human-agent-collaboration

Temporary rooms for Humans and AI Agents — run, supervise and steer Agent Tasks without a permanent workspace.

You don't need a chat ui but a canvas with ai.

[ACL 2026] LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey | Awesome Human-Agent Collaboration | Human-AI Collaboration

Framework and toolkits for building and evaluating collaborative agents that can work together with humans.

Local-first coordination and authority layer for long-running human-agent projects

SYMBIVELA - Human-Agent Collaboration Workspace. Set goals, review machine plans, approve high-risk actions, resolve exceptions, intervene in execution, accept outcomes, and inspect evidence across agents, workflows, robots, and twins.

Spring Voyage — A human-agent collaboration platform

Team templates for human × agent collaboration — dev, sales, marketing, and more. Powered by hxa-connect.

A declarative specification language for human-agent collaboration. Define what and what constraints, not how. Built with Rust + PEG grammar (pest). 🤖 Co-developed with Claude (Anthropic).

CyberAgent — agent orchestration & human-agent collaboration: agentic project and task management where coding agents and people ship work together, with review gates, shared context and full audit. By Hyperspace.

An open source protocol for Human Agent Interaction

internOS — Workstreams framework for human-agent collaboration. Coordinate work across projects, tasks, communication threads, and filesystem workstreams for any AI agent framework.

Embodied agent that learns from human teaching; hybrid agent architecture with computer vision, AI planning, knowledge graph reasoning & generalization , inverse kinematics. Supported by the DARPA GAILA program.

人体智能体协作模式-多智能体架构系统

A knowledge coordination protocol for human-agent collaboration. Connects research → strategy → requirements → implementation into a traversable, version-aware graph.

A conversation-card deck for exploring, challenging, planning, and explaining ideas with AI.

The semantic protocol behind Control Decks. Cards are the interface. Control is the protocol.

Private mailbox for autonomous coding agents across human teams, machines, and providers. Share work, verify handoffs, and build reusable skills behind the scenes.

Open, Agent-neutral and mechanism-neutral human-Agent collaboration system: a portable reliability kernel plus adaptive outcome delivery.

Co-Gym extension for evaluating collaborative agents under changing human-specified delegation.