 \
    --dns 1.1.1.1 \
    -v $PWD/cert/:/data/cert \
    -e CERT_FILE=/data/cert/backend.raycast.com.cert.pem \
    -e CERT_KEY=/data/cert/backend.raycast.com.key.pem \
    -e LOG_LEVEL=INFO \
    -d \
    ghcr.io/yufeikang/raycast_api_proxy:main

You can also deploy this service in the cloud or your local network, as long as your Raycast can access this address.

Then, restart Raycast, and you should be able to use it.

Advanced Configuration

1. Using Azure OpenAI API

Refer to How to switch between OpenAI and Azure OpenAI endpoints with Python.

Simply modify the corresponding environment variables.

docker run --name raycast \
    -e OPENAI_API_KEY=$OPENAI_API_KEY \
    -e OPENAI_BASE_URL=https://your-resource.openai.azure.com \
    -e OPENAI_API_VERSION=2023-05-15 \
    -e OPENAI_API_TYPE=azure \
    -e AZURE_DEPLOYMENT_ID=your-deployment-id \
    -p 443:443 \
    --dns 1.1.1.1 \
    -v $PWD/cert/:/data/cert \
    -e CERT_FILE=/data/cert/backend.raycast.com.cert.pem \
    -e CERT_KEY=/data/cert/backend.raycast.com.key.pem \
    -e LOG_LEVEL=INFO \
    -d \
    ghcr.io/yufeikang/raycast_api_proxy:main

2. Google Gemini API

Can be used together with the OpenAI API by setting the corresponding environment variables.

Obtain your Google API Key and export it as GOOGLE_API_KEY.

# git clone this repo and cd to it
docker build -t raycast .
docker run --name raycast \
    -e GOOGLE_API_KEY=$GOOGLE_API_KEY \
    -p 443:443 \
    --dns 1.1.1.1 \
    -v $PWD/cert/:/data/cert \
    -e CERT_FILE=/data/cert/backend.raycast.com.cert.pem \
    -e CERT_KEY=/data/cert/backend.raycast.com.key.pem \
    -e LOG_LEVEL=INFO \
    -d \
    raycast:latest

3. Local Manual Run

Clone this repository
Install dependencies using pdm install
Create environment variables

export OPENAI_API_KEY=<your openai api key>

Generate self-signed certificate using ./scripts/cert_gen.py --domain backend.raycast.com --out ./cert
Start the service using python ./app/main.py

4. Local Development

Since you might have modified the local DNS, developing locally might lead to DNS loops. To avoid this, use Docker during local development and start the development environment by specifying the DNS.

Reference:

sh ./local_docker.sh

5. Using Custom Mapping

You can refer to the custom_mapping.yml.example file in the project directory to customize the modifications to some interface responses.

"api/v1/me/trial_status":
  get:
    response:
      body:
        # json path replace
        "$.trial_limits.commands_limit": 30

For example, the above configuration will replace $.trial_limits.commands_limit in the response body of the GET api/v1/me/trial_status interface with 30. The $.trial_limits.commands_limit is a JSON path.

Currently, only response body replacements are supported.

6. Multi-User Shared Service

If you want to allow multiple users to share this service or you deploy the service on the public internet, you need to restrict which users can access the service. You can use the ALLOWED_USERS environment variable to restrict which users can access the service.

ALLOWED_USERS="[email protected],[email protected]"

The email addresses are the Raycast user email addresses, separated by commas.

Notes

DNS Designation Due to the presence of GFW (Great Firewall of China), if you use this in mainland China, you might need to designate a domestic DNS server. Otherwise, domain names might not resolve correctly. For instance: --dns 223.5.5.5.
DNS Not Taking Effect Sometimes on macOS, modifying the /etc/hosts file does not take effect immediately. There’s no known solution to this yet. Sometimes restarting Raycast helps, or modifying the /etc/hosts file again might work.

