Develop and evaluate web agents through a unified, extensible Gym environment.
Project overview
BrowserGym exposes open-ended browser tasks and benchmarks such as MiniWoB, WebArena, WorkArena, and VisualWebArena through a consistent Gym interface. Researchers can install only the core environment or add benchmark-specific packages, then run agent–environment loops with Chromium controlled through Playwright. It is designed as research infrastructure rather than a consumer automation product, and individual benchmark suites require their own setup.
Organize medical evidence and appointment questions around a specific health concern.
Project overview
Informed Patient guides Claude through a structured intake, evidence search, source review, and synthesis for questions about symptoms, diagnoses, or condition progression. It is designed to help users prepare for appointments and investigate possibilities, not to diagnose. Citations can still be hallucinated, so every source link and claimed finding should be checked.
Build and package cross-platform desktop apps with Next.js and Electron.
Project overview
Nextron combines Next.js and Electron so developers can create desktop applications using familiar React and web-development workflows. It supplies project conventions, development commands, and packaging through electron-builder, with configuration for application metadata, resources, output, and platform targets. ESM projects are supported, but packaging still follows host-platform constraints—for example, macOS binaries must be built on macOS.
Compare skill-enabled and baseline runs to measure whether an Agent Skill actually helps.
Project overview
agent-skills-eval tests an Agent Skill against the same prompts in two modes: with the skill loaded and without it as a baseline. A judge model grades both outputs against defined assertions, producing JSON and JSONL artifacts plus a static HTML report that shows measurable lift, failures, timing, and tool-call behavior. The project includes a command-line runner and a TypeScript SDK, supports OpenAI-compatible chat backends and custom providers, and can run in CI. Users supply both the target model and the judge model.
Run and embed Streamlit apps entirely in the browser without a server.
Project overview
Stlite runs Streamlit applications inside the browser through Pyodide and WebAssembly, removing the need for a Python server. Apps can be mounted with a custom HTML element or JavaScript API, including multiple files, package requirements, configuration, and optional IndexedDB persistence. Because execution stays in a browser sandbox, packages with unsupported native extensions and some blocking Streamlit behaviors will not work as they do in a standard Python environment.
A Unity client-server combat framework built on ET 10
Project overview
Legends-Of-Heroes is a C# client-server game framework based on ET 10, Unity 2022.3.62, and .NET 10. It includes state synchronization, hot updates, skills, buffs, behavior trees, timeline events, server-side collision logic, and a playable ball-survival demo. Setup requires the specified toolchain, and commercial use of the underlying ET framework requires a license from its author.
Build cross-platform desktop apps with Python and your preferred web stack.
Project overview
Pyloid lets Python developers package web frontends and Python backends as desktop applications for Windows, macOS, and Linux. It includes a project generator and common desktop facilities such as windows, tray integration, storage, timers, servers, and build tooling. It is a framework for teams that want to keep their existing web technology choices while delivering installable desktop software.
Build desktop apps with web frontends and Swift backends.
Project overview
Velox brings a Tauri-style desktop application model to Swift, connecting HTML or modern web frontends to Swift backends through typed IPC. Its CLI can initialize projects, run watched development sessions with optional frontend HMR, build releases, and create macOS application bundles; simple static interfaces do not require Node.js. The implementation still compiles a Rust FFI layer around Tao and Wry, and the newer Swift-first runtime remains incomplete, so the event-loop APIs are currently the primary path.
Build an AI agent that loads skill instructions and resources only when needed.
Project overview
This Pydantic AI reference project demonstrates a vendor-independent skill system based on progressive disclosure. The agent keeps only brief skill metadata in its initial context, loads a full `SKILL.md` after selecting a relevant skill, and retrieves deeper references or scripts only when required. Included examples cover tasks such as weather, academic search, and code review, with a CLI for trying the runtime. It is primarily a foundation for developers building their own agents and requires local dependencies plus credentials for the chosen model provider.
