* [ComputeSDK @computesdk/runloop@...](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [mcp-use mcp-use@1.15.2-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [OpenCode Manager v0.8.2](https://github.com/chriswritescode-dev/opencode-manager) – Mobile-first web interface to manage AI coding agents with Git integration, file browsing, and real-time chat.

* [Prisma-AI: AI co-pilot v5.3.4](https://github.com/weicanie/prisma-ai) – AI co-pilot optimizing projects, customizing resumes, matching jobs, and assisting interview preparation.

* [OpenCode Manager v0.8.1](https://github.com/chriswritescode-dev/opencode-manager) – Mobile-first web interface to manage AI coding agents with Git integration, file browsing, and real-time chat.

* [WeKnora v0.2.13](https://github.com/Tencent/WeKnora) – LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using the RAG paradigm.

* [mcp-use create-mcp-use-app@0...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [mcp-use mcp-use@1.15.0-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [mcp-use mcp-use@1.15.0-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [mcp-use create-mcp-use-app@0...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [mcp-use mcp-use@1.15.0-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [OpenCode Manager v0.8.0](https://github.com/chriswritescode-dev/opencode-manager) – Mobile-first web interface to manage AI coding agents with Git integration, file browsing, and real-time chat.

* [archestra platform-v1.0.34](https://github.com/archestra-ai/archestra) – MCP-native centralized platform for orchestrating, securing, and observing MCP servers with private registry and cost controls.

* [Super-Agent-Party v0.3.7](https://github.com/heshengtao/super-agent-party) – 3D AI desktop companion platform with modular LLM enhancements, multi-terminal deployment, and cross-platform compatibility.

* [Agentica, AI Function Calling Framework v0.40.0](https://github.com/wrtnlabs/agentica) – Agentic AI framework specialized in AI Function Calling using TypeScript classes, OpenAPI, and MCP protocols.

* [WeKnora v0.2.12](https://github.com/Tencent/WeKnora) – LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using the RAG paradigm.

* [OpenCode Manager v0.7.8](https://github.com/chriswritescode-dev/opencode-manager) – Mobile-first web interface to manage AI coding agents with Git integration, file browsing, and real-time chat.

* [OpenContext desktop-v0.2.6](https://github.com/0xranx/OpenContext) – Personal context and knowledge store for AI assistants providing CLI, MCP server, desktop and web UIs to capture, search, and reuse project knowledge.

* [Prisma-AI: AI co-pilot v5.3.3](https://github.com/weicanie/prisma-ai) – AI co-pilot optimizing projects, customizing resumes, matching jobs, and assisting interview preparation.

* [Cherry Studio v1.7.15](https://github.com/CherryHQ/cherry-studio) – Desktop client supporting multiple LLM providers, available on Windows, Mac, and Linux.

* [Prisma-AI: AI co-pilot v5.3.2](https://github.com/weicanie/prisma-ai) – AI co-pilot optimizing projects, customizing resumes, matching jobs, and assisting interview preparation.

* [Cherry Studio v1.7.14](https://github.com/CherryHQ/cherry-studio) – Desktop client supporting multiple LLM providers, available on Windows, Mac, and Linux.

* [OpenCode Manager v0.7.7](https://github.com/chriswritescode-dev/opencode-manager) – Mobile-first web interface to manage AI coding agents with Git integration, file browsing, and real-time chat.

* [OpenCode Manager v0.7.6](https://github.com/chriswritescode-dev/opencode-manager) – Mobile-first web interface to manage AI coding agents with Git integration, file browsing, and real-time chat.

* [Manifest v5.0.3](https://github.com/mnfst/manifest) – Backend framework enabling data, storage, logic, and admin panel definition in a single YAML file.

* [Advanced iMessage Kit v1.11.5](https://github.com/photon-hq/advanced-imessage-kit) – TypeScript SDK for reading, sending, and automating iMessage conversations on macOS with real-time messaging support.

* [OpenCode Manager v0.7.5](https://github.com/chriswritescode-dev/opencode-manager) – Mobile-first web interface to manage AI coding agents with Git integration, file browsing, and real-time chat.