Roadmap

[ ] Support web search
[ ] Support more AI models
[ ] Improve project structure

For Tasks:

Click tags to check more tools for each tasks

modify user support translate text complete ai chat list ai models generate images

For Jobs:

software developer ai engineer data scientist machine learning engineer ai researcher

Alternative AI tools for raycast_api_proxy

Similar Open Source Tools

raycast_api_proxy

github

: 317

chatgpt-cli

ChatGPT CLI provides a powerful command-line interface for seamless interaction with ChatGPT models via OpenAI and Azure. It features streaming capabilities, extensive configuration options, and supports various modes like streaming, query, and interactive mode. Users can manage thread-based context, sliding window history, and provide custom context from any source. The CLI also offers model and thread listing, advanced configuration options, and supports GPT-4, GPT-3.5-turbo, and Perplexity's models. Installation is available via Homebrew or direct download, and users can configure settings through default values, a config.yaml file, or environment variables.

github

: 610

BodhiApp

Bodhi App runs Open Source Large Language Models locally, exposing LLM inference capabilities as OpenAI API compatible REST APIs. It leverages llama.cpp for GGUF format models and huggingface.co ecosystem for model downloads. Users can run fine-tuned models for chat completions, create custom aliases, and convert Huggingface models to GGUF format. The CLI offers commands for environment configuration, model management, pulling files, serving API, and more.

github

: 67

ethereum-etl-airflow

This repository contains Airflow DAGs for extracting, transforming, and loading (ETL) data from the Ethereum blockchain into BigQuery. The DAGs use the Google Cloud Platform (GCP) services, including BigQuery, Cloud Storage, and Cloud Composer, to automate the ETL process. The repository also includes scripts for setting up the GCP environment and running the DAGs locally.

github

: 394

llm-vscode

llm-vscode is an extension designed for all things LLM, utilizing llm-ls as its backend. It offers features such as code completion with 'ghost-text' suggestions, the ability to choose models for code generation via HTTP requests, ensuring prompt size fits within the context window, and code attribution checks. Users can configure the backend, suggestion behavior, keybindings, llm-ls settings, and tokenization options. Additionally, the extension supports testing models like Code Llama 13B, Phind/Phind-CodeLlama-34B-v2, and WizardLM/WizardCoder-Python-34B-V1.0. Development involves cloning llm-ls, building it, and setting up the llm-vscode extension for use.

github

: 1.1k

LEADS

LEADS is a lightweight embedded assisted driving system designed to simplify the development of instrumentation, control, and analysis systems for racing cars. It is written in Python and C/C++ with impressive performance. The system is customizable and provides abstract layers for component rearrangement. It supports hardware components like Raspberry Pi and Arduino, and can adapt to various hardware types. LEADS offers a modular structure with a focus on flexibility and lightweight design. It includes robust safety features, modern GUI design with dark mode support, high performance on different platforms, and powerful ESC systems for traction control and braking. The system also supports real-time data sharing, live video streaming, and AI-enhanced data analysis for driver training. LEADS VeC Remote Analyst enables transparency between the driver and pit crew, allowing real-time data sharing and analysis. The system is designed to be user-friendly, adaptable, and efficient for racing car development.

github

: 249

Construction-Hazard-Detection

Construction-Hazard-Detection is an AI-driven tool focused on improving safety at construction sites by utilizing the YOLOv8 model for object detection. The system identifies potential hazards like overhead heavy loads and steel pipes, providing real-time analysis and warnings. Users can configure the system via a YAML file and run it using Docker. The primary dataset used for training is the Construction Site Safety Image Dataset enriched with additional annotations. The system logs are accessible within the Docker container for debugging, and notifications are sent through the LINE messaging API when hazards are detected.

github

: 153

sandbox

Sandbox is an open-source cloud-based code editing environment with custom AI code autocompletion and real-time collaboration. It consists of a frontend built with Next.js, TailwindCSS, Shadcn UI, Clerk, Monaco, and Liveblocks, and a backend with Express, Socket.io, Cloudflare Workers, D1 database, R2 storage, Workers AI, and Drizzle ORM. The backend includes microservices for database, storage, and AI functionalities. Users can run the project locally by setting up environment variables and deploying the containers. Contributions are welcome following the commit convention and structure provided in the repository.

