Open Source Alternatives to Agency

An open-source platform for building and running AI coding agents that automate software development tasks.

An open-source framework for building, operating, and benchmarking Multimodal Language Model (MLM) agents across diverse environments.

IronClaw is a security-first, open-source AI agent framework that runs agents in encrypted environments, protecting sensitive credentials.

Experimental open-source framework for building self-building autonomous agents with a novel function framework.

An open-source platform for creating, managing, and interacting with AI workflows and agents.

Adala is an Autonomous DAta (Labeling) Agent framework for data processing and labeling tasks.

Open-source infrastructure for coding agents, enabling AI to plan, generate, and deploy software autonomously.

Open-source community discovering scaling laws of intelligent agents for data generation, world simulation, and task automation.

An AI deep research API and web console that generates adversarially reviewed reports with verified citations and stores sources in a persistent, searchable vault.

Open-source framework enabling autonomous AI agents to make frictionless web3 payments via web2 infrastructure.

Simulates 1,000 LLM-powered agents for diverse movie recommendation preferences.

Open-source Python framework for building autonomous AI agents and agentic workflows, purpose-built for FinTech operations.

Cisco's internal incubation engine for emerging technologies like agentic AI and quantum networking.

Open-source AI platform for securely deploying intelligent agents, private enterprise search, and complex document workflows on an organization's own data.

An open-source, autonomous AI agent for complex tasks using terminal, browser, and editor interactions.

Developing advanced AI models with a focus on reducing hallucinations, including large language models, vision language models, and text-to-video models.

Cloud-based browser API for AI agents, simplifying web automation with anti-bot protection and session persistence.

Elementary Data provides a unified data control plane for the AI era, offering observability, quality, governance, and discovery for data and AI reliability.

An open-source technology provider offering an open control plane for AI agents.

Track experiments, validate models, and collaborate with confidence using Skore, the methodology layer for AI coding tools.

An open-source platform enabling enterprises to securely connect sensitive data to AI agents.

An open-source, end-to-end AI agent engineering platform for simulating, evaluating, and optimizing LLM applications.

Cua provides an open-source framework and cloud desktops for AI agents to control operating systems and desktop applications across Linux, Windows, macOS, and Android.

Open-source AI agent framework for automating tasks across messaging platforms and software systems.

Open-source infrastructure, developer tools, and research for agent runtimes.

Open-source AI research lab training decentralized large language models and building infrastructure for accessible AI.

BenchFlow is a frontier environment lab that builds environments for AI agents to learn and be evaluated on real computer work.

Open source AI model visibility tracking and competitor benchmarking.

An AI software engineer that connects your repositories and infrastructure to autonomously complete development tasks, improving with every run.

Low-code platform for building, iterating, and deploying AI applications, especially RAG and multi-agent systems.

A non-profit AI research lab focused on open science and developing advanced multimodal and voice AI models.

Sponsors of OpenWALDO, a community-driven initiative for open-source AI training data, and provider of enterprise Linux, HPC, and AI infrastructure software.

Agentic endpoint security for AI coding, providing visibility, governance, and real-time protection.