技能目录

为 AI Agent 发现可复用技能。

按任务搜索真实的 GitHub 技能,并在使用前查看 Stars、信任、审计、分类和安装路径。

每个推荐都保留与其仓库、审计和安装路径的明确关联。

搜索结果: deepseek-harness

英文目录

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

35K
Stars
85/100
信任
分类: agent-frameworks审计

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

71K
Stars
87/100
信任
分类: agent-frameworks审计

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

68K
Stars
84/100
信任
分类: agent-frameworks审计

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

67K
Stars
87/100
信任
分类: media-automation审计

The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3

66K
Stars
85/100
信任
分类: support-automation审计

A lightweight coding agent for open models like Deepseek, Kimi, and Qwen

64K
Stars
82/100
信任
分类: coding-agents审计

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

63K
Stars
79/100
信任
分类: agent-frameworks审计

Harness Open Source is an end-to-end developer platform with Source Control Management, CI/CD Pipelines, Hosted Developer Environments, and Artifact Registries.

37K
Stars
85/100
信任
分类: devops审计

The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.

22K
Stars
84/100
信任
分类: coding-agents审计

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.

22K
Stars
86/100
信任
分类: data审计

Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.

18K
Stars
87/100
信任
分类: agent-frameworks审计

Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, MiniMax, Ollama, SiliconFlow, Moonshot, openclaw / hermes agent, deerflow

16K
Stars
87/100
信任
分类: data审计