github

: 1.1k

tiledesk-dashboard

Tiledesk is an open-source live chat platform with integrated chatbots written in Node.js and Express. It is designed to be a multi-channel platform for web, Android, and iOS, and it can be used to increase sales or provide post-sales customer service. Tiledesk's chatbot technology allows for automation of conversations, and it also provides APIs and webhooks for connecting external applications. Additionally, it offers a marketplace for apps and features such as CRM, ticketing, and data export.

github

: 244

holmesgpt

HolmesGPT is an open-source DevOps assistant powered by OpenAI or any tool-calling LLM of your choice. It helps in troubleshooting Kubernetes, incident response, ticket management, automated investigation, and runbook automation in plain English. The tool connects to existing observability data, is compliance-friendly, provides transparent results, supports extensible data sources, runbook automation, and integrates with existing workflows. Users can install HolmesGPT using Brew, prebuilt Docker container, Python Poetry, or Docker. The tool requires an API key for functioning and supports OpenAI, Azure AI, and self-hosted LLMs.

github

: 617

langserve

LangServe helps developers deploy `LangChain` runnables and chains as a REST API. This library is integrated with FastAPI and uses pydantic for data validation. In addition, it provides a client that can be used to call into runnables deployed on a server. A JavaScript client is available in LangChain.js.

github

: 1.9k

gemini-pro-bot

This Python Telegram bot utilizes Google's `gemini-pro` LLM API to generate creative text formats based on user input. It's designed to be an engaging and interactive way to explore the capabilities of large language models. Key features include generating various text formats like poems, code, scripts, and musical pieces. The bot supports real-time streaming of the generation process, allowing users to witness the text unfold. Additionally, it can respond to messages with Bard's creative output and handle image-based inputs for multimodal responses. User authentication is optional, and the bot can be easily integrated with Docker or installed via pipenv.

github

: 130

llm-functions

LLM Functions is a project that enables the enhancement of large language models (LLMs) with custom tools and agents developed in bash, javascript, and python. Users can create tools for their LLM to execute system commands, access web APIs, or perform other complex tasks triggered by natural language prompts. The project provides a framework for building tools and agents, with tools being functions written in the user's preferred language and automatically generating JSON declarations based on comments. Agents combine prompts, function callings, and knowledge (RAG) to create conversational AI agents. The project is designed to be user-friendly and allows users to easily extend the capabilities of their language models.

github

: 263

pacha

Pacha is an AI tool designed for retrieving context for natural language queries using a SQL interface and Python programming environment. It is optimized for working with Hasura DDN for multi-source querying. Pacha is used in conjunction with language models to produce informed responses in AI applications, agents, and chatbots.

github

: 75

aio-theme

github

: 71

log10

Log10 is a one-line Python integration to manage your LLM data. It helps you log both closed and open-source LLM calls, compare and identify the best models and prompts, store feedback for fine-tuning, collect performance metrics such as latency and usage, and perform analytics and monitor compliance for LLM powered applications. Log10 offers various integration methods, including a python LLM library wrapper, the Log10 LLM abstraction, and callbacks, to facilitate its use in both existing production environments and new projects. Pick the one that works best for you. Log10 also provides a copilot that can help you with suggestions on how to optimize your prompt, and a feedback feature that allows you to add feedback to your completions. Additionally, Log10 provides prompt provenance, session tracking and call stack functionality to help debug prompt chains. With Log10, you can use your data and feedback from users to fine-tune custom models with RLHF, and build and deploy more reliable, accurate and efficient self-hosted models. Log10 also supports collaboration, allowing you to create flexible groups to share and collaborate over all of the above features.

github

: 96

For similar tasks

raycast_api_proxy

github

: 317

lollms-webui

LoLLMs WebUI (Lord of Large Language Multimodal Systems: One tool to rule them all) is a user-friendly interface to access and utilize various LLM (Large Language Models) and other AI models for a wide range of tasks. With over 500 AI expert conditionings across diverse domains and more than 2500 fine tuned models over multiple domains, LoLLMs WebUI provides an immediate resource for any problem, from car repair to coding assistance, legal matters, medical diagnosis, entertainment, and more. The easy-to-use UI with light and dark mode options, integration with GitHub repository, support for different personalities, and features like thumb up/down rating, copy, edit, and remove messages, local database storage, search, export, and delete multiple discussions, make LoLLMs WebUI a powerful and versatile tool.

