Search Results for "backend" - Page 4
Sort By:
Showing 220 open source projects for "backend"
View related business solutions-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
1
WhisperLive
A nearly-live implementation of OpenAI's Whisper
WhisperLive is a “nearly live” implementation of OpenAI’s Whisper model focused on real-time transcription. It runs as a server–client system in which the server hosts a Whisper backend and clients stream audio to be transcribed with very low delay. The project supports multiple inference backends, including Faster-Whisper, NVIDIA TensorRT, and OpenVINO, allowing you to target GPUs and different CPU architectures efficiently. It can handle microphone input, pre-recorded audio files, and network streams such as RTSP and HLS, making it flexible for live events, monitoring, or accessibility workflows. ... -
2
LangChain for Java
LangChain4j is an open-source Java library
LangChain for Java is an open-source Java framework designed to simplify the development of applications powered by large language models. The library provides a unified API that allows developers to connect Java applications to multiple AI providers and embedding databases without having to implement separate integrations for each service. Its architecture includes abstractions for prompts, chat interactions, document processing, embeddings, and vector storage, enabling developers to build... -
3
Cheshire Cat AI
AI agent microservice
Cheshire Cat AI Core is an open-source framework for building customizable AI agents as scalable microservices, designed to integrate conversational intelligence into applications through an API-first architecture. It allows developers to create advanced AI assistants that can interact through WebSockets, REST APIs, and embedded chat interfaces, making it suitable for both backend services and user-facing applications. The framework includes built-in support for retrieval-augmented generation using vector databases such as Qdrant, enabling agents to incorporate external knowledge and documents into their responses. It is highly extensible through a plugin system that supports custom tools, event hooks, and workflows, giving developers fine-grained control over agent behavior and interactions. ... -
4
Open Interface
Control Any Computer Using LLMs
Open Interface is a cross-platform application that allows users to control their computers using large language models (LLMs). By sending user requests to an LLM backend, it determines the necessary steps and executes them by simulating keyboard and mouse inputs. The system can adjust its actions based on real-time feedback, providing a self-driving computer experience. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
React Native AI
Full stack framework for building cross-platform mobile AI apps
...It supports real-time streaming responses from multiple AI providers and enables developers to build chat interfaces, AI-driven image generation tools, and natural language features within mobile apps. The framework includes backend components such as an Express-based server proxy that handles authentication and API communication with model providers. Developers can also integrate multiple models and services through a unified interface, making it easier to experiment with different AI capabilities. Built-in theming and UI templates allow developers to quickly create polished interfaces for AI chat and generative features. -
6
Farfalle
AI search engine - self-host with local or cloud LLMs
...It can run either with local language models or with cloud-based providers, allowing developers to deploy it privately or integrate with hosted AI services. The architecture separates the frontend and backend, using modern web technologies such as Next.js and FastAPI to deliver an interactive interface and scalable server logic. Farfalle also includes an agent-based search workflow that plans queries and executes multiple search steps to produce more accurate results than traditional keyword searches. The system supports multiple external search providers and integrates caching and rate-limiting mechanisms to maintain reliability during heavy usage. -
7
OpenAI CS Agents Demo
Demo of a customer service use case implemented with the OpenAI Agents
This repository is a customer service agent demo built using the OpenAI Agents SDK to showcase how to build a production-style conversational assistant for use cases like airline customer support. It consists of two major parts: a Python backend that orchestrates agent logic (tool calls, handoffs, memory, routing) and a Next.js UI for chat interaction and visualizing agent state. The demo covers tasks you’d expect in customer service: changing flights, checking status, answering FAQs, etc. It shows how multiple subagents can be coordinated under a triage agent that decides which specialized agent should handle a given request. ... -
8
OpenAI Realtime Agents
This is a simple demonstration of more advanced, agentic patterns
...The SDK offers abstractions such as agent orchestration, event handling, handoffs, state management, and guardrails, tailored to support realtime, conversational systems. The demo includes a Next.js frontend for browser interaction and likely a backend component to orchestrate realtime sessions and agent logic. It also supports a “Chat-Supervisor” pattern where a lightweight realtime chat agent handles user interactions and delegates more complex reasoning or tool usage to a stronger textual model (e.g. GPT-4). Because realtime agents are still a beta feature, the code and API surface are subject to changes and may evolve. -
9
Switchyard
Switchyard lets LLM applications route traffic across models
Switchyard is a Rust proxy and library for routing traffic between LLM clients and model backends. It translates among OpenAI Chat, OpenAI Responses, and Anthropic Messages formats so agents can keep using their native APIs. Requests can be distributed across vLLM, NVIDIA NIM, Ollama, OpenRouter, and other compatible endpoints. Routing strategies include random splits, LLM classification, signal-driven stage routing, escalation, and custom algorithms. Prometheus metrics track requests,... -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
xiaogpt
Play ChatGPT and other LLM with Xiaomi AI Speaker
xiaogpt is a Python project that connects Xiaomi AI speakers with ChatGPT and other large language models. It lets users turn compatible XiaoAI speaker devices into conversational AI assistants beyond the default built-in voice capabilities. The project works by listening for user interactions, forwarding prompts to supported model providers, and sending generated responses back through the speaker. It supports multiple operating modes, wake-word styles, and model backends depending on the... -
11
Agent Development Kit (ADK)
Open-source, code-first Python toolkit for building, evaluating, etc.
