[opensourcedex]

ACI.dev is a free, open source integration platforms project written in Python and released under Apache-2.0. It has 4,891 GitHub stars, 485 forks and 63 open issues, and was last pushed 4 months ago. On this registry it ranks #3 of 5 tracked projects in Integration Platforms, with 5 head-to-head comparisons available. It gained 3 stars over the last 6 tracked days.

What is ACI.dev?

What it is

ACI.dev is an open-source tool-calling platform that connects more than 600 tools to any agentic IDE or custom AI agent. It lives in the Python ecosystem and is released under the Apache-2.0 license, with the backend, developer portal, and integrations all published as open source. Agents reach tools either through direct function calling or through a Unified Model-Context-Protocol (MCP) server, and the same capabilities are also exposed through a lightweight Python SDK and a TypeScript SDK that work with any LLM framework.

The concrete problem it solves is the integration tax that every agent builder pays. Instead of writing separate OAuth flows, API clients, and permission checks for services such as Google Calendar, Slack, Vercel, Supabase, Cloudflare, and Sentry, a developer points the agent at ACI.dev and lets the platform manage authentication and expose unified, secure function calls. It also addresses two reliability problems that appear once agents scale: context windows that get overwhelmed by too many tool definitions, and permission models that are too coarse to trust. ACI.dev answers both with dynamic tool discovery and natural-language permission boundaries.

Key capabilities

  • 600+ pre-built integrations that connect agents to popular services and apps.
  • Two access paths: a Unified MCP server and a lightweight SDK for direct function calling.
  • Multi-tenant authentication with built-in OAuth flows and secrets management for developers and end-users.
  • Natural-language permission boundaries that define what an agent is allowed to do.
  • Dynamic tool discovery that finds relevant tools without flooding the LLM context window.
  • Tool-use logging that records how an agent called tools and where it ran into issues.
  • Framework and model agnostic design, so agents are not locked to a single vendor or architecture.

Who uses it and how

  • VibeOps teams let an agentic IDE reach Vercel, Supabase, Cloudflare, and Sentry to provision, deploy, configure databases, and debug, turning a prototype into a live product.
  • Personal assistant chatbots use it to search the web, manage calendars, send email, and interact with SaaS tools.
  • Research agents conduct research on a topic and sync results into apps such as Notion and Google Sheets.
  • Outbound sales agents automate lead generation, email outreach, and CRM updates.
  • Customer support agents answer questions, manage tickets, and take actions based on customer queries.

Getting started

The README points to a managed service at aci.dev, documentation at aci.dev/docs, and a tools list at aci.dev/tools. Developers can also use the Python SDK, the TypeScript SDK, or the Unified MCP server, and configure the MCP with platforms such as Vercel, Supabase, and Cloudflare

project readme (upstream, from github) — read inline

ACI: Open-Source Infra to Power Unified MCP Servers and VibeOps

aipotheosis-labs%2Faci | Trendshift

Documentation PyPI version License Discord Twitter Follow

[!NOTE] This repo is for the ACI.dev platform. If you're looking for the Unified MCP server built with ACI.dev, see aci-mcp.

ACI.dev is the open-source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent. It gives agents intent-aware access to tools with multi-tenant auth, granular permissions, and dynamic tool discovery—exposed as either direct function calls or through a Unified Model-Context-Protocol (MCP) server.

Examples: Instead of writing separate OAuth flows and API clients for Google Calendar, Slack, and more, use ACI.dev to manage authentication and provide AI agents with unified, secure function calls. Access these capabilities through our Unified MCP server or via our lightweight Python SDK, compatible with any LLM framework.

Supercharge vibe coding and automate devOps by adding a single unified MCP server to your favourite agentic IDE. Configure the MCP with Vercel, Supabase, Cloudflare, and other platforms. Let AI handle provisioning, deployment, database configs, and debugging to turn a vibe coded prototype into a live product.

ACI.dev Architecture

Join us on Discord to help shape the future of Open Source AI Infrastructure and VibeOps.

🌟 Star ACI.dev to stay updated on new releases!

GitHub Stars

📺 Demo Video

ACI.dev Unified MCP Server Demo

ACI.dev Unified MCP Server Demo

ACI.dev VibeOps Demo

ACI.dev VibeOps Demo

✨ Key Features

  • 600+ Pre-built Integrations: Connect to popular services and apps in minutes.
  • Flexible Access Methods: Use our unified MCP server or our lightweight SDK for direct function calling.
  • Multi-tenant Authentication: Built-in OAuth flows and secrets management for both developers and end-users.
  • Enhanced Agent Reliability: Natural language permission boundaries and dynamic tool discovery.
  • Framework & Model Agnostic: Works with any LLM framework and agent architecture.
  • 100% Open Source: Everything released under Apache 2.0 (backend, dev portal, integrations).

💡 Why Use ACI.dev?

ACI.dev improves tool-calling reliability and accountability:

  • Authentication at Scale: Connect multiple users to multiple services securely.
  • Discovery Without Overload: Find and use the right tools without overwhelming LLM context windows.
  • Natural Language Permissions: Control agent capabilities with human-readable boundaries.
  • Tool-use Logging: See how your agent called tools and the issues it ran into.
  • Build Once, Run Anywhere: No vendor lock-in with our open source, framework-agnostic approach.

🧰 Common Use Cases

  • VibeOps: Automate devOps by letting your agentic IDE access Vercel, Supabase, Cloudflare, Sentry and more to ship live products.
  • Personal Assistant Chatbots: Build chatbots that can search the web, manage calendars, send emails, interact with SaaS tools, etc.
  • Research Agent: Conducts research on specific topics and syncs results to other apps (e.g., Notion, Google Sheets).
  • Outbound Sales Agent: Automates lead generation, email outreach, and CRM updates.
  • Customer Support Agent: Provides answers, manages tickets, and performs actions based on customer queries.

🔗 Quick Links

💻 Getting Started: Local Development

To run the full ACI.dev platform (backend server and frontend portal) locally, follow the individual README files for each component:

👋 Contributing

We welcome contributions! Please see our CONTRIBUTING.md for more information.

Integration Requests

Missing any integrations (apps or functions) you need? Please see our Integration Request Template and submit an integration request! Or, if you're feeling adventurous, you can submit a PR to add the integration yourself!

Star History

Star History Chart

Frequently asked questions

Is ACI.dev free to use?

ACI.dev is open source under the Apache-2.0 licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does ACI.dev do?

Build reliable AI agents with unified tool integration

What is ACI.dev written in?

ACI.dev is primarily written in Python. Its source is publicly available at https://github.com/aipotheosis-labs/aci, and it has 4,891 GitHub stars.