AI Agents

A self-hosted AI assistant for academic research — manages your papers, searches literature, tracks deadlines, and answers you on the channels you already use.

Built from the ground-up for agents, Vessel Browser is an open source AI browser for Linux/Mac/Windows that provides a durable state, MCP control, and BYOK with full autonomous browsing. Use with Hermes Agent, OpenClaw, or connect to your favorite API provider.

An autonomous AI agentic harness built to code anything, automate terminals, perform cybersecurity tasks, and execute complex real-world workflows with minimal human intervention. From writing and debugging code to analyzing systems, managing files, running commands, and orchestrating tools, Agent-2 turns simple prompts into autonomous execution.

A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.

基于多模态视觉感知与 LLM Agent 的 macOS 微信自动化框架 | Visual RPA for WeChat

🍟 麦麦省钱助手 —— 麦当劳中国官方 MCP 的省钱点餐 Agent Skill：官方 calculate-price 实时核价 + 券组合优化 + 沉默成本体检与多单用券排程，官方券/套餐/团购券/积分四渠道同口径算终局价。免登录在线试算。

GateMem: a benchmark and evaluation toolkit for memory governance in multi-principal shared-memory LLM agents.

Kapso by Leeroo: Long-running agents that optimize AI and Data systems, and learn from every experience. #1 open-source on MLE-Bench; ALE-Bench; RelBench

Top Dynamic AI World Simulation & Storytelling Tools 2026

A Burp Suite extension that exposes the full Montoya API as a local REST API, with Swagger UI

A small terminal coding agent for DeepSeek models: it reads your repository, runs commands after asking, proposes edits as patches you apply, and checkpoints the workspace around every turn so any turn can be undone.

29 essential agentic design patterns for building intelligent AI systems

Token Efficiency For AI Agents

Autonomous multi-agent pentest framework — plans, exploits, verifies (proof-required), CVSS-scores and writes client-ready reports. 104/104 (100%) on the XBOW validation benchmarks, powered by Kimi K3.

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

A Curated List of Coding-agent that treat a program as the executable intermediate representation for Policy, World, Editor and beyond

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.

动手学大模型全栈：CS336 中文精讲 · PyTorch 手搓 Transformer · 单卡复现 Pretrain/SFT/LoRA/DPO/GRPO/RLVR · PEFT/Agent/RAG 落地（含真实实验、曲线与复现脚本）

Fluent is a self-improving software factory. It autonomously turns your team's vision, ideas, bug reports, user feedback, production logs, and agent traces into working software.

Automate viral reel/tik-tok videos via AI multi-agent system. ~$0.1/reel.

Local-first agent platform: board + role agents + agent CLI runs (Claude Code, Cursor, Antigravity, OpenCode) or local and API models (Ollama, LM Studio), all on your own Pc

Open-source agentic security operations platform:

Hermes Agent plugin: say 'make me a <role>' and your agent builds a complete, working Bot — name, face, SOUL.md, memory, tools, skills, routines, gateway.

An end-to-end framework for Agentic Reinforcement Learning.

An "LLM wiki" upgraded to a real database — typed entities, graph relations, HTTP API, and a built-in natural-language agent.

Open-source platform for AI chat agents that answer from your own knowledge base. Hybrid RAG search in PostgreSQL, MCP and custom tools, guardrails and human handoff. Put agents on a hosted chat page, a website widget, Slack, Teams, WhatsApp, Telegram or a REST API. Self-host with Docker and open-weight models.

Spec2Case 是生产级 AI 测试用例生成智能体，支持图片/文本需求理解、人工确认、LangGraph 流程编排和 Excel 用例导出。

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。

Source code of Local Code, a private AI agent for Mac, iPad and iPhone. Runs DeepSeek 4.1 on device, with Python, Node.js and a shell built into the app.

Autonomous DFIR agent: point it at disk images, memory dumps or log exports and get back an investigation that shows its work. Volatility 3, Plaso, YARA and any OpenAI-compatible LLM.

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。

Multi-agent research execution system: paper reproduction, benchmark evaluation, AutoResearch and claim-evidence graphs

Autonomous AI Lead Generation, Social Discovery & Smart Conversational Growth Agent for Threads & Instagram. Multi-platform with native browser CDP.

An agent-native QA CLI for web pages. Deterministic, no tests to write, no LLM.

Open-Source Intelligent Command Layer

An opinionated list of awesome Pydantic-AI frameworks, libraries, software and resources.

AtlasAgent - an auditable AI agent control plane: evidence-backed memory, governed tool runtime, checkpoint DAG recovery, and a 55-chapter engineering tutorial. FastAPI / Next.js PWA / Textual TUI

Agent framework for smart-cockpit apps · 面向智能座舱业务的 Agent 框架:零后端、权限分级、确认流、卡片编排、快慢双层、真实三方集成,加能力=加数据不加代码

SkillAdam: Better Skills for Your AI Agent🚀 Claude Code/Codex/Cursor 插件，一键进化你的skill

CrewOS 是一个关于企业 Agent 产品形态的公开实验。 我正在尝试回答一个问题： 当 AI 已经能够完成任务以后，它能否进一步接住长期、复杂、持续变化的真实业务？ 这里会持续记录产品原型、设计实验、思考过程以及失败的假设。 如果你也在研究类似问题，欢迎一起讨论。

CYPRESS (Contextual Yield Protocol for Routed Expert Seed Systems) — a project- and vendor-agnostic multi-agent seed for AI coding tools. Drop it into any repo to give agents a large number of per-role expert team, named protocols, a progressive-discovery knowledge graph, and spec- and test-driven discipline by default.

A memory governance engine for multi-agent cloud knowledge bases — one knowledge base shared by every agent and every device, with consistency guaranteed. Pure Markdown, nine governance automations, zero dependencies.

A simple yet versatile context engineered for scalable online data collection

Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideation, adversarial critique, and design-space exploration. 12 framings × hard-ban-on-incomplete-leaves × stable convergence.

Portable, verifiable work state for coding agents

The Agentic-Native Operating System

Nosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in toolset, Skill / Plugin / MCP extensions, one runtime shared by GUI and TUI, and file-persisted sessions, plans, and memory.

Agent Factory is an open-source studio for building, editing and chatting with AI agents. You build them from simple nodes: LLM calls, HTTP requests, JavaScript, memory and sub-agents. It runs locally with one docker-compose command, and ready-made testing agents are available in the shared agents-store repo.

Estrella Bot · QQ 群 AI 群友机器人。把 QQ 小号接给任意 OpenAI 兼容模型（本机 / DeepSeek / 智谱 / 通义），让 AI 像群友一样插话、接梗、潜水。OneBot v11 + NapCat，零构建网页控制台。Apache-2.0

RAM efficient terminal agent harness for coding, cybersecurity, and automation.