AI Agents

An automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.

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.

A repo lists papers related to LLM based agent

AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate solutions, and synthesize the best approach for your code.

Organization-as-Code for autonomous AI agents. Brain-inspired memory that grows, consolidates, and forgets. Multi-model (Claude/Codex/Gemini/Cursor/Ollama).

Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!

Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.

Persistent Agent Workspace — AI agents that remember, collaborate, and never start from zero.

Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.

A copy-paste system prompt that has your coding agent (Claude Code, Codex, Cursor) build a self-improving agent system for any computer work.

AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro.

RikkaHub Agent · Pure — an Android AI agent that survives long runs. Independent hardening pass on the rikkahub on-device agent: usage ledger & budgets, on-demand tools, expert sub-agents, cold memory, chained workflows. Kotlin/Compose, Shizuku/Termux/MCP. QQ group 1030362371.

Mission control for AI coding agents. Watch Claude Code, Codex, Gemini and a dozen more work live in one macOS terminal: live status, an editor that follows their edits, undo for any turn, approvals from your phone and local models. 20+ built-in tools, all on the site below. Built on Ghostty.

A self-hosted workspace where people and AI agents work together

The most autonomous AI agent framework: runs unattended on GitHub Actions, self-healing skills, drives Claude Code, Grok, Codex & more. No approval loops. Configure once, forget forever.

Harness engineering in two books: constraints, query loops, context governance and multi-agent verification in Claude Code and Codex. harness-books.agentway.dev

Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz

LuaN1aoAgent is a fully autonomous AI-driven penetration testing agent powered by graph-based cognitive reasoning.

ClawX is a desktop app that provides a graphical interface for OpenClaw AI agents. It turns CLI-based AI orchestration into a desktop experience without using the terminal. China website is https://clawx.com.cn.

AI Multi-Agent Framework in .NET

Open-source (AGPL-3.0), self-hostable lights-out software factory for the agent era: label a GitHub Issue, get an independently reviewed, merged PR and a tagged release.

Run coding agents like infrastructure, not terminal sessions. Warren manages isolation, lifecycle, spend, recovery, and Git delivery on compute you control.

Independent Android client for Codex with on-device tools, live voice, and Claude/Gemini collaboration. No Termux or PC server required.

Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform

A codex plugin for running optimization loops inside a codebase. It is useful when you have a measurable target and many possible changes to try: test runtime, build speed, bundle size, model loss, Lighthouse scores, memory use, query latency, or any other metric you can print from a script.

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

BINNY: an open source agent harness for reverse engineering. Plug in any model, or a local one.

A Web3 wallet and agent platform for the Unicity network - crypto wallet, DMs, group chat, and marketplace.

Pocket Flow: Codebase to Tutorial

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

Full-stack AI agent for coding, files, terminals, tools, research, content, multimodal work, and multi-agent workflows.

Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt. File-only, no external services.

Smart Promise Tracker AI 2026 – Commit Memory Engine

Autonomous LLM Trading Asterism — a research-only multi-agent trading platform with evidence-first research, an auditable console, Shadow simulation and explicitly authorized broker execution.

Deterministic agent harness for Temporal (in Rust)

Monid - OpenRouter for agent tools. Join our community at https://discord.gg/rQzztcgJV8

Multi-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.

The AI agent that always stays sharp. 200k+ tokens of work in a 64k context. Sandboxed for unattended overnight runs. Sub-10ms Go CLI, any model.

Cayu is an open-source Python framework for building and running domain-specific long-horizon agents, with a durable runtime built in.

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

剧本分镜智能体（PenShot）：电影/动漫/短剧/小说→分镜片段→视频提示词。基于 LLM 通过 LangGraph+LlamaIndex实现任意格式剧本的自动解析，生成 Sora/Veo/Runway 等模型可用的连贯text-to-video提示词。保持角色/剧情跨片段一致，支持 MCP/REST API/Function Calls/A2A 集成。（LLM-powered text-to-video-prompt agent. Break scripts into Sora/Veo-ready shots with character consistency）

结合多大模型分析与确定性代码风控的自主量化交易系统 ｜ Autonomous crypto trading system with multi-LLM analysis, deterministic Python risk control & OKX execution.

A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows

Enables organizations to create and deploy customizable AI agents with support for multiple LLM providers, real-time chat, voice, document training, analytics, user management, SSO authentication, and embeddable widgets. Built with React 19, Redux Toolkit, Radix UI, and Tailwind CSS.

Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation.

Pi.NET 是 Pi 的 .NET 10 移植版。Pi 是一个极简、可扩展的 Agent harness（TypeScript monorepo，约 17.1 万行），本项目把它的核心库逐一移植到 net10.0，让 .NET 生态用上同一套能力。

The agent loop for Rust — stream from 7 LLM protocols, run tools, loop until done. From a laptop to a Cloudflare Worker.

Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.

A design system for AI applications. Material, physical, tactile, technical.