ADK (Android Device Key) Python is a reference implementation by Google for working with Android attestation keys in Python. It facilitates the integration of Android attestation features into backends or systems that require verification of device identity and integrity. This is especially important in high-security applications where verifying that a device is genuine and uncompromised is critical. ADK Python helps developers verify hardware-backed keys, work with JSON Web Tokens (JWT),... -
12
AutoClip
AI-powered video clipping and highlight generation
AutoClip is an open-source, AI-powered video processing system designed to automate the extraction of “highlight” segments from full-length videos — ideal for creators who want to generate bite-sized clips, compilations, or highlight reels without manually sifting through hours of footage. The system supports downloading videos from major platforms (e.g. YouTube, Bilibili), or accepting local uploads, and then applies AI analysis to identify segments worth clipping based on content (e.g.... -
13
Quadratic
Data science spreadsheet with Python & SQL
...Our goal is to build a spreadsheet that enables you to pull your data from its source (SaaS, Database, CSV, API, etc) and then work with that data using the most popular data science tools today (Python, Pandas, SQL, JS, Excel Formulas, etc). Quadratic has no environment to configure. The grid runs entirely in the browser with no backend service. This makes our grids completely portable and very easy to share. Quadratic has Python library support built-in. Bring the latest open-source tools directly to your spreadsheet. Quickly write code and see the output in full detail. No more squinting into a tiny terminal to see your data output. -
14
caveman
Why use many token when few token do trick
Caveman is a lightweight and experimental project focused on simplifying backend or full-stack development workflows through minimalistic abstractions and rapid prototyping principles. It is designed to reduce the complexity of modern frameworks by offering a stripped-down approach that prioritizes speed, clarity, and ease of use. The project often serves as a foundation for developers who want to build applications quickly without being constrained by heavy conventions or extensive configuration. ... -
15
ChatTTS webUI & API
A simple native web interface that uses ChatTTS to synthesize text
ChatTTS-ui is a local web interface and API wrapper around the ChatTTS speech synthesis system, designed to make advanced TTS models easy to use from a browser. It runs a small backend server (Python + Torch + ffmpeg) and exposes a simple webpage where you can type text, adjust parameters, and generate audio. The project supports Chinese, English, and mixed text with digits and control symbols, making it suitable for bilingual content and numerically heavy text like announcements or prompts. From version 0.96 onward, ffmpeg installation is required for deployment, and previous CSV/PT voice tables are no longer valid, so users instead work with updated “voice value” parameters. ... -
16
deepclaude
Use Claude Code's agent loop with DeepSeek V4 Pro, OpenRouter & more
...By swapping out the underlying model instead of the interface, deepclaude delivers the same familiar UX with significantly cheaper token pricing. The platform supports seamless backend switching in real time, allowing users to choose between cost efficiency and higher reasoning power when needed. It also includes built-in cost tracking and benchmarking tools to help developers monitor usage and optimize performance. Designed for flexibility and efficiency, deepclaude is ideal for developers who want powerful AI coding agents without the premium price tag. -
17
HelixDB
Graph-vector database for building unified AI backends fast
...HelixDB is built from scratch in Rust and uses LMDB as its storage engine, enabling high performance and low-latency query execution. HelixDB also supports additional data formats such as key-value, document, and relational data, making it flexible for a wide range of backend architectures. A central feature of the project is its custom query language, HelixQL, which is fully type-safe and compiled to ensure reliability and correctness in production environments. HelixDB includes built-in capabilities for embeddings, vector search, keyword search, and graph traversal, which are particularly useful for retrieval-augmented generation and agent-based systems. -
18
Antigravity Kit
AI Agent templates with Skills, Agents, and Workflows
