diegosouzapw/OmniRoute
OmniRoute is a free AI gateway that consolidates over 237 AI providers, including 90+ free tiers, into a single endpoint, offering token compression and smart auto-fallback for various AI tools.
Awesome AI Agents › AI Agent Gateway
OmniRoute is a free AI gateway that consolidates over 237 AI providers, including 90+ free tiers, into a single endpoint, offering token compression and smart auto-fallback for various AI tools.
Sim Studio is an open-source platform for building, testing, and optimizing AI agent workflows with flexible deployment options including cloud and self-hosting.
9Router is a FREE AI router and token saver that connects various AI coding tools to over 40 providers and 100+ models, with features like auto-fallback and token compression.
Mastra is a TypeScript AI agent framework that enables rapid development of AI applications with support for multiple LLMs, advanced agents, workflows, RAG, integrations, and automated evaluations.
SuperAGI is an open-source autonomous AI agent framework that enables developers to build, manage, and deploy scalable and efficient autonomous AI agents with extensible capabilities through toolkits and a user-friendly interface.
Casdoor is an open-source, AI-first Identity and Access Management (IAM) / LLM MCP gateway and authentication server with a web UI and broad protocol support.
Phoenix is an open-source AI observability platform that enables tracing, evaluation, and optimization of large language model applications across various deployment environments.
Open-source product integration platform with a single REST API syntax for connecting agents, backend services, and dashboards to third-party apps.
Upsonic is a reliability-focused AI agent framework that supports Model Context Protocol (MCP) and provides advanced features for trustworthy, production-ready AI agent workflows with integrated tool use and secure runtime environments.
Superagent is an open-source AI assistant framework and API that enables developers to build and integrate powerful AI agents into applications using large language models and generative AI technologies.
Fragments by E2B is an open-source Next.js template for building AI-generated applications with secure code execution, multi-stack support, and integration with various large language model providers.
Cloudflare Agents is a framework for building and deploying intelligent, stateful AI agents that operate autonomously at the edge of the network with real-time communication and persistent memory.
Go AI gateway that translates any SDK request into any provider format, adding request tracing, role-based access control, load balancing with failover and per-request cost tracking.
OpenAgents is an open platform providing versatile language agents for data analysis, plugin integration, and autonomous web browsing, designed for real-world applications and easy deployment.
Multi-tenant AI agent gateway written in Go that runs agent teams over 20+ LLM providers and seven messaging channels from a single static binary backed by PostgreSQL.
Dev-GPT is an AI-powered automated virtual development team that generates, runs, and deploys custom microservices based on user descriptions using advanced OpenAI models.
MCPJungle is a self-hosted gateway that registers many MCP servers behind one endpoint, giving AI clients and agents unified tool discovery, access control and observability.
Apache-2.0 control plane that registers MCP servers, agents and skills, then exposes them through one authenticated gateway with natural-language discovery, access control and audit logging.
Golf is a production-ready MCP server framework that simplifies building, deploying, and scaling secure AI agent infrastructure with built-in support for authentication, observability, debugging, telemetry, and runtime management.
HermesClaw is a Python gateway that becomes the sole WeChat iLink poller and proxies messages so Hermes Agent, OpenClaw and OpenCode can share one WeChat account without token conflicts.
WorkGPT is a versatile GPT agent framework that enables conversational AI to invoke and interact with multiple APIs using OpenAPI specifications to complete complex directives.
AWS Secrets Manager Agent is a local HTTP service that caches secrets from AWS Secrets Manager in memory, enabling secure and efficient secret retrieval for applications across various AWS compute environments.
LLM gateway written in Node that sits between coding agents and 14 providers, cutting token usage through tool stripping and JSON compression, routing requests by complexity and serving semantic cache hits.
Source-available Go control plane that governs what AI agents are allowed to do: a safety kernel returns allow, deny or require-approval verdicts on every job, with an API gateway, workflow engine, dashboard and a Claude Code hook.
Centralized proxy and management platform for Model Context Protocol servers, letting one endpoint install, group, monitor and serve MCP services to agent clients, with a Go backend and React web interface.
deco Studio is an open-source, self-hostable control plane that puts organisation-wide AI agents, MCP connections, model routing, SSO, RBAC, audit logs and cost tracking behind a single MCP endpoint.
A repository providing official and community examples demonstrating how to use the Restack AI Python SDK with setup instructions and Docker support.
OCSInventory-ocsreports is a web console for OCS Inventory NG that enables centralized asset management, network discovery, and software deployment across large IT infrastructures.
LangChain.js MCP Adapters provide integration adapters for connecting Model Context Protocol tools with LangChain.js applications, supporting multiple transport methods and multi-server management.
A TypeScript toolkit for interacting with Bitcoin and Stacks blockchains, offering wallet management, smart contract interactions, and blockchain operations.