Agenta-AI/awesome-ai-agent-platforms

A curated list of open-source AI agent platforms: AI coworkers and teammates, agent builders and frameworks, workflow automation platforms, browser agents, and coding agents, with licenses.

What it solves

This project addresses the challenge of discovering and comparing open-source AI agent platforms. It provides a structured, up-to-date list of tools for building, running, and automating AI agents, with key details about each entry's license and hosting model.

How it works

The project is a curated list on GitHub, organized into five categories: AI coworkers and teammates, agent builders and frameworks, workflow automation platforms, browser agents, and coding agents. Each entry links to the official repository or product page and includes a one-sentence description, the current license, and hosting options. The README also specifies selection criteria (active repository, usable product, verifiable license, maintained) and encourages contributions via pull requests. A companion website, aiagentplatforms.dev, offers a full comparison table.

Who it’s for

Developers, researchers, and teams evaluating or building with AI agents will find this list useful for quickly scanning options, checking licensing constraints, and understanding hosting choices. It also serves as a reference for anyone wanting to grasp the breadth of open-source agent tooling.

Highlights

  • Covers 50+ platforms across five practical categories (coworkers, builders, workflow automation, browser agents, coding agents).
  • Each entry includes license and hosting notes, saving time on due diligence.
  • Clear selection criteria ensure listed projects are active, usable, and well-documented.
  • Contribution guidelines make it easy for the community to add or update entries.
  • A companion website (aiagentplatforms.dev) provides a full comparison table for side-by-side review.

Related

  • Project
    zhongyu09/openchatbi

    OpenChatBI is an open‑source, LLM‑driven chat interface for business intelligence. It turns natural‑language questions into SQL, runs them against your data warehouse, and returns results with Plotly visualisations. Built on LangGraph/LangChain, it includes a data‑catalog, optional vector retrieval, forecasting, anomaly detection, Python code execution, persistent conversation memory, and optional human‑in‑the‑loop gating. Install via `uv sync` or `pip`, configure LLM and database credentials, and launch the provided Gradio or Streamlit UI.

  • Project
    oneshot-agent/oneshot-gtm

    oneshot‑gtm is a locally‑run, TypeScript‑based outbound‑sales tool for early‑stage founders. It watches public signals, filters prospects against a user‑defined ICP, drafts personalized messages with an LLM you provide, and sends them via email, LinkedIn, SMS, voice or physical mail. Every API call is recorded with a signed receipt, and all data lives in a local SQLite ledger. The stack uses Bun, Vite + React for the dashboard, and the @oneshot‑agent/sdk for communications.

  • Project
    MORTEN-BUUR/nordef-matrix-open-control

    A model-independent safety control plane for AI agents that enforces deterministic policies and cryptographic human approval outside the language model.

  • Project
    microsoft/copilot-camp

    Copilot Developer Camp is a virtual workshop repo with hands-on learning paths for developers building agents and connectors for Microsoft 365 Copilot. It covers declarative agents, custom engine agents, Copilot Cowork extensibility, and SharePoint agents, with both no-code and pro-code options.