隐私与广告选择
Git-Stars 会使用必要存储来保障网站运行。可选分析和广告测量脚本默认不加载，只有在你同意后，Google 等合作伙伴才可能按要求使用 Cookie 或类似标识符。 隐私政策
Ouroboros — self-creating AI agent. Born Feb 16, 2026.
这个仓库详情页已经具备足够的原创分析、来源证据和同类对比，可以作为 Git-Stars 的可索引评测页。
100
评测分
解决的问题
Ouroboros addresses the fragmentation of AI agents by providing a single agent with a continuous identity and memory that persists across sessions, unlike stateless or task-specific agents. It also enables self-modification and autonomous evolution, allowing the agent to improve its own implementation without human intervention, which is not typically offered by other frameworks.
部署现实
当前可用的安装信号是：Download the latest release from https://github.com/razzant/ouroboros/releases/latest and follow platform-specific instructions (macOS DMG, Linux tar.gz, Windows zip).。这只能作为起点，正式使用前建议让 Codex 或 Claude 检查 README、环境变量、运行时版本和部署目标。
商业可用性
当前记录的许可证是 MIT。这是重要的商业使用信号，但仍应核验许可证全文、依赖许可证、模型/API 条款和商标限制。
能力上限
Developers can build autonomous agents that manage long-term projects, maintain context and memory over extended periods, and coordinate complex multi-agent workflows. Real-world use cases include automated software development, continuous research and analysis, personal AI assistants with persistent memory, and self-improving automation pipelines. The ceiling is high: the agent can theoretically evolve its own capabilities, integrate new tools, and adapt to new domains without manual reprogramming.
Git-Stars 是独立产品，不隶属于 GitHub 或该项目。 分析可能由 AI 辅助生成，依据公开仓库元数据和 README 的短摘要。 我们不镜像完整 README、文档、Issue 或社媒评论。
razzant/ouroboros 被追踪为 Python 项目，主要属于 AI Agent, LLM Tool, MCP Server 方向。这个评估结合公开 GitHub 元数据、分类信号、短来源摘要和 Git-Stars 编辑规则，而不是复制项目文档。
增长检查：该仓库目前有 1.1k Star，今日 +0，本周 +158，本月 +0。这些窗口用于区分持续采用信号和短期曝光峰值。
维护检查：当前活跃度为 一般；最近一次推送距今 63 天，未关闭 Issue 为 77，约占总 Star 的 6.97%。这只是采用信号，不替代工程尽调。
采用检查：587 Fork 和 1.1k Watcher 反映项目被复用和关注的程度。许可证信号：MIT。商业或内部使用前请核验许可证兼容性。
适用判断：当你需要「AI 原型、LLM 工作流和 Agent 类应用」时，这个项目更值得评估；如果「需要法律审查、安全审计或生产 SLA 保证」，则需要谨慎。
来源检查：Git-Stars 当前为这份报告保留了 2 个明确来源引用，近期增长信号为 158。最终安装、安全和版本信息仍应以原始 GitHub 仓库为准。
原创分析
充分已经具备问题、能力和结论层面的原创判断。
来源
充分已附带仓库元数据和 README/来源引用。
许可证
充分已记录 MIT，可作为评估依据。
维护
充分仓库元数据中可以看到近期活跃信号。
同类对比
充分已有足够相近项目用于对比。
热度
1.1k 星标
复用
587 复刻
关注
1.1k 关注者
维护
moderate
许可证
MIT
未解决 Issue
77
Ouroboros is an open-source, general-purpose AI agent with persistent identity, memory, and history across tasks and restarts. It can modify its own implementation, coordinate a swarm of specialist agents, and run as a native desktop app or headless CLI.
核心特性
- Self-modification: can rewrite its own code, architecture, prompts, tools, and dependencies. - Autonomous evolution: runs evolution campaigns that integrate reviewed changes into its Git history. - Persistent memory and identity: continues across restarts with a unified biography.
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
LLM Tool
Libraries and tools for LLM apps, RAG, prompts, and evals
MCP Server
Model Context Protocol servers, clients, and integrations
Download the latest release from https://github.com/razzant/ouroboros/releases/latest and follow platform-specific instructions (macOS DMG, Linux tar.gz, Windows zip).63
健康评分
一般
提交活跃度
Feb 11, 2026
创建于
Aug 12, 2026
最近提交
每日同步积累数据后，Star 历史将在此显示。
复刻
未解决
关注者
razzant
GitHub 主页obra/superpowers
An agentic skills framework & software development methodology that works.
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
NousResearch/hermes-agent
The agent that grows with you
mattpocock/skills
Skills for Real Engineers. Straight from my .agents directory.
multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
✓
许可证
✓
Fork 情况
~ 一般
维护情况
解决的问题
Ouroboros addresses the fragmentation of AI agents by providing a single agent with a continuous identity and memory that persists across sessions, unlike stateless or task-specific agents. It also enables self-modification and autonomous evolution, allowing the agent to improve its own implementation without human intervention, which is not typically offered by other frameworks.
能力范围
Developers can build autonomous