mdreview
v0.7.0
io.github.ranawaqas-ai/mdreview
Human-in-the-loop document review: an agent pushes a draft, a person comments, the agent revises.
“Ralph Loop” 共 72 个结果
v0.7.0
io.github.ranawaqas-ai/mdreview
Human-in-the-loop document review: an agent pushes a draft, a person comments, the agent revises.
v0.15.0
io.github.ShekharBhardwaj/agentic-ledger
Local-first flight recorder for AI agents: sessions, costs, loop runs, and stuck-loop flags.
v1.0.0
ai.scout7/scout7
Marketing MCP: your AI agent runs your organic growth loop — you approve before it ships.
v0.1.4
io.github.cyanheads/evals-mcp-server
通过草稿、评审、修订、提交的闭环撰写可验证的评测记录,并强制使用评分器。
v1.0.0
site.star365/commerce
Buy a star365 subscription with USDT stablecoin: quote, pay, activate. No human in the loop.
v0.1.1
app.vercel.groundtruth-ruby/groundtruth
Human-in-the-loop user research: ask real people what the web can't answer, get verbatim replies
v1.0.0
io.github.BuilderIO/agent-native-chat
Minimal chat-first app with durable threads, actions, and the app-agent loop
v2.0.0
io.nolt/nolt
A collaborative place for user requests: collect feedback, plan work, keep users in the loop.
v0.2.1
town.liars/arena
Play Werewolf against other AI agents. join once, then loop observe/act. Public ELO leaderboard.
v1.0.0
ai.qualityclouds/norma
确定式的 AI 代码审查并留存审计记录,把治理放进智能体循环内。
v2026.8.19
ai.elicitly/pro
经 MCP 为 AI 智能体引入人工参与:可持久化审批,配托管审阅页与审计追踪。
v0.1.0
io.identark/gateway
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
v0.4.1
io.github.grzgrzgrz3/pingwa
Zero-setup WhatsApp notifications + human-in-the-loop for AI agents — text 'join', send in 60s.
v2.0.0
com.narrowhighway/concordance
在约 60 个领域进行确定性的主张核验并附带凭证,链路中不调用模型。
v0.1.0
net.glyt/glyt
Human-in-the-loop approval for agent actions, with verifiable action-bound receipts.
v1.0.0
cz.salesbot/linkedin-mcp-server
人在环路的 LinkedIn 外联与内置销售 CRM,供 AI 智能体使用,带安全闸门与反垃圾机制。
v1.0.0
reviews.rami/rami
面向 GitHub PR 的 AI 代码审查,为 Claude Code 与 Cursor 提供 MCP 自动修复回路。
v2026.06.10
ai.joinmultiplayer/gpu
面向团队的智能体互联网络:私信、按“谁懂 X”路由、共享房间,并保留人工在环。
v0.1.0
io.github.zmarten/meatspace
AI 智能体的人类在环服务:提交选项,获取人类决策。
v2026.03.22
io.github.ariffazil/arifosmcp
合宪式 AI 治理:11 个巨型工具、13 条底线、VAULT999 账本,设计上人在环。
v0.1.10
io.github.unmodeled-tyler/vessel-browser
面向自主智能体的 AI 原生浏览器运行时,支持人在回路监督。
v1.0.0
io.github.aataqi-boop/siliconbridge
面向 AI 智能体的人机协同 API:由真人完成验证码、OTP、KYC 与审批。
v0.1.3
io.github.ferm-ai/agentwork-mcp
Agentwork 官方 MCP server:把任务委派给支持人工介入(human-in-the-loop)的 AI agent。
v1.0.1
com.lassare/ask
为 AI 编码智能体提供人在回路——通过 Slack 提问并获取批准。