Havuz

The execution safety layer for AI agents.

Read-only trading journal and review harness: Jev typed judgments, agent integration, and a reproducible finance benchmark. No orders, no ad

Research Pilot helps AI agents understand, maintain, and advance research projects through papers, claims, evidence, experiments, and human-

Local-first AI project OS that turns coding models into reliable software agents with memory, sandboxed execution, verification, recovery, G

Open-source governance infrastructure for AI-assisted legal work

Measures Jev classifier's confidence is really worth observability.

AIRadar · 每日定时运行的 AI 行业情报工作流

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

Enterprise Zero-Trust AI Security & Governance Gateway: Real-Time Prompt Injection Defense, Action Scoping, HITL Approvals, Post-Quantum Mer

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

AI-automated SDLC pipeline with human-controlled quality gates, for Claude Code — spec before code, evidence before pass, a human sign-off a

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

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

Druks runs agent apps on your own infrastructure: durable runs that survive restarts, human approvals, and full history. Apps install as Pyt

A production-ready toolkit to accelerate and automate the end-to-end lifecycle of AI Agent development.

Codex Pro Max helps you keep working with Codex without interrupting the same conversation.

Local Codex control with bounded runs, crash recovery, and auditable results. Optional ChatGPT bridge.

Open-source, self-hosted AI employees that ask before they act. 46 business roles, approval-gated autonomy, untrusted-content safeguards, sa

Local-first permission gateway for AI agents with scoped connector access, human approval, audit trails, and encrypted local credentials.

Desktop personal AI agent for local projects, coding and learning. Persistent conversations, editable memory, scoped helpers and a living Vi

It lets an AI agent put a live, interactive page on any screen you own, and brings what you do on it back into the conversation.

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

The agent that learns how you decide - and proves it by never deciding for you. A local-first, loop-native runtime for a team of AI agents o

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

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

The human approval layer for AI Agents.

Mail for AI agents ( and humans). MCP server giving Claude (or any agent) safe, permission-controlled access to email (Microsoft Graph + IMA

Build and operate production-safe agents that run in your own environment.

Local-first Agent communication runtime and gateway for A2A, MCP, E2EE messaging, REST/Webhook, and multi-agent collaboration.

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

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.

AI coding agent that shows its work — every step visible, every patch approved by you. Build projects brick by brick, stay in control.

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

影武者 / kagemusha: a Markdown governance kit for Claude Code and AI agents—approval queues, correction promotion, and judgment distillation.

TypeScript SDK for durable agents, workflows, and custom execution kinds. Built by Swirls.

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

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

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

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

TypeScript AI agent runtime. Write your agents in code and choose how predictable they are: deterministic steps where they can be, an LLM on

AI agents and workflows for Kotlin Multiplatform, as small typed graphs: loops, parallel steps, streaming, save points and human approval. I

AI code-review cockpit: Claude reviews PRs into local artifacts; nothing reaches GitHub until you say so

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

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

FinishUP — local-first structured work evidence, deterministic checks, and honest verification receipts.

A PI-led laboratory of AI agents for proposing research questions, testing predictions and reviewing results.

Arcgram — an interactive diagram engine for human–AI collaboration: an AI agent draws its reasoning as an auditable node-and-edge flow and s

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

Self-hosted, cross-platform control plane for persistent AI employees with local channels, replaceable Worker Hosts, human approval, memory,

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