Antigravity Kit is an AI agent capability expansion toolkit that provides structured templates, skills, and workflows designed to boost the productivity of AI assistants and autonomous agents in coding environments. It comes with an extensive library of predefined agent personas and domain-specific skills that help in performing targeted tasks such as frontend development, backend engineering, quality assurance, and more. With this kit, developers can rapidly initialize a project scaffold and gain access to specialist agents and command workflows that guide the agent through multi-step tasks and slash-command procedures. The repository follows a clear pattern for defining agents and their behaviors, making it easier to extend with new skills or tailor existing ones to your use case. ... -
19
MagicMirror²
Modular smart mirror platform with a list of installable modules
...Share your ideas, ask your questions and get support. The perfect place for you to start. MagicMirror² has an extensively documentated API. It allows you to built your own module backed by a powerful backend. Check out the API documentation for more information and start developing today. -
20
AutoCVE
Agent-driven automated CVE discovery platform for source code auditing
...Vulnerabilities are deduplicated and stored in a structured management system, while configurable skills extend individual agents. The platform uses a React frontend, FastAPI backend, PostgreSQL database, and Docker-based deployment. -
21
ChatGPT Exporter
Export and Share your ChatGPT conversation history
ChatGPT Exporter is a browser-based userscript tool designed to export ChatGPT conversations into multiple structured and shareable formats, enabling users to preserve, analyze, and reuse AI-generated content outside the ChatGPT interface. It integrates directly into the ChatGPT web environment, typically via tools like Tampermonkey, and adds export functionality without requiring backend services or complex setup. The tool supports a wide range of output formats including plain text, HTML, Markdown, JSON, and even image-based exports, making it suitable for documentation, knowledge management, and data analysis workflows. One of its key strengths is its ability to preserve formatting such as code blocks, tables, and structured responses, ensuring that exported content remains usable and readable. ... -
22
Pinchtab
High-performance browser automation bridge and orchestrator
Pinchtab is a lightweight browser automation backend built specifically for AI agents that need efficient, programmatic web control. Implemented as a small standalone HTTP server, it allows any agent or script to interact with web pages using simple API calls instead of heavyweight browser frameworks. The tool emphasizes accessibility-first snapshots that dramatically reduce token usage compared to screenshot-based approaches, making it cost-effective for large-scale automation. ... -
23
AstrBot
Agentic IM Chatbot infrastructure
AstrBot is an AI-driven chatbot framework designed to help developers build intelligent conversational agents that can be deployed across multiple messaging environments. The project focuses on modular architecture so users can extend the bot with plugins, custom skills, and integrations without modifying the core engine. It is built to support modern large language model workflows, enabling natural language understanding, automated responses, and task execution within chat contexts. AstrBot... -
24
ComfyUI-LTXVideo
LTX-Video Support for ComfyUI
ComfyUI-LTXVideo is a bridge between ComfyUI’s node-based generative workflow environment and the LTX-Video multimedia processing framework, enabling creators to orchestrate complex video tasks within a visual graph paradigm. Instead of writing code to apply effects, transitions, edits, and data flows, users can assemble nodes that represent video inputs, transformations, and outputs, letting them prototype and automate video production pipelines visually. This integration empowers... -
25
Taskmaster
An AI-powered task-management system
...It uses structured task formats and orchestration logic to coordinate how AI assistants plan and complete work. The system supports multiple model providers through configurable keys, allowing teams to choose their preferred AI backend. Its goal is to bring discipline and repeatability to agent-assisted coding by turning loosely defined prompts into organized execution plans. Overall, Claude Task Master functions as a productivity and orchestration layer for developers working with AI coding assistants.
