Loading page
44 sản phẩm
A mobile drafting desk that turns approved account facts into three editable sales-email approaches while the human keeps the send decision.
AI tool that generates smart pricing strategies, packages, competitor positioning and profit-maximizing offers.
This tool helps users organize their day more efficiently by turning simple inputs like tasks, goals, and deadlines into a clear, optimized plan. Instead of just listing tasks, it intelligently prioritizes what matters most and suggests how to allocate time throughout the day. The goal is to reduce decision fatigue and help users stay focused on high-impact work with a structured, easy-to-follow schedule.
Invoicing and client portal app for freelancers and small agencies. Send branded PDF invoices, accept Stripe/PayPal payments, and give each client a private login. React frontend + Express API.
Full-stack TypeScript job board with Express backend, React frontend, SQLite database, JWT authentication, and role-based access for employers and jobseekers. Features job listings, applications tracking, and Zod validation across both layers. Licensed under Tetrees License.
Idea Clustering Board
Backend API for AI Decision Simulator with outcome, risk analysis, confidence score, and suggestions
SaaS pricing calculator
Express backend API for OpenAI chat completions with two configurable model slots (GPT-5.3 and GPT-5.4). Routes chat requests to gpt-4o or gpt-4o-mini with full parameter control (temperature, max_tokens, top_p, penalties). Includes health checks, model introspection endpoints, and structured error handling. Built in TypeScript with CORS support and environment-based configuration.
4.8 (25)
A floating or embedded chat box you drop into any website. User types a message, it sends to OpenAI, streams the reply back in real time. Buyers use it to add a chatbot to their product without building one from scratch.et
Express.js backend service for LLM applications that ingests documents, conversations, and behavioral events to build a persistent, queryable memory system for users. Features Claude-powered extraction of structured memories, full-text search, entity profiles with timelines, and a query API that returns contextual bundles for RAG pipelines. Built for multi-tenant deployments with versioned memory records and audit trails.
4.8 (30)
Flowise is an open-source, low-code platform for building and deploying AI agent workflows visually. It provides a drag-and-drop canvas, runtime observability, REST APIs, and Docker-ready deployment for developers and teams.
Build production-ready conversational AI applications with a Python backend and React hooks client. Supports WebSocket sessions, tool steps, chat profiles, and integrations with OpenAI, LangChain, and more.
A curated collection of ready-to-deploy Appwrite function templates spanning 14 runtimes, covering AI integrations, search sync, messaging bots, payments, and more.
Train GPT-2 and GPT-3 class language models in pure C and CUDA with no PyTorch or Python runtime required. Designed for researchers and engineers who want fast, readable, low-dependency LLM pretraining from scratch.
Agno is a full-stack framework for building, running, and managing AI agent platforms with multi-agent teams, RAG, memory, guardrails, and a production-ready FastAPI runtime with 50+ endpoints.
A fully typed TypeScript/JavaScript client library for the Together AI REST API, supporting chat completions, streaming responses, automatic retries, and configurable logging for server-side applications.
Revstack is an open-source billing platform that handles subscriptions, entitlements, usage metering, and payment provider abstraction. Define pricing models as code, deploy via CLI, and gate features in milliseconds across Node, Next.js, and React.
Official Node.js library for the Recurly V3 API, enabling developers to integrate subscription management, billing, and payment workflows into backend applications.
A single TypeScript API for LLMs, embeddings, and image generation across 10+ providers including OpenAI, Anthropic, Google, Groq, and Ollama. Supports streaming, tools, structured output, multimodal input, and reasoning.
A comprehensive TypeScript monorepo for interacting with the Hugging Face Hub, running inference across 100,000+ models, building AI agents with MCP tool use, and parsing ML model formats like GGUF and DDUF.
Mastra is a TypeScript framework for building production-ready AI agents, workflows, and applications. It includes model routing, browser automation, auth integrations, observability exporters, and multi-platform deployers.
Manifest is a smart model router for AI agents and applications that redirects each query to the most appropriate model, cutting AI costs by up to 70% across 300+ models and 16 providers.
Manifest is a smart AI model router that redirects each query to the right model based on complexity and custom rules, cutting AI costs by up to 70%. Supports 300+ models across 16 providers including OpenAI, Anthropic, Google, and local models.