1.deepseek-ai / deepseek-harness
DeepSeek Harness: Everything is a Plugin.
- cordis
- dsh
- dsh-plugin
- ai-agents
Ranked by Attention Score: stars gained over the last 30 complete days
40 repositories by Attention Score · Oct 5, 2026 – Nov 3, 2026 (UTC)
DeepSeek Harness: Everything is a Plugin.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create motion, prototypes, websites, apps, dashboards, presentations, images, and videos with your team and AI agents. Share work, exchange feedback, and iterate together in one workspace.
Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
Build and run agents you can see, understand and trust.
The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.
The agent engineering platform.
Build resilient agents.
Agnes Harness: A pluggable agent harness for Forward Deployed Engineering (FDE). Built for trust. Made for the real world.
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
Your lightweight open-source personal agent.
The batteries-included agent harness.
The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol
Mastra is the modern TypeScript framework for AI-powered applications and agents.
Learning to Recover from LLM Agent Failures at Test Time
Build AI agents that run 100% on-device. Sub-100ms latency on Qualcomm NPU. Zero cloud dependency.
A lightweight, powerful framework for multi-agent workflows
🤗 smolagents: a barebones library for agents that think in code.
The self-driving agent platform
MCP gateway & OAuth MCP servers. LangGraph agent: memory, eval/tracking, PII guard, context trimming. Docker quick start for enterprise agents.
A programming framework for agentic AI
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
A framework for continual learning and recursive self-improvement through harness adapter evolution.
🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.
LlamaIndex is the document processing platform for AI
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
oar (Open Agent Runtime): programming interface for all agent harnesses
An agent that compiles git maintenance chores into reusable programs, then decides whether to replay them by running checks rather than by guessing the task looks familiar
Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
A local-first multi-agent app development platform, built on PenguinHarness
Integrate cutting-edge LLM technology quickly and easily into your apps
Zeline — an open-source agentic AI framework developed by Zerolinear.
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。
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.
No description provided by the repository host.