* [Prisma-AI: AI co-pilot v5.3.1](https://github.com/weicanie/prisma-ai) – AI co-pilot optimizing projects, customizing resumes, matching jobs, and assisting interview preparation.

* [Go Agent for the Internet Computer v0.7.7](https://github.com/aviate-labs/agent-go) – Golang library for interacting with Internet Computer replicas, providing Candid support, identity management, and certificate handling.

* [Halo v1.2.12](https://github.com/openkursar/hello-halo) – Visual desktop interface for Claude Code enabling agent-based automation, file management, remote access, and an embedded AI browser.

* [Cyrus v0.2.19](https://github.com/ceedaragents/cyrus) – Claude Code-powered Linear agent that monitors assigned issues, runs isolated Git worktrees, processes them locally, and posts comments back to Linear.

* [ComputeSDK @computesdk/provider...](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [Giselle v0.62.2](https://github.com/giselles-ai/giselle) – Platform for building and composing agentic AI workflows with a visual drag-and-drop agent builder.

* [ComputeSDK @computesdk/hopx@0.2...](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [Agentbaker v0.20260101.0](https://github.com/Azure/AgentBaker) – Components to provision Linux and Windows Kubernetes nodes, build VM images, and render node configuration for Azure.

* [OpenCode Manager v0.7.4](https://github.com/chriswritescode-dev/opencode-manager) – Mobile-first web interface to manage AI coding agents with Git integration, file browsing, and real-time chat.

* [ComputeSDK @computesdk/workbenc...](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [ComputeSDK compute-v1.0.62](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [ComputeSDK computesdk@1.19.0](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [mux v0.14.1](https://github.com/coder/mux) – Desktop application providing isolated, parallel agentic development workspaces.

* [lazycommit v1.4.0](https://github.com/m7medVision/lazycommit) – AI-powered generator that analyzes staged changes to produce conventional commit messages and pull request titles.

* [Beads UI v0.9.3](https://github.com/mantoni/beads-ui) – Local UI for the bd CLI to view and manage issues, epics, and kanban-style boards with keyboard navigation.

* [UnicomAI/wanwu v0.3.6](https://github.com/UnicomAI/wanwu) – Enterprise-grade multi-tenant platform for developing large model applications including intelligent agents, workflows, and text Q&A with model management.

* [Acontext cli/v0.1.0](https://github.com/memodb-io/Acontext) – Context data platform for storing contexts, observing tasks, and enabling agent self-learning through experience collection.

* [OpenCode Manager v0.7.2](https://github.com/chriswritescode-dev/opencode-manager) – Mobile-first web interface to manage AI coding agents with Git integration, file browsing, and real-time chat.

* [OpenCode Manager v0.7.1](https://github.com/chriswritescode-dev/opencode-manager) – Mobile-first web interface to manage AI coding agents with Git integration, file browsing, and real-time chat.

* [WeKnora v0.2.11](https://github.com/Tencent/WeKnora) – LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using the RAG paradigm.

* [MCP Toolbox for Databases v0.26.0](https://github.com/googleapis/genai-toolbox) – Toolbox simplifies database interactions for AI tools, enhancing development speed and security.

* [Giselle v0.62.1](https://github.com/giselles-ai/giselle) – Platform for building and composing agentic AI workflows with a visual drag-and-drop agent builder.

* [ComputeSDK compute-v1.0.60](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [archestra platform-v1.0.33](https://github.com/archestra-ai/archestra) – MCP-native centralized platform for orchestrating, securing, and observing MCP servers with private registry and cost controls.

* [ComputeSDK @computesdk/render@1...](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [mux v0.14.0](https://github.com/coder/mux) – Desktop application providing isolated, parallel agentic development workspaces.

* [Beads UI v0.9.2](https://github.com/mantoni/beads-ui) – Local UI for the bd CLI to view and manage issues, epics, and kanban-style boards with keyboard navigation.

* [mcp-use python-v1.6.0](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [@photon-ai/imessage-kit v2.1.2](https://github.com/photon-hq/imessage-kit) – Type-safe, elegant iMessage SDK for macOS with Node.js and Bun cross-runtime support.

* [F5 NGINX Agent v2.45.1](https://github.com/nginx/agent) – Companion application for remote management, configuration, and real-time metrics collection from NGINX instances.

* [mcp-use mcp-use@1.14.2-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [mcp-use mcp-use@1.14.2-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [mcp-use mcp-use@1.14.2-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [PageAgent v1.0.0](https://github.com/alibaba/page-agent) – Client-side JavaScript GUI enabling natural-language control and DOM interaction on webpages.

* [PageAgent v1.0.0-beta.5](https://github.com/alibaba/page-agent) – Client-side JavaScript GUI enabling natural-language control and DOM interaction on webpages.

* [AgentField v0.1.37](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [ComputeSDK @computesdk/gateway@...](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [AgentField v0.1.36](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [AgentField v0.1.35](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [ComputeSDK @computesdk/workbenc...](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [AgentField v0.1.34](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [ComputeSDK @computesdk/daytona@...](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [AgentField v0.1.33](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [AgentField v0.1.32](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [Inkeep Agents v0.42.0](https://github.com/inkeep/agents) – Platform offering a no-code visual builder and TypeScript SDK for creating and managing AI agents with full two-way sync.

* [ComputeSDK @computesdk/daytona@...](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [mcp-use create-mcp-use-app@0...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [mcp-use mcp-use@1.14.1-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [mcp-use mcp-use@1.14.0-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [PageAgent v1.0.0-beta.4](https://github.com/alibaba/page-agent) – Client-side JavaScript GUI enabling natural-language control and DOM interaction on webpages.

* [PageAgent v1.0.0-beta.3](https://github.com/alibaba/page-agent) – Client-side JavaScript GUI enabling natural-language control and DOM interaction on webpages.

* [mcp-use mcp-use@1.14.0-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [ComputeSDK @computesdk/railway@...](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [AgentField v0.1.32-rc.3](https://github.com/Agent-Field/agentfield) – Control-plane infrastructure that deploys, scales, and secures autonomous AI agents as observable, identity-aware backend services.

* [PageAgent v1.0.0-beta.2](https://github.com/alibaba/page-agent) – Client-side JavaScript GUI enabling natural-language control and DOM interaction on webpages.

* [mcp-use mcp-use@1.14.0-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [mcp-use mcp-use@1.14.0-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [mcp-use mcp-use@1.14.0-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [Coze Loop v1.5.1](https://github.com/coze-dev/coze-loop) – Developer-oriented platform providing full lifecycle management for AI agent development, debugging, evaluation, and monitoring.

* [mcp-use mcp-use@1.14.0-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [AgentScope Studio v1.0.8](https://github.com/agentscope-ai/agentscope-studio) – Local visualization toolkit for developing, debugging, tracing, and evaluating agent-based applications.

* [mcp-use mcp-use@1.14.0-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [OpenCode Manager v0.7.0](https://github.com/chriswritescode-dev/opencode-manager) – Mobile-first web interface to manage AI coding agents with Git integration, file browsing, and real-time chat.

* [Eliza v1.7.2](https://github.com/elizaOS/eliza) – Framework for developing and deploying multi-agent systems with real-time communication and extensible integrations.

* [Eliza v1.7.2-alpha.10](https://github.com/elizaOS/eliza) – Framework for developing and deploying multi-agent systems with real-time communication and extensible integrations.

* [PageAgent v1.0.0-beta.1](https://github.com/alibaba/page-agent) – Client-side JavaScript GUI enabling natural-language control and DOM interaction on webpages.

* [PageAgent v0.3.0](https://github.com/alibaba/page-agent) – Client-side JavaScript GUI enabling natural-language control and DOM interaction on webpages.

* [Coze Loop v1.5.0](https://github.com/coze-dev/coze-loop) – Developer-oriented platform providing full lifecycle management for AI agent development, debugging, evaluation, and monitoring.

* [Eliza v1.7.2-alpha.7](https://github.com/elizaOS/eliza) – Framework for developing and deploying multi-agent systems with real-time communication and extensible integrations.

* [archestra platform-v1.0.27](https://github.com/archestra-ai/archestra) – MCP-native centralized platform for orchestrating, securing, and observing MCP servers with private registry and cost controls.

* [Backlog.md v1.34.0](https://github.com/MrLesk/Backlog.md) – Markdown-native task manager and Kanban visualizer that turns any Git repository into a self-contained project board.

* [Eliza v1.7.2-alpha.6](https://github.com/elizaOS/eliza) – Framework for developing and deploying multi-agent systems with real-time communication and extensible integrations.

* [OpenCode Manager v0.6.4](https://github.com/chriswritescode-dev/opencode-manager) – Mobile-first web interface to manage AI coding agents with Git integration, file browsing, and real-time chat.

* [mux v0.13.1](https://github.com/coder/mux) – Desktop application providing isolated, parallel agentic development workspaces.

* [Acontext core/v0.1.0](https://github.com/memodb-io/Acontext) – Context data platform for storing contexts, observing tasks, and enabling agent self-learning through experience collection.

* [mcp-use mcp-use@1.13.5-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [lazycommit v1.3.32](https://github.com/m7medVision/lazycommit) – AI-powered generator that analyzes staged changes to produce conventional commit messages and pull request titles.

* [PageAgent v0.2.5](https://github.com/alibaba/page-agent) – Client-side JavaScript GUI enabling natural-language control and DOM interaction on webpages.

* [PageAgent v0.2.4](https://github.com/alibaba/page-agent) – Client-side JavaScript GUI enabling natural-language control and DOM interaction on webpages.

* [PageAgent v0.2.3](https://github.com/alibaba/page-agent) – Client-side JavaScript GUI enabling natural-language control and DOM interaction on webpages.

* [OpenContext desktop-v0.2.5](https://github.com/0xranx/OpenContext) – Personal context and knowledge store for AI assistants providing CLI, MCP server, desktop and web UIs to capture, search, and reuse project knowledge.

* [Halo v1.2.10](https://github.com/openkursar/hello-halo) – Visual desktop interface for Claude Code enabling agent-based automation, file management, remote access, and an embedded AI browser.

* [LangGraphGo v0.8.5](https://github.com/smallnest/langgraphgo) – Go library to build resilient, parallel-executing AI agents modeled as composable graphs.

* [Cyrus v0.2.15](https://github.com/ceedaragents/cyrus) – Claude Code-powered Linear agent that monitors assigned issues, runs isolated Git worktrees, processes them locally, and posts comments back to Linear.

* [Agent Development Kit (ADK) for TypeScript v0.2.4](https://github.com/google/adk-js) – Code-first TypeScript toolkit for building, evaluating, and deploying sophisticated AI agents with fine-grained control.

* [Giselle v0.61.0](https://github.com/giselles-ai/giselle) – Platform for building and composing agentic AI workflows with a visual drag-and-drop agent builder.

* [ComputeSDK compute-v1.0.58](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [Eliza v1.7.2-alpha.4](https://github.com/elizaOS/eliza) – Framework for developing and deploying multi-agent systems with real-time communication and extensible integrations.

* [PageAgent v0.2.2](https://github.com/alibaba/page-agent) – Client-side JavaScript GUI enabling natural-language control and DOM interaction on webpages.

* [mux v0.13.0](https://github.com/coder/mux) – Desktop application providing isolated, parallel agentic development workspaces.

* [archestra platform-v1.0.26](https://github.com/archestra-ai/archestra) – MCP-native centralized platform for orchestrating, securing, and observing MCP servers with private registry and cost controls.

* [mcp-use mcp-use@1.13.4-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [OpenContext desktop-v0.2.4](https://github.com/0xranx/OpenContext) – Personal context and knowledge store for AI assistants providing CLI, MCP server, desktop and web UIs to capture, search, and reuse project knowledge.

* [mcp-use mcp-use@1.13.3-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [UnicomAI/wanwu v0.3.5](https://github.com/UnicomAI/wanwu) – Enterprise-grade multi-tenant platform for developing large model applications including intelligent agents, workflows, and text Q&A with model management.

* [mcp-use create-mcp-use-app@0...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [PageAgent v0.2.1](https://github.com/alibaba/page-agent) – Client-side JavaScript GUI enabling natural-language control and DOM interaction on webpages.

* [Cossistant @cossistant/types@0....](https://github.com/cossistantcom/cossistant) – Chat support widget for React with headless components, real-time messaging, and backend infrastructure.

* [WeKnora v0.2.10](https://github.com/Tencent/WeKnora) – LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using the RAG paradigm.

* [Giselle v0.60.13](https://github.com/giselles-ai/giselle) – Platform for building and composing agentic AI workflows with a visual drag-and-drop agent builder.

* [OpenCode Manager v0.6.3](https://github.com/chriswritescode-dev/opencode-manager) – Mobile-first web interface to manage AI coding agents with Git integration, file browsing, and real-time chat.

* [ComputeSDK @computesdk/runloop@...](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [ComputeSDK @computesdk/gateway@...](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [Agent Development Kit (ADK) for TypeScript v0.2.3](https://github.com/google/adk-js) – Code-first TypeScript toolkit for building, evaluating, and deploying sophisticated AI agents with fine-grained control.

* [ComputeSDK compute-v1.0.54](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [ComputeSDK @computesdk/railway@...](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [Eliza v1.7.2-alpha.3](https://github.com/elizaOS/eliza) – Framework for developing and deploying multi-agent systems with real-time communication and extensible integrations.

* [PageAgent v0.2.0](https://github.com/alibaba/page-agent) – Client-side JavaScript GUI enabling natural-language control and DOM interaction on webpages.

* [mcp-use mcp-use@1.13.2](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [mcp-use mcp-use@1.13.2-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [Giselle v0.60.12](https://github.com/giselles-ai/giselle) – Platform for building and composing agentic AI workflows with a visual drag-and-drop agent builder.

* [ComputeSDK compute-v1.0.52](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [mcp-use mcp-use@1.13.2-canar...](https://github.com/mcp-use/mcp-use) – Easily build MCP servers, clients and AI agents in Python and TypeScript with minimal code.

* [ComputeSDK compute-v1.0.51](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.

* [Cloudflare Sandbox SDK @cloudflare/sandbox@...](https://github.com/cloudflare/sandbox-sdk) – Run untrusted code in isolated, secure containers at the edge with command execution, file access, and service previews.

* [PageAgent v0.1.0](https://github.com/alibaba/page-agent) – Client-side JavaScript GUI enabling natural-language control and DOM interaction on webpages.

* [tRPC-Agent-Go session/clickhouse/v...](https://github.com/trpc-group/trpc-agent-go) – Go framework for building autonomous intelligent agents with multi-agent orchestration, persistent memory, and tool integration.

* [PageAgent v0.0.23](https://github.com/alibaba/page-agent) – Client-side JavaScript GUI enabling natural-language control and DOM interaction on webpages.

* [tRPC-Agent-Go v1.2.0](https://github.com/trpc-group/trpc-agent-go) – Go framework for building autonomous intelligent agents with multi-agent orchestration, persistent memory, and tool integration.

* [Giselle v0.60.11](https://github.com/giselles-ai/giselle) – Platform for building and composing agentic AI workflows with a visual drag-and-drop agent builder.

* [Cloudflare Sandbox SDK @cloudflare/sandbox@...](https://github.com/cloudflare/sandbox-sdk) – Run untrusted code in isolated, secure containers at the edge with command execution, file access, and service previews.

* [Inkeep Agents v0.41.2](https://github.com/inkeep/agents) – Platform offering a no-code visual builder and TypeScript SDK for creating and managing AI agents with full two-way sync.

* [ComputeSDK @computesdk/lambda@1...](https://github.com/computesdk/computesdk) – Provider-agnostic TypeScript toolkit for securely running untrusted code in isolated sandboxes.