Havuz

基于 Git 的项目上下文管理：每项需求的上下文跟代码存在一起。| Git-based project context management: each piece of work's context lives with the code.

Personalized top-conference recommendations, human-guided paper notes, and shareable research galleries that grow with your work.

Evidence-grounded AI agent for Java code repair with LLM-guided patches and human-in-the-loop review.

Open-source browser automation broker for AI agents: persistent Chrome profiles, proxy-aware identities, remote API, MCP tools, browser-use/

Runtime-adaptive steering layer and portable control contract for hard agentic work: durable goals, proportional control, bounded delegation

Shepherd is an end-to-end AI Software Engineering platform that supervises the complete software delivery lifecycle—not just code generation

VERDICT — a DFIR agent (Claude Code as the engine) that produces a signed, offline-verifiable verdict. SANS Find Evil! 2026.

Inline review tool for MDXG markdown — capture highlighted comments and export them as structured JSON for LLM agents.

Bring your teammates into your AI coding agent's planning loop. An MCP server that routes your agent's design questions to a shared web page

A manual-first, human-in-the-loop workflow harness for AI-assisted development—aligns plans, approval gates, validation, and project state a

An agent that builds agents — closed-loop AI system that interviews, designs, tests, and ships standalone Python agents.

Turn one ZCode conversation into a restartable multi-agent workflow with persistent memory, isolated coding agents, real-result checks, and

面向 Vibe Coding 的能力增强型协作框架（Harness），让 Vibe Coding 看得见，可审查、可学习、可进化。

AI Agent 浏览器自动化 CLI：Chrome CDP 操控、会话复用、多 Agent 隔离与人工接管。Browser automation CLI for AI agents with CDP, reusable sessions and human-in-the-loo

音乐发行管理工作台：上架台账、平台账号与填表辅助，提交和签署由人确认。 / Music release management dashboard with listing records, platform accounts, and form-filling assistanc