Havuz

把智能体当函数，把想法写成程序。Agent-native functional language with a CLI, Web IDE, goal-driven bots and live UI. Source-available; no AI training.

Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans i

Visual builder and execution engine for AI powered organizations

Multiplayer harness that shapes around your work. Agents, apps and workflows your team shares, used from Slack, Telegram, WhatsApp, Teams, E

Self-healing infrastructure for AI agent payments. 90.3% auto-recovery.

Open-source AI business orchestration platform for running governed AI agents across ERP, CRM, Microsoft 365 and other business systems.

CrewOS 是一个关于企业 Agent 产品形态的公开实验。 我正在尝试回答一个问题： 当 AI 已经能够完成任务以后，它能否进一步接住长期、复杂、持续变化的真实业务？ 这里会持续记录产品原型、设计实验、思考过程以及失败的假设。 如果你也在研究类似问题，欢迎一起讨论。

Your job landing in one conversation

Source-available, self-hosted AI agent workspace for small businesses and lean teams — with BYOK, workflows, tools, and human approvals.

Reusable Codex + Claude Code skill and plugin implementing Anthropic's AI-Native SDLC: Plan → Design → Build → Test → Deploy → Maintain, wit

DeepSeek Harness control center for balance, usage, peak/off-peak pricing, encrypted multi-account switching, health checks, reminders, rech

Offline-first Python AI agent that runs a tiny research business: quotes each job against its own costs, collects via Stripe, fulfils with N

Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and reviewable automations. Local memory; local or clo

Stop re-explaining yourself

开源 · 本地优先的 AI 智能体：编程与实干兼备。 自带模型密钥，内置 MCP、技能、插件、工作流、知识库以及数据库。

Nirvana-OS engine: ready-to-run agentic operations. One sentence in, finished work out. Source-available engine for companies, squads and mi

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

Aetox harness: a local-first Windows AI environment - model, skills, team and memory as one system. Two doors - an Assistant that adapts to

Engineering workflows for AI coding agents or flesh engineers. It helps absorb silent base-model quality drift.

The control layer for agentic AI. A protocol-aware proxy that applies identity, policy, trust and payment controls to A2A, MCP and DIDComm t

Self-hosted AI agents with persistent memory, browser and computer access, and scheduled workflows.

Production-grade software delivery for coding-agent teams on Multica — dynamic planning, deterministic execution, verifiable delivery.

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

Open-source agentic software development platform for building, orchestrating and monitoring autonomous AI coding agents.

All-in-one open-source framework & middleware for enterprise-grade multi-tenant and multi-tier XaaS Services development

Dynamic graph runtime for building, adapting, and observing multi-agent LLM systems in Python.

Turn a one-line idea into a branch with tested, reviewed, committed code. The brainstorm-to-commit pipeline for Claude Code.

Run a team of AI agents on your own computer. Your files, browser sessions and passwords stay local. Works with Claude Code, Codex, hosted o

Codex skill for generating editable Excalidraw diagrams, previews, web links and iterative diagram workflows.

Compile an AI agent's repeated workflows into deterministic, auditable routines that replay for free, with a fallback to the agent.

Graph-native studio, runtime integration, and self-hosted observability for mutable multi-agent LLM workflows.

Production Claude Code skills for n8n from a Verified Creator's 100+ workflows

Open-source AI employees that ask before they act. 46 business roles, approval-gated autonomy, sandboxed code, Graph RAG on your own documen

A complete engineering team in one folder: 26 specialist agents, 20 workflow skills, orchestrated workflows and quality gates.

Agentizable: an open-source bounty network where AI agents post, fund, claim, solve, verify, and get paid for digital work.

Stateful execution layer for browser agents.

Your Local Email Agent

Detent is board-driven agentic work orchestration, shipped as a single Go binary — it watches a GitHub Projects board and runs each ready is

AI-agent toolkit for structural biology: design binders, map structures, screen candidates, rank results, and prepare cloud-scale runs.