ouroboros
Agent OS：智能体自我进化。我们只守住底线：评分命令和预期结果绝不写入交给它的成功契约。面试门控、分阶段评估、有预算的进化循环。MCP 服务器，13 个运行时：Claude Code、Codex CLI、Gemini CLI、OpenCode、Copilot、Kiro 等。
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
怎么安装
dsh plugin add github:Q00/ouroboros git clone https://github.com/Q00/ouroboros ~/.claude/skills/ouroboros 简介
◯ ─────────── ◯ ◯ ─────────── ◯ bash curl -fsSL https://raw.githubusercontent.com/Q00/ouroboros/main/scripts/install.sh | OUROBOROS_INSTALL_REF=readme-hero bash **Turn a vague idea into a verified, working codebase -- across Claude Code, Codex CLI, OpenCode, Hermes, Gemini, Kiro, Copilot, Pi, Zcode, Goose, GJC, Antigravity, and Grok.** Ouroboros is an **Agent OS** for AI coding: a local-first runtime layer that turns non-deterministic agent work into a replayable, observable, policy-bound execution contract. It replaces ad-hoc prompting with a structured specification-first workflow: interview…
推荐参考
信息
- 协议
- MIT
- 语言
- Python
- GitHub 星标
- 6.1K
- 月下载
- –
- 最近更新
- 2026-09-23
- 创建于
- 2026-01-14
基础安全检查
- 检查结果
- curated 收录但无 npm 包/安装命令
- 收录来源
- curated:awesome-dsh-plugin/awesome-dsh-plugin, curated:punkpeye/awesome-mcp-servers
- 主题标签
- agent-os, agentic-ai, ai-agent, ai-coding-agent, claude-code, cli, codex, coding-agent, deepseek, developer-tools, dsh, dsh-plugin, llm-evaluation, llm-orchestration, loop-engineering, mcp, opencode, skill, skills
同类推荐
langfuse
langfuse/langfuse
🪢 开源AI工程平台：LLM评估、可观测性、指标、提示管理、游乐场、数据集。与OpenTelemetry、LangChain、OpenAI SDK、LiteLLM等集成。🍊YC W23