Tools

Cloudflare's SDK for running untrusted or generated code in isolated sandboxes via a Worker.

Daytona is infrastructure for running AI-generated code in isolated sandboxes via SDKs, API and CLI.

DeepEval is an Apache-2.0 open-source Python framework for evaluating LLM applications and agents.

E2B is an open-source sandbox environment for running AI agents in secure, on-demand Linux VMs.

Self-hosted life OS for habits, goals, Kanban, finance and focus, with an MCP server for AI.

Open source platform for tracing, evaluating and improving AI agents and LLM applications.

LiteLLM is an open-source library with a unified interface to call 100+ LLMs in the OpenAI format.

Modal runs code in the cloud and offers Sandboxes, secure containers for untrusted user or agent code.

Ollama is a tool for running open AI models locally or in the cloud, per its own site.

Open WebUI is the platform for running AI on your own terms, connecting to any model, local or cloud.

OpenAI's agent harness, shipped as a Python SDK update in April 2026 and as the hosted Agents API in September 2026.

OpenRouter is an API with SDKs and an agent package for sending chat requests to models via one endpoint.

Open-source platform for tracing, evaluating and optimizing LLM applications and agents.

Phoenix is an Arize-maintained AI observability and evaluation tool with prompt and dataset tooling.

Portkey is an AI gateway with guardrails that routes requests to many LLMs through a single API.

promptfoo is an open-source CLI and library for evaluating and red-teaming LLM apps.

Apache-2.0 scanner from NVIDIA for agent skills and MCP installs, with a local MCP server that exposes scan_skill.

Open-source platform for agent-built apps and workflows with company login, databases and file storage.

Chrome Relay lets AI agents use your signed-in Chrome in background tabs.

Apache-2.0 browser infrastructure that learns a website once and turns that knowledge into commands for later runs.

Apache-2.0 terminal pair programmer. The project describes Aider as AI pair programming in your terminal.

Claude Code is an agentic coding tool that runs in your terminal and works on your codebase.

Apache-2.0 coding agent published as an SDK, IDE extension, or CLI assistant in the cline/cline repository.

Crush is a terminal-based agentic coding tool from Charm, published as charmbracelet/crush on GitHub.

Devin is an AI coding agent and software engineer that helps developers build better software faster.

E2E is an open source TypeScript testing framework for web and mobile apps with AI agent actions.

Terminal coding agent announced September 18, 2026, with an open-source Go agent SDK and MCP.

Google's frontier model for complex coding, agentic and reasoning tasks, available in GitHub Copilot.

Open-source terminal AI agent that brings Gemini into the command line for coding and workflows.

Apache-2.0 agent from Block. The repository describes Goose as an open-source, extensible AI agent that goes beyond code suggestions.

Laya guard is a free local guardrail that judges every AI coding agent tool call on-device.

Open-source coding agent from the anomalyco/opencode repository, MIT-licensed, with a terminal client and a site at opencode.ai.

MIT-licensed project to build and run AI coding agents: start locally, automate workflows, use any model.

An open-source AI coding agent that lives in your terminal to turn ideas into code.

Open-source tool that learns your engineering rules and delivers them as skills to coding agents.

Free Apache-2.0 macOS app that lets agents use desktop software on a virtual display while you keep the cursor.

An open-source, code-first Python toolkit for building, evaluating and deploying AI agents.

Agno is an orchestration and service layer for agents, exposing them through a REST API and an MCP server.

CrewAI is a framework for orchestrating role-playing, autonomous AI agents that work together.

DSPy is a framework for programming, not prompting, language models, maintained in stanfordnlp/dspy.

LangChain is an open-source agent engineering platform and Python framework for building agents.

LangGraph is an open-source orchestration runtime for building stateful, resilient agents.

TypeScript agent framework. Mastra Code is the terminal agent; AgentController is the extracted loop, in @mastra/core 1.47.0 or later.

Pydantic AI is a model-agnostic Python framework for building typed AI agents and applications.

Functionize Studio tests real applications. Its MCP server lets coding agents request and read those tests from chat.

GitHub's official MCP server. Version 1.0.0 shipped April 16, 2026 with organization issue fields and an MCP Apps flag.

GitHub repository of Model Context Protocol servers, shipped as npm and PyPI packages such as filesystem and git.

Hosted web agent with an MCP server for search, browsing, and extraction, plus an MIT-licensed local proxy.

Microsoft's Windows debugger. WinDbg MCP, from version 1.2610.1001.0, lets Copilot query an active session.

LiveKit Agents is an open source framework for building realtime voice AI agents in Python and Node.js.

MIT-licensed TTS from Resemble AI. Chatterbox Multilingual V3 is a 500M model for 23 or more languages with zero-shot cloning.

Apache-2.0 TTS model with 82 million parameters. Version 1.0, published January 27, 2025, lists 8 languages and 54 voices.

Apache-2.0 speech family from OpenMOSS. MOSS-TTS-v1.5 supports 31 languages, with separate models for realtime streaming and voice design.

Apache-2.0 speech models from the Qwen team, 0.6B and 1.7B, with voice clone, voice design, and 10 languages.

Apache-2.0 tokenizer-free TTS from OpenBMB. VoxCPM2 is a 2B model with 30 languages, voice design, cloning, and 48 kHz output.