Looking for free AI agents in Software Development? Explore our marketplace of digital assistants and automation tools designed specifically for the Software Development industry.

AI Agents for Software Development, free pricing

Playwright MCP is an open-source Model Context Protocol (MCP) server from Microsoft that exposes Playwright-powered browser automation as callable tools for AI agents. Instead of relying on screenshots or visually-tuned models, it provides structured page state (including accessibility snapshots) so an LLM can reliably understand and interact with live web pages—clicking, typing, waiting for selectors, navigating, and validating outcomes. It’s useful for AI-assisted web testing, agent-driven site exploration, and automations that need a real browser environment with deterministic, tool-based control.

Playwright MCP

playwright-mcp

An open-source MCP server that lets LLMs automate real browsers with Playwright using structured accessibility snapshots (no screenshots needed).

Together Open Data Scientist is an open-source AI data analysis agent built around the ReAct (Reasoning + Acting) pattern. It automates common end-to-end data science workflows: loading and exploring datasets, running EDA, engineering features, training baseline models, creating plots, and writing a structured report. The agent can execute Python code either locally (via Docker/internal execution) or in the cloud using Together Code Interpreter (TCI), and it supports uploading a data directory for analysis. It’s positioned as experimental software—outputs should be reviewed and validated—making it most useful for exploration, learning, and fast first-pass analysis rather than unattended production analytics.

Together Open Data Scientist

together-open-data-scientist

Open-source data scientist agent that runs Python (locally or in the cloud) to explore datasets, build models, and generate detailed analysis reports using the ReAct framework.

GLM-4.6V is a next-generation multimodal large language model series from Z.ai (Zhipu AI), designed for high-fidelity visual understanding and long-context reasoning across images, video, documents, and text. It comes in two main variants: the 106B-parameter GLM-4.6V foundation model for cloud and cluster deployment, and the lightweight GLM-4.6V-Flash (9B) optimized for local and low-latency applications. With a 128k token context window, GLM-4.6V can read large PDFs, slide decks, and multi-page mixed-media documents in a single pass. Native multimodal function calling lets it use tools directly from visual inputs, closing the loop from perception to executable actions and enabling powerful agent-style workflows. Typical use cases include visual document QA, chart and layout understanding, multimodal search and analysis, converting UI screenshots into production-ready code, and generating image-rich content. The models are released with open weights under a permissive open-source license, making them suitable for research, self-hosted deployments, and integration into production systems.

GLM-4.6V

glm-4-6v

Open-source multimodal GLM from Z.ai unifying vision, text, and tool calling for long-context reasoning, search, coding, and UI-to-code.

x402 is an open, internet-native payment protocol that activates the long-reserved HTTP 402 “Payment Required” status code to handle payments directly inside web and API requests. It allows AI agents, apps, and APIs to charge and pay per request using stablecoins like USDC, removing the need for traditional API keys, subscriptions, or manual billing. Built as an open standard by Coinbase and deployed on chains such as Solana and Base, x402 supports low-cost, high-throughput micropayments suitable for agentic workflows, data APIs, model inference, and digital content. By embedding pricing, payment instructions, and proof of payment in normal HTTP flows, x402 enables fully autonomous, machine-to-machine commerce and a more granular, usage-based business model for online services.

x402 Protocol

x402-protocol

Open payment protocol that lets AI agents and APIs send instant stablecoin micropayments over HTTP using the 402 status code.

ComfyUI is a free, open-source, node-based platform for generative AI. Creators assemble visual workflows to produce images, video, 3D, and audio, extend functionality with custom nodes, and run everything locally for speed, control, and cost savings. The Comfy Org ecosystem includes a desktop app, a registry for custom nodes, continuous-integration testing, and an announced Comfy Cloud beta to run workflows in the browser without setup.

ComfyUI (Comfy.org)

comfyui-comfy-org

Open-source, node-based generative AI platform to build image, video, 3D, and audio workflows locally or in the cloud.

