Havuz

A production-grade reference implementation for LLM agent systems: flow declared as a LangGraph graph, Pydantic AI for typed agents, generat

Hand agents the keyboard. Keep the whiteboard.

An AI writing skill that turns agent-generated drafts into clearer, warmer, more human documents by removing templated phrasing, markdown cl

Review every AI edit before it touches your LaTeX. A local web app: comment on a passage, get a word-level diff, accept or reject. Uses Clau

State-Aware Collaboration Protocol: auditable work receipts for AI agents.

An open-source desktop AI agent foundation powered by OpenCode and connected through OpenConnector, with local tools, permission controls, a

An AI-assisted newsroom workflow system for event tracking, evidence organization, approval chains, correction handling, and post-publicatio

面向企业合同全生命周期的生产级 AI Agent 平台，支持合同解析、条款结构化、风险审查、HITL 人工确认、版本管理、客户回传 Diff、谈判辅助及 PDF/Email 交付；基于 LangGraph + RAG + ContractPolicy + Agent Workfl

A workflow-driven AI agent framework that executes YAML-defined decision trees.

Measures Jev classifier's confidence is really worth observability.

Local-first MCP coordination hub for multi-agent teams, with durable messaging, handoffs, governance, and observability.

Run your own AI team from your phone. Claude Code, Codex and more on your own server: shared tasks, always-on agents, a small composable bas

Continuum — the agent runtime by ShyftLabs. Build, orchestrate, ship.

A work-centered runtime for agentic software engineering. Work persists; agents, context, and graphs assemble around it.

Agents propose. People approve. Change control for AI agents: everyday work runs on its own, anything an agent can't take back waits for a t

Open-source desktop AI agent with an embedded browser runtime and human-in-the-loop control.

Human escalation for Solari browser agents — hand off the live session, solve the blocker, resume in the same session.

A Python app that shows how an agent calls tools, saves results, and recalls them after a restart.

食毅：已上线的 AI 饮食记录微信小程序，采用多模态识别、Human-in-the-loop 与确定性营养护栏

ALGAL is a programming language for agents. Programs pause for approvals, survive restarts, replay from recorded effects, and improve throug

oly runs coding agents and long-running commands in persistent, supervised terminal sessions. The daemon owns the PTY, so you can close your

Elixir-native LangChain, LangGraph, and DeepAgents for traceable LLM apps: OTP workflows, tools, memory, human-in-the-loop, streaming, custo

Open-source, local-first job search app for private discovery, evidence-backed fit scoring, truthful resume tailoring, durable workflows, an

The execution safety layer for AI agents.

Open-source alternative to Claude Artifacts for every coding agent. Any agent ships a self-contained page or app to a live URL — Claude Code

Assessment-driven, local-first learning agent built on an observable Agent Runtime and eval harness—grounded ingestion, trace replay, HITL a

Muffin — one owner-run personal agent: continuity of memory, work and authority across models, tools and surfaces.

Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a clai

Open-source full-stack AI agent with an embeddable React UI and FastAPI runtime. Self-host with streaming, pause/resume, durable state, and

半人马环 Centaur Loop：AI 员工的最小工作单元框架。把复杂岗位拆解为可由 AI 接管、由人类治理、由反馈和记忆持续进化的循环工作流 / The smallest work unit for building AI employees.

DeepSeek Harness Web GUI 的网页预览与元素批注插件，让 AI 根据可视化反馈直接修改前端源码。

Observe AI agent runs and control consequential actions. Signed policies, exact-action approvals, AuthZEN API vetoes and evidence. MCP gatew

AIRadar · 每日定时运行的 AI 行业情报工作流

Build micro-vertical AI products with memory, workflows, human approvals, and governed improvement. The open-source engine behind every Aree

One dashboard for all your AI agents — manage teams across Claude Code, Codex, Gemini, Aider, and more. No database required.

The gate between an AI agent and real money. Runtime authorization for financial AI agents: structured intent, deterministic policy, human a

Rules-and-receipts layer for AI agents that spend money: plain-English policy → human approval → signed receipts anyone can verify.

👁️ The visual layer for CLI coding agents. Pipe JSON → interactive native UI → modified JSON back. Like fzf, but for visual decisions.

Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing

Generative UI for working with coding agents. Review, annotate, brainstorm, and give feedback through task-specific desktop workbenches.

Build and supervise scheduled AI workers with an open-source runtime, human approvals, run logs, REST API, and MCP tools.

NOW you can let AI agents make code changes without losing engineering control.

Let your AI agents call and text your actual phone (iPhone or Android) — Claude Code plugin + agent skill

Local-first Agent Skills for safe social-web workflows—starting with Douyin and designed around reusable browser adapters.

Extracts claims from SOPs, policies and regulations, has a person approve or reject each one, then serves the approved set to agents over MC

The live attention layer for Paperclip. Re-stacks approvals, issues, and agent signals into now, next, and ambient.

A Sovereign Agent Governance Protocol for Deep-Water Workflows

Personal, endpoint-encrypted CAPTCHA handoff between an Agent and Android

Policy-aware AI permission reviewer for OpenCode V1 and V2. Evaluates tool and command requests, allowing, denying with feedback, or escalat

Evidence-grounded AI secretary for Claude Code and Codex, with frozen context, deterministic retrieval, bounded quality review, and explicit