Add task traceability, approval gates, memory, and audits to coding agents.
Project overview
Agentic Engineering Framework wraps CLI coding agents with task gates, human approval for destructive actions, persistent session memory, dependency mapping, and audit trails. It coordinates and governs tools such as Claude Code, Cursor, or Aider rather than running the model itself. The framework is intended for long-lived repositories that need traceable commits and controlled agent autonomy, and it is still alpha software.
Scaffold or starterAI and agent developmentModel Context Protocol
Skill_Seekers
@yusufkaraaslan·Python
Converts docs, repositories, PDFs, videos, and other sources into reusable knowledge assets for AI systems.
Project overview
Skill Seekers uses a Python CLI and MCP server to turn documentation sites, GitHub repositories, PDFs, videos, and other sources into structured knowledge assets. It can compare code with documentation, generate example-rich SKILL.md files, and export for Claude, Gemini, OpenAI, LangChain, and multiple vector-database formats. It also supports caching, resumable jobs, and project-configuration scanning. Basic use requires Python 3.10+ and Git; AI enhancement or upload features may need provider credentials.
Build agents, workflows, and deployable AI applications with TypeScript.
Project overview
Mastra gives TypeScript developers one framework for model access, autonomous agents, graph-based workflows, and AI application development. It can integrate with React, Next.js, and Node or run as a standalone server, supporting a path from prototypes to deployed products through a common interface for many model providers. Most of the core uses Apache 2.0, but enterprise features under `ee/` require a commercial license for production.
Build and operate an agent platform in infrastructure you control.
Project overview
Agno combines an SDK, the AgentOS runtime, and a control plane for teams building agent products in their own cloud. It keeps data, context, tools, permissions, memory, and human-review loops under the operator’s control, while providing production APIs, persistent storage, integrations, and observability for running the platform.
Agent harnessAI and agent developmentModel Context Protocol
deepagents
@langchain-ai·Python
Build extensible agents for long-running, multi-step work
Project overview
Deep Agents is an agent harness for long-running, multi-step work, with built-in planning, sub-agents, filesystem access, shell use, and persistence. Each part can be overridden or replaced without forking, and the framework can work with tool-calling frontier, open-weight, or local models.
Combine interchangeable models, data sources, and tools in LLM applications.
Project overview
LangChain provides common interfaces and modular components for building agents and other LLM-powered applications. Developers can connect models, embeddings, vector stores, retrievers, and third-party tools while swapping providers without rebuilding the whole application. The core framework works on its own; LangGraph handles lower-level orchestration, while LangSmith products support debugging, evaluation, and deployment workflows.
Build type-safe Python agents with tools, structured outputs, and provider choice
Project overview
Pydantic AI is a Python framework for building agents with typed instructions, dependencies, tool calls, and structured outputs. It supports many model providers, MCP integrations, streamed results, tool-call approval, durable execution, and graph-based workflows. This makes it a fit for developers who want agent behavior checked by Python types and evaluated over time.
Build local-first desktop and mobile apps with Elixir and Phoenix LiveView.
Project overview
Elixir Desktop lets Phoenix LiveView developers build native-like local applications for Windows, macOS, Linux, iOS, and Android. It routes window, webview, menu, and notification operations through platform backends, using wxWidgets on desktop, a JSON bridge on mobile, or a browser backend for headless environments. An example application and setup guides provide a starting point. Core desktop and mobile execution works, but complete desktop installer generation, signing, and one-command cross-platform packaging remain roadmap items.
Build and run Python agents with graph-based workflows
Project overview
Google ADK is a code-first Python toolkit for building, evaluating, and deploying AI agents. Its Agent and Workflow APIs support graph-based routing, nested workflows, and structured agent-to-agent tasks, while the CLI can run an agent locally or open a web UI for an agent directory. Version 2.0 changes the agent API, event model, and session schema, so existing applications need an upgrade check.