human-in-the-loop repositories

Trending repositories tagged human-in-the-loop, ranked by trending score. Updated daily.

  1. 1
    mdiri-ai/SoduWork

    The AI-native engine for teams and their agents. Multi-harness, multi-agent, self-hosted.

    GitHub · JavaScript · 6,483 stars · 509 forks · +833 stars in 24 hours · Trending score 5.70

  2. 2
    agentes-chat/agentes-chat

    Open-source, self-hosted Slack alternative where your team and AI agents work together in channels and DMs. Agents run on Claude, ChatGPT/Codex, Gemini or Grok, with MCP tools, their own computer and browser, routines, memory and approvals. Web, desktop and phone apps. Docker Compose + Postgres. AGPL-3.0.

    GitHub · TypeScript · 1,914 stars · 367 forks · +152 stars in 24 hours · Trending score 4.33

  3. 3
    zj-unicom-ai/UniEmployee

    面向企业的数字员工构建与运行平台:把专业员工的经验、流程与判断标准,固化为可随时上岗、可配置、可审批、可观测的 AI 数字员工。

    GitHub · Python · 862 stars · 32 forks · +198 stars in 24 hours · Trending score 3.92

  4. 4
    Ryder-Sun/Meldwork

    Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.

    GitHub · JavaScript · 1,600 stars · 110 forks · +119 stars in 24 hours · Trending score 3.54

  5. 5
    XY-code1/Nexora

    Local-first, model-agnostic personal AI profile framework

    GitHub · Python · 131 stars · 16 forks · +64 stars in 24 hours · Trending score 3.36

  6. 6
    heymrun/heym

    Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure.

    GitHub · Python · 1,841 stars · 138 forks · +38 stars in 24 hours · Trending score 3.18

  7. 7
    chenxiachan/thoughtdag

    Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.

    GitHub · TypeScript · 800 stars · 77 forks · +73 stars in 24 hours · Trending score 3.15

  8. 8
    dabingfy-dot/solo-to-team-skills

    Human-led MAS toolkit: 16 roles, 6 group templates, four platform bundles, evidence-based review and handoff. 一人成队:一个人统筹多智能体协作。

    GitHub · HTML · 1,087 stars · 134 forks · +20 stars in 24 hours · Trending score 3.07

  9. 9
    mtarcure/claude-vibe-squad

    Markdown-first orchestration for 71 specialists across Codex, Claude, Gemini, and Grok. Chrono coordinates scoped tasks in isolated git worktrees, with tests, cross-family review when triggered, and private Markdown memory. Runs locally in tmux.

    GitHub · Python · 227 stars · 33 forks · +63 stars in 24 hours · Trending score 3.03

  10. 10
    kling01/human-value-allocation

    Evidence-linked analysis of human contributions in human–AI conversations. Research preview.

    GitHub · Python · 90 stars · 18 forks · +41 stars in 24 hours · Trending score 2.82

  11. 11
    synergycodes/workflowbuilder

    Workflow orchestration framework for your product, open source: a white-label React workflow builder, durable execution on your own Temporal, human approval steps for AI agents, and a live view of every run.

    GitHub · TypeScript · 449 stars · 87 forks · +24 stars in 24 hours · Trending score 2.48

  12. 12
    Anionex/dsh-computer-use

    为 DeepSeek Harness 提供电脑控制插件:新鲜 Accessibility 观测、过期状态拒绝、作用域权限与安全输入(目前支持macos)|Accessibility-first macOS Computer Use bundle for DSH with fresh observations, stale-state rejection, scoped permissions, and safe input.

    GitHub · TypeScript · 109 stars · 8 forks · +34 stars in 24 hours · Trending score 2.44

  13. 13
    argilla-io/argilla

    Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

    GitHub · Python · 5,209 stars · 515 forks · +23 stars in 24 hours · Trending score 2.35

  14. 14
    dagucloud/dagu

    Self-hostable workflow orchestrator for teams whose main work isn't orchestration. Declarative YAML over your scripts, SSH commands, containers, etc; keep workflows separate from business logic. One binary, no database, runs on limited H/W resources. Alternative to Airflow / Cron / Job Scheduler.

    GitHub · Go · 4,645 stars · 410 forks · +12 stars in 24 hours · Trending score 2.33

  15. 15
    Anil-matcha/open-agent-email

    Open-source email infrastructure for AI agents: secure inboxes, REST and MCP APIs, SMTP, human approval workflows, signed webhooks, and Python and TypeScript SDKs. Self-host with Docker and PostgreSQL.

    GitHub · Python · 2,136 stars · 393 forks · +28 stars in 24 hours · Trending score 2.29

  16. 16
    petergyang/human-review

    A visual tool to edit HTML and Markdown files, leave comments like a Google Doc, and send feedback to your AI agent. Works inside your favorite AI harness.

    GitHub · JavaScript · 1,461 stars · 125 forks · +24 stars in 24 hours · Trending score 2.19

  17. 17
    Shy2593666979/AgentChat

    AgentChat 是一个基于 LLM 的智能体交流平台,内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作,Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术,实现高效的知识检索与工具调用,使用 FastAPI 构建高性能后端服务。

    GitHub · Python · 935 stars · 119 forks · +15 stars in 24 hours · Trending score 2.05

  18. 18
    mitaku/andon

    A one-person software factory: AI coding agents take tasks from a ledger through review to merge, and call the human only for decisions only they can make.

    GitHub · Go · 166 stars · 3 forks · +61 stars in 24 hours · Trending score 2.00

  19. 19
    ai-swiss/base

    BASE is an open framework and proposed standard for shaping AI through conversation—turning the way you work into a durable, portable method you control across tools and models.

    GitHub · JavaScript · 66 stars · 10 forks · +13 stars in 24 hours · Trending score 1.93

  20. 20
    DY-2026/GameDesignOS

    Local-first game design OS for AI agents: turn sessions into evidence, experiments, reviewable decisions, and durable project memory—Human Gates and rollback.

    GitHub · Python · 459 stars · 58 forks · +14 stars in 24 hours · Trending score 1.92

  21. 21
    iamsonal/pluto

    Run AI agents inside Salesforce on standard licenses. Pluto Core handles model calls, tools, approvals, recovery, and a record of every run. Works with OpenAI, Azure OpenAI, or your own model provider.

    GitHub · Apex · 92 stars · 37 forks · +13 stars in 24 hours · Trending score 1.88

  22. 22
    BrightbeamAI/chap

    CHAP, the Collaborative Human Agent Protocol, is a MCP/A2A-compatible runtime for auditable human-agent work: approvals, overrides, handoffs, escalation and verifiable evidence logs.

    GitHub · Python · 123 stars · 14 forks · +13 stars in 24 hours · Trending score 1.82

  23. 23
    busabase/busabase

    Open-source database & workspace for AI agents — structured data, durable knowledge, reusable skills, runnable apps, and human review on the writes that matter. Local-first and self-hostable.

    GitHub · TypeScript · 929 stars · 110 forks · +2 stars in 24 hours · Trending score 1.81

  24. 24
    XiaoLuoLYG/GOD

    Govern, Observe, Direct - a real-time control room for agent societies

    GitHub · Python · 1,287 stars · 136 forks · +11 stars in 24 hours · Trending score 1.70