Wildcard AI provides an open-source specification called *agents.json* that builds on OpenAPI to let agents consume APIs more reliably. It enables defining API contracts, flows (chains of calls), links between actions, and metadata so autonomous agents can discover and invoke workflows automatically. It includes Wildcard Bridge SDK, a registry of agents.json files, and motivations around statelessness, better tool-selection, and easier LLM-API integration.

Wildcard AI / agents.json

wildcard-ai-agents-json

Open-source spec & platform letting AI agents discover and invoke API workflows via agents.json rather than fixed prompts.

Vercel AI SDK is a free, open-source TypeScript library from the creators of Next.js, designed to help developers build AI-powered applications and agents. It offers a unified provider API—OpenAI, Anthropic, Claude, Google Gemini, etc.—structured output (via Zod), streaming responses, chat UI integrations, tool calling, agentic loops, and full TypeScript type safety across React, Svelte, Vue, Angular, or Node apps. With over 2 million weekly downloads, it simplifies LLM integration and enables rapid development of robust AI workflows.

Vercel AI SDK

vercel-ai-sdk

Free open-source TypeScript SDK for building LLM-powered apps and agents across frameworks with unified API.

GLM‑4.5 is an open‑source, Mixture‑of‑Experts (MoE) large‑language model from Z.ai, designed for intelligent agent applications. It features 355 B parameters (32 B active) with an efficient ’thinking/non‑thinking’ hybrid reasoning mode and 128 K context length. A smaller variant, GLM‑4.5‑Air, offers 106 B parameters (12 B active) for more efficient deployments. GLM‑4.5 excels at reasoning, coding, and tool‑calling tasks and ranks among the top performers on benchmarks compared with models like o3, Grok‑4, Claude Sonnet, and GPT‑4.1.

GLM‑4.5

glm-4-5

Open-source hybrid‑reasoning MoE foundation model optimized for intelligent agent tasks with 128K context and tool use.

Google Opal is an experimental no‑code tool from Google Labs that lets users build, edit, and share AI mini‑applications using plain English. It converts natural language prompts into visual workflows—chain prompts, AI model calls, and outputs—editable via conversational or drag‑and‑drop interfaces. Templates and sharing via Google account ease prototyping and collaboration. Currently available in U.S. public beta, Opal offers a frictionless entry into agentic app creation using Gemini models.

Google Opal

google-opal

An experimental no‑code platform from Google Labs to build and share AI mini‑apps via natural language workflows.

Amazon SageMaker Studio Lab is a free, browser‑based machine learning development environment powered by open‑source JupyterLab. It gives users access to T3.xlarge CPU and G4dn.xlarge GPU runtimes (with session and daily limits), along with 15 GB of persistent storage, Git integration, preinstalled ML frameworks, and the SageMaker Distribution environment for easy migration to SageMaker Studio. No AWS account or credit card is required. Ideal for students, educators, and developers looking to learn, prototype, or teach ML workflows without setup overhead.

Amazon SageMaker Studio Lab

amazon-sagemaker-studio-lab

Free browser‑based JupyterLab environment for ML experiments with CPU/GPU and persistent storage.

Qwen3‑Coder is an agentic code model from Alibaba’s Qwen3 family. Its flagship variant (480B MoE, 35B active) excels at agentic coding, tool use, and browser tasks with long context (256K–1M tokens). It’s open‑source under Apache‑2.0 and integrates with Qwen Code CLI and Qwen‑Agent workflows.

Qwen3‑Coder

qwen3-coder

Open‑source Mixture‑of‑Experts code model by Alibaba for agentic coding and tool use.

TEN Framework is an open-source modular system for building autonomous AI agents capable of reasoning, memory management, and tool usage. Designed to reflect real-world constraints, it incorporates a Thought-Emission-Norm (TEN) architecture, encouraging agents to think before acting. The framework supports open-ended planning, persistent memory storage, and tool augmentation. Developers can use TEN to experiment with agent autonomy and deploy agents that simulate complex decision-making workflows.

TEN Framework

ten-framework

An open-source framework for building autonomous AI agents that interact with the real world through tools and memory.

AI Agents for "Software Development" Industry, free pricing