Havuz

Local-first control plane for long-running and multi-agent AI systems. Observe, steer, recover and orchestrate agents.

基于多智能体（Multi-Agent）架构的 AI 投资分析平台，聚焦 A 股与港股市场，融合情绪面、技术面、资金面和基本面研究能力。 An AI-powered multi-agent investment analysis platform for China A-share

CLODEx, kodlama görevlerini kalıcı bir çalışma alanında sürdürmek için dosya, Git, terminal, browser ve MCP araçlarını birleştiren local-first masaüstü agentic IDE'dir.

Neden yükseliyor · 77 günlük bir repoda 868 yıldız dikkat çekiyor; local-first agentic IDE ve kalıcı görev çalışma alanı fikri güncel geliştirici araçları ilgisiyle örtüşüyor. Ancak son 28 günde commit ve farklı yazar sayısının sıfır olması, ilginin devam eden geliştirme veya topluluk katkısına dönüştüğünü göstermiyor.

An autonomous research colleague — from a question to a compiled manuscript, while you sleep.

Agentlens is a trusted agent trading platform. Here, you can quickly find the Agent that meets your needs, and you can also publish your ow

Event-sourced graph runtime for durable and stateful agents

Personal-Model First Self Evolving AI Agent 🐘

Open-source adversary emulation for AI agents and MCP servers.

Inference-native Tokenmaxxing Agent Harness for Loop Engineering

Run a task with AI as a flow of steps you keep, reuse, and refine, not a one-off chat.

Deterministic safety solutions for probabilistic AI agents

本地优先的 AI 投资研究工作台（AI investment research workbench），支持深度调研、证据化投资论点、投资组合风险分析、自选股与 Pi Agent 副驾驶。

Turn your Win, Mac or DGX Spark into an AI hotspot. Nightshift races hundreds of attempts overnight and keeps what passes. Plus the open con

Govern: one Decionis verdict before a workflow step runs — a deploy, a migration, an infrastructure change, an agent's action — with a signe

Open-source desktop AI agent that gets work done — plans & self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in

CDAF (Cached Descriptive Asset Files) - open sidecar format for video so AI agents stop re-analyzing the same footage. Spec, CLI, agent skil

AI Developer for Unreal Engine — An autonomous AI agent that creates Blueprints, C++, levels, materials, widgets, and more inside the UE5 ed

An AI agent for running, testing, and hardening GitHub Docker Compose apps.一个用于运行、测试和加固 GitHub Docker Compose 应用的 AI Agent。

High performance multithreaded task execution and optimization engine for agents and dweb apps

A full featured, powerful, and efficient AI Agentic Harness/Desktop Agent app designed from the ground up with local inference on consumer h

A Swift reimplementation of a Claude Code-style coding agent, built stage by stage to explore what makes coding agents work

3x more usage on your coding agent, same quality. Have an multi-agent setup in mind? Bello already supports it. Mix models, run agents in pa

This is a fork of the https://dockbox.dev project I made

Agentic text-to-SQL SDK: hand the LLM one execute_sql tool and let it explore the schema, test queries, and self-correct — no RAG, no semant

The open-source agentic framework to build, orchestrate, and operate production AI agents.

Terminal-first, knowledge-grounded multi-agent software delivery pipeline: scope requirements, implement changes, run tests, and gate pull r

Govern consequential AI agent actions in Docker with deterministic policy, human approval, and signed Decision Dossiers.

A collaborative AI system where multiple specialized agents work together to plan, write, edit, and refine complete books.

NEWTON: Agentic Planning for Physically Grounded Video Generation

Graph-Orchestrated Agent Loop — a production-grade framework on LangGraph. Combine workflow graphs and agent loops, transpile Dify DSL to ru

one Memory across your devices and apps

We read all 512K lines of Claude Code's accidentally exposed source. 82 docs, 15 diagrams, every subsystem mapped — from the hidden YOLO saf

An open-source cost controller for AI agent loops — stops a loop when it's actually converged and rolls back before it degrades, instead of

Autonomous multi-agent pentest framework — plans, exploits, verifies (proof-required), CVSS-scores and writes client-ready reports. 104/104

Epistemological database for agent and human efforts, beliefs, and findings.

Top Open-Source AI Engineering Platform 2026 Qyvaria Kernel

Local-first agent platform: board + role agents + agent CLI runs (Claude Code, Cursor, Antigravity, OpenCode) or local and API models (Ollam

AI Agent Toolkit 2026: Smart Device Control for iOS & Android

Edit Videos and Design Images with Claude code or Codex

Production-Grade AI Agent Development Full-Chain Guide: Development, Testing, and Base Framework

Ultimate AI Fitness Coach PWA 2026: Iron Mike Workout & Smart Recipe Agent

Automated Proof-of-Carrying Change Management for AIOps 2026

Agentic prompts are the most important code you're not engineering. PromptKit fixes that — composable, version-controlled prompt components

agent定制自由化，agent流程可视化。在浏览器里用画布搭出工业级 Agent 流程，选框架自动生成架构图， 拖节点、连线、写代码、配模型，点「保存」就把整张画布编译成一个可独立运行的 Python Agent 项目， 点「运行」直接在你的机器上真实执行并流式回传每一步。欢迎

Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-

3-tier agentic ChatOps (n8n + GPT-4o + Claude Code) implementing all 21 patterns from "Agentic Design Patterns" — solo operator managing 137

The $0 AI Empire Playbook — 180 scheduled jobs, 43 free LLM lanes, and the failure classes that almost killed it. Free tiers only.

Loop engineering for software development. Turn any repository into a self-organizing AI engineering team — 8 specialists, contract-driven,

Agentic AI platform with pixel agent technology — autonomous code generation, PR automation & multi-tenant SaaS

Pi coding agent extensions with code intelligence (LSP + Tree-sitter AST), semantic refactoring, code review, web/Context7 docs, and ask-use