agentteams

AgentTeams plugin for DeepSeek Harness

Evidence-driven autonomous SOC team on AgentTeams: hash-bound approvals, HMAC audit chain, rollback and reproducible attack scenarios — auditable governance primitives for agent infrastructure.

Auditable repository maintenance AgentTeam with evidence-backed pull requests, automated code review, and human approval gates.

RevGuard-面向企业渠道佣金结算异常的多智能体治理平台

Official Website: https://opskeeper.yueming.xin OpsKeeper Console: https://opskeeper.yueming.xin/login AgentTeams Dashboard: https://teams.yueming.xin AgentTeams Element: https://rooms.yueming.xin Live Demo: https://opskeeper.yueming.xin/live-incident

多 Agent PR 审修闭环：webhook 自动触发审查/修复/验证，结论以 check run 回写 PR；高风险停人工门，无 merge 权限不越权。GOAI 2026 决赛项目。

AgentTeams-native team that turns an Agent brief into a checked minimum Agent project package.

面向企业软件研发场景的深度研究项目：以多 Agent 协同、角色权限治理、可观测审计、Skill 复盘沉淀为核心的 AI 算法与工程实现（基于 AgentTeams / HiClaw 构建）

Edge AIOps — Multi-Agent Incident Response for Edge + AI Fleets (AgentTeams). Demo for Agent Infra competition.

AdVeto · 送审前的 AI 律师 —— 营销素材合规审查多 Agent 流水线（AgentTeams × 三轨互证 × 条款级证据链）｜GOAI Agent Infra 参赛项目

AgentTeams 动作控制平面：精确授权、崩溃对账与包外验真

Evidence-driven safety control plane for AI-generated software changes, built with AgentTeams.

aicodingagentteam-A Golang-based AI coding orchestration platform. coding agent teams.

RealityGate: transactional, replayable runtime guard for authorized multi-agent actions

Codex skill for multi-agent worker orchestration, parallel thread teams, safe dispatch, serial integration, and final closeout.

Auditable AgentTeams multi-agent software delivery with contract-driven Skills.

OpenXnet by SynapXnet: enterprise AI employee collaboration, governed MCP tools, evidence chains, approvals, verification, and auditable execution.

Evidence-verified deterministic action gate for AgentTeams workflows; GOAI 2026 Agent Infra candidate.

Automate GitHub issue resolution with AI-driven test generation, code repair, and independent verification.

Turn AgentTeams execution traces into reusable, validated Agent Skills.