AI Agents

Auto researching harness that burns through everything.

Frontier-level agent capabilities with nothing more than high-quality data and a simple training recipe: 2 SFT + RL, no mid-training/DPO/OPD. Full recipe released.

面向个人用户的一站式智能财务管理平台，覆盖日常记账、账单统计、预算、资产、发票及财务数据管理，并通过自然语言交互、RAG 与 Agent 工作流提供智能记账、财务问答和个性化分析，同时支持社区互动与用户成长体系。

seanswarm: multi-agent workflow pack for coding agents (Claude Code / Codex / Cursor) - evidence-governed research fan-out, dual-read docs, dev delivery with independent review, and visual acceptance gates.

阶跃星辰 Harness｜让 AI 在桌面真正开工：订阅与 API、多代理工作流、插件、Mini。A desktop AI workspace powered by Step Code.

Human in the loop for agent workflows

An application to manage your Hermes agents. Available on Windows, macOS and iOS (soon).

Visual builder and execution engine for AI powered organizations

BYOB Table Protocol v0.1 and reference implementation: bring your own agent (MiniMax Code and others) to one shared table for any-topology discussion and collaboration.

Open-source live workspace where AI agents work alongside your team in real time: live docs, sheets and slides, a shared browser, a Linux desktop and full-duplex voice. Bring Claude Code, Codex, Gemini CLI or any LLM. Self-hosted, MIT. Built by MemoAir (memoair.ai).

Turn intent into work. Open-source Desktop/Web agent harness with long-horizon memory, live evaluation and recoverable batches.

A lightweight coding agent 🧑‍💻 built from scratch, with tool calling, session persistence, workspace context, memory, and multi-provider LLM support 🛠️.

Open cross-harness protocol with terminal and local web interfaces

Autonomous trading agents with deterministic execution. The agents propose; the system decides.

Self-hosted web workspace for the Pi coding agent on desktop, tablet & phone: subagents, scheduled tasks, MCP, memory and a bring-your-own image/video/speech lab. 自托管 AI 编程 Agent 网页工作台：多 Agent、定时任务、MCP、记忆与多媒体，电脑/平板/手机随时接着用。

AI Agent Engineering 101 — SeoulTech 2026 Fall. Lecture notes and PR-based assignment submission.

面向 AI/CS 科研的多 Skill 实验智能体：助力全自动科研实验，以 Claim 驱动、骨干实验优先、独立结果审计与 Evidence Freeze，把发散的模型能力收束为可追溯、可复现、可收敛的论文证据。

An agent hub for Claude Code: one hub runs teams of Claude Code agents across all your projects, with delegate mode, reviews and gates.

This repository is a collection of independent skills and tools for software development and automation. Each skill is a self-contained project with its own purpose, implementation, and documentation.

An Agent Skill: drive Cline CLI coding tasks as the user's proxy.

Kether-governed AI agent orchestration with Pi/MCP, isolated workers, LSP tools, and a portable Windows/WSL2 installer

Weft Coordination Protocol (WCP): live coordination for parallel coding agents across harnesses, built on Cloudflare. An Atelier (elier.ai) open-source project.

An AI workforce on your desktop. Describe the work; a team of AI agents does it in the open and hands it back checked. Any model, any harness: Claude Code, Codex, Hermes, any ACP agent, or you. Windows, macOS, Linux.

基于 LangGraph 的多 Agent 深度研究助手：可中断恢复、按依赖并行、引用治理与评测，成本降低 45%

A Codex skill for CTO, product manager, and engineer teams with task routing and completion follow-up.

A small, free, open-source Mac and Windows app for talking to your AI agents, WhatsApp-style: OpenClaw, Hermes, Claude Code, Codex and any ACP agent, on every machine, are contacts with their own chats, and a little guy in the menu bar (or taskbar) shows who needs you.

Open-source multi-agent coding harness. Coordinate Claude Code, Codex, Cursor, Gemini CLI, Copilot, and more to split work, communicate, and hand off tasks at limits. Local-first, no account required. Works on macOS, Windows, and Linux.