github

: 4.5k

daily-poetry-image

Daily Chinese ancient poetry and AI-generated images powered by Bing DALL-E-3. GitHub Action triggers the process automatically. Poetry is provided by Today's Poem API. The website is built with Astro.

github

: 492

InvokeAI

InvokeAI is a leading creative engine built to empower professionals and enthusiasts alike. Generate and create stunning visual media using the latest AI-driven technologies. InvokeAI offers an industry leading Web Interface, interactive Command Line Interface, and also serves as the foundation for multiple commercial products.

github

: 24.3k

LocalAI

LocalAI is a free and open-source OpenAI alternative that acts as a drop-in replacement REST API compatible with OpenAI (Elevenlabs, Anthropic, etc.) API specifications for local AI inferencing. It allows users to run LLMs, generate images, audio, and more locally or on-premises with consumer-grade hardware, supporting multiple model families and not requiring a GPU. LocalAI offers features such as text generation with GPTs, text-to-audio, audio-to-text transcription, image generation with stable diffusion, OpenAI functions, embeddings generation for vector databases, constrained grammars, downloading models directly from Huggingface, and a Vision API. It provides a detailed step-by-step introduction in its Getting Started guide and supports community integrations such as custom containers, WebUIs, model galleries, and various bots for Discord, Slack, and Telegram. LocalAI also offers resources like an LLM fine-tuning guide, instructions for local building and Kubernetes installation, projects integrating LocalAI, and a how-tos section curated by the community. It encourages users to cite the repository when utilizing it in downstream projects and acknowledges the contributions of various software from the community.

github

: 29.8k

classifai

Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

github

: 595

StableSwarmUI

StableSwarmUI is a modular Stable Diffusion web user interface that emphasizes making power tools easily accessible, high performance, and extensible. It is designed to be a one-stop-shop for all things Stable Diffusion, providing a wide range of features and capabilities to enhance the user experience.

github

: 2.7k

civitai

Civitai is a platform where people can share their stable diffusion models (textual inversions, hypernetworks, aesthetic gradients, VAEs, and any other crazy stuff people do to customize their AI generations), collaborate with others to improve them, and learn from each other's work. The platform allows users to create an account, upload their models, and browse models that have been shared by others. Users can also leave comments and feedback on each other's models to facilitate collaboration and knowledge sharing.

github

: 6.3k

For similar jobs

sweep

Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

github

: 7.1k

teams-ai

The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

github

: 390

ai-guide

This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

github

: 159

classifai

github

: 595

chatbot-ui

Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

github

: 27.7k

BricksLLM

BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

github

: 953

uAgents

uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

github

: 1.2k

griptape

Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.

github

: 2.1k

raycast_api_proxy

README:

Raycast AI Proxy

Introduction

How It Works (Man-in-the-Middle)

YAML-Based Model Configuration

Ai chat

Translate

Image Generation

Usage

Installation and Configuration

1. Generate Certificate

2. Add Certificate to System Keychain

3. Modify /etc/host to add the following lines

4. Launch the service

Advanced Configuration

1. Using Azure OpenAI API

2. Google Gemini API

3. Local Manual Run

4. Local Development

5. Using Custom Mapping

6. Multi-User Shared Service

Notes

Roadmap

For Tasks:

For Jobs:

Alternative AI tools for raycast_api_proxy

Similar Open Source Tools

raycast_api_proxy

chatgpt-cli

BodhiApp

ethereum-etl-airflow

llm-vscode

LEADS

Construction-Hazard-Detection

sandbox

tiledesk-dashboard

holmesgpt

langserve

gemini-pro-bot

llm-functions

pacha

aio-theme

log10

For similar tasks

raycast_api_proxy

lollms-webui

daily-poetry-image

InvokeAI

LocalAI

classifai

StableSwarmUI

civitai

For similar jobs

sweep

teams-ai

ai-guide

classifai

chatbot-ui

BricksLLM

uAgents

griptape

3. Modify `/etc/host` to add the following lines