#agent

A slide framework built for agents.

企业级 AI 资源纳管平台，提供统一 AI网关、Token调度能力，纳管 OpenAI、Azure、Claude、DeepSeek 等主流模型，并支持 MCP 工具与 Skill 的集中注册分发。具备内外双轨定价、成本归因、统一身份认证、安全审计与效能报表，帮助企业精准控制成本、量化 ROI，高效治理 AI 资产。

The simplest, thinnest harness that gives an LLM complete freedom to control a Mac.

Free, open-source AI Office suite (Word, Excel, PowerPoint, PDF, Markdown) — macOS build, one-click install

94 specialist Blender skills for Cursor, Claude Code, Kiro & Codex -> MCP-powered production pipeline from blockout to engine export.

Import conversation history from 25+ AI coding agents into DeepSeek Harness as resumable sessions — tool calls, reasoning and results kept intact, with reverse export and sync. | 把 25+ AI 编程 Agent 的聊天记录导入 DeepSeek Harness 继续对话，保留工具调用、推理与结果，支持反向导出与同步。

Dulus Ai — Agentic AI, Making Gemini web cappable of running bash commands in your terminal! [Gui, Web, Cli, Telegram, 2,000 MCP, 100K Skills . LiteLLM (100+ providers), local models via Ollama, /lang in 34 languages, Mesa Redonda, I create the first utility coin that can be used 100% as AI quota or Fuel, is called $Dulus

沙漏记忆系统 V2.20.1 (V3架构) — pip install nexsandglass。纯本地零依赖，记忆之流编织时间。Drift-Weaved Time: The Soul Forged from Memory Flow

Ultra-lightweight native AI agent framework written entirely in Object Pascal for Delphi and Free Pascal, designed for performance, portability, and extensibility.

DeepSeek Harness (DeepSeek 官方 agent 浏览器 UI) fnOS 应用 — 本地常驻服务

Device Context Protocol — bridge LLM agents to physical devices. Sub-50-byte frames, 27.6KB flash / 0.6KB RAM measured on ESP32, capability-scoped and safe by design. Complementary to MCP. Paper: arXiv:2605.26159

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM

A terminal coding interface that brings the DeepSeek Harness kernel's full capability set — special modes, plugins, model & subagent management — to the terminal. Interaction layer inspired by Claude Code, Codex CLI, and Pi agent; model-switch animations; unified panel key grammar. Tracks the latest upstream RC. Self-iterating since 1.0.0.

Ryu is the open-source layer around your agents. Bring Claude Code, Codex, OpenClaw or your own. Start without building from scratch, add tools with plugins, and turn your agents into apps. Monitor every run and control what your agents can access.

Oh My Tianshu 是一款完全体开源 coding agent:在 dsh harness 基础之上带视觉、跨会话记忆、验证门、agent 路由、语义 + 图谱代码检索、文件回滚和全屏终端 UI——全部以插件组合。它是 DeepSeek Harness(dsh)的友好 MIT fork,保留上游一切皆插件的架构,界面交互对标 oh-my-pi。

Claude Code-style terminal UI for DeepSeek Harness agents, as an out-of-tree dsh plugin bundle

Mnemosyne OS 8.0.0 — zero-dependency, local-first AI memory system (MCP / API / CLI / Python). MIT. https://ai-memory.net

Give your DSH agent hands: drive a real browser (Edge/Chrome over CDP) from the chat — ref-driven clicking, per-session browsers, and a live cockpit panel. Zero runtime deps, no API key.

Touhou-inspired Agent Skills: distinct, testable, composable problem-solving workflows.

微信读书 CLI / WeRead CLI: 基于官方支持 API，面向人类与 AI Agent 的书架、笔记、划线、书评、阅读统计和推荐工具。Official API-based WeRead command-line tool with Agent Skill support.

一个记住你的本地浏览器agent (A local browser agent that remembers you)

Umbrella for the LLM Dark Patterns Hooks suite — single-purpose Claude Code Stop hooks that suppress sycophancy, paternalism, false-success, permission-loops, training-cutoff confidence at the textual boundary.

Not just an agent demo — a local coding-agent platform: plan mode, sub-agent teams, cron, memory, MCP. Single Go binary, DeepSeek-native, MIT.

Turn your Cursor AI agent's work and your own typing into live, generative music 🎼

An autonomous orchestrator for the Copilot Go SDK in Neovim, delivering a native, agentic coding experience.

Evidence-grounded scientific agent system for research automation, citation verification and paper production.

Lightweight agent that pulls and runs LLM benchmarks from Protorikis Bench

Claude Opus 5.5 with the effort level re-decided every step by the TypeSafe Jev reflex — without breaking the prompt cache. CLI + Claude Code plugin.

Launch agents in seconds. Scale to hundreds.

⚡ DSH 指挥家 / Conductor for DeepSeek Harness — in-session dispatch to 11 external agent CLIs (Codex, Claude Code, TraeCode, OpenCode, Gemini, Cursor, Kimi, Qwen, Copilot, WorkBuddy, Grok). Zero-dep skill + host-only bundle.

ESG knowledge graph + RAG agent. Turn long-form sustainability disclosures into cited answers, extracted entities, and a reviewable graph of evidence.

A reliable text/image to CAD Agent harness that supports different MCPs and LLMs

A gateway + skill letting Claude Code agents collaborate across machines

🏛️ Multi-Agent Debate & Brainstorm Studio | 本地多Agent辩论&头脑风暴 — run Hermes/Codex/Ollama on your machine

Review every file Claude Code touches — accept or revert with one click.

An autonomous AI chatbot built for WhatsApp using Node.js, Baileys, and the Vercel AI SDK powered by OpenAI. Designed to act like an active, context-aware participant in group chats and direct messages, Quart goes far beyond traditional command-and-response bots by actively listening and engaging in human conversations.

Self-hosted, pluggable personal agent that gleans signal from RSS, scraping, search, and APIs — processes it with any LLM, then delivers on a schedule to whatever sink you wire up

Docs site of OpenAgent: https://github.com/the-open-agent/openagent

Local-first memory engine for AI-agent teams — private/team/project ACL, associative recall, federated sync, and a built-in MCP server. One SQLite file, no LLM required. Apache-2.0.

Desktop GUI for running multiple Claude Code agents in parallel, organized by task