* [RuFlo v3.56.0](https://github.com/ruvnet/ruflo) – Enterprise-grade multi-agent orchestration platform for deploying, coordinating, and optimizing specialized AI agents.

* [DeerFlow v2.1.0](https://github.com/bytedance/deer-flow) – Long-horizon super-agent harness orchestrating sub-agents, memory, sandboxes, and extensible skills to perform complex tasks.

* [Kun v0.4.0](https://github.com/KunAgent/Kun) – Electron and React-based AI agent workspace with code and write modes, including GUI-driven planning, review, and Todo workflows via an integrated CLI.

* [Sim v0.9.19](https://github.com/simstudioai/sim) – Platform to build and deploy AI agent workflows quickly.

* [CAPA v2.3.0](https://github.com/infragate/capa) – Capability-centric package manager that provisions skills, tools, rules, sub-agents, MCP servers, and plugins from capabilities.yaml into many AI coding agents.

* [sentry-mcp 0.42.0](https://github.com/getsentry/toolkit) – A remote MCP middleware that lets LLM coding assistants interact with Sentry through an upstream API, with optional stdio transport for self-hosted setups.

* [Eigent v1.0.5](https://github.com/eigent-ai/eigent) – Desktop application to build, manage, and deploy customizable multi-agent AI workforces that automate complex workflows.

* [FLUJO v3.46.0](https://github.com/mario-andreschak/FLUJO) – Local-first platform for building MCP-powered AI workflows with model management, a visual flow builder, and a chat interface.

* [Flare v2.1.0](https://github.com/AlgoNoRhythm/Flare) – Graph-first IDE that maps a codebase into a live dependency graph with lenses, snapshots, and an embedded agent terminal.

* [Pilot v2.281.0](https://github.com/qf-studio/pilot) – Autonomous development pipeline that picks issues, implements code, runs tests, and opens pull requests for review.

* [Secure MCP Tunnel client v0.0.16](https://github.com/openai/tunnel-client) – Secure MCP Tunnel customer-run client that connects a private MCP server to ChatGPT, Codex, and related APIs via an OpenAI-hosted tunnel endpoint.

* [Taskuary v0.3.7.0](https://github.com/ldbumble/taskuary) – Local-first AI task hub that triages incoming messages into tasks, routes them to agent workers, and returns evidence and decisions for your approval.

* [Wallfacer v0.6.0](https://github.com/changkun/wallfacer) – Self-operating engineering platform orchestrating autonomous coding agents across a task board with isolated sandboxes, live logs, diffs, cost tracking, and full oversight.

* [ThinkRail v0.1.2](https://github.com/JetBrains/thinkrail) – Desktop and mobile client that hosts the pi coding agent in-process and bridges it to a mobile-first IDE UI.

* [AgentRQ v0.6.3](https://github.com/agentrq/agentrq) – AgentRQ is a human-in-loop collaboration platform that connects AI agents to task management through MCP for real-time workspace coordination.

* [AG-UI release/2026-10-10](https://github.com/ag-ui-protocol/ag-ui) – Lightweight event-based protocol standardizing AI agent integration with user-facing applications.

* [Agent! v1.1.93.293](https://github.com/AgentiLoop/Agent) – macOS native agentic AI that automates tasks, edits files with undoable diffs, and coordinates multiple LLM providers for hands-free computer control.

* [Grix v3.2.10+3013](https://github.com/askie/grix) – Mobile and desktop chat app for DeepSeek Harness and other coding agents, managing agents as contacts and enabling shared threaded collaboration with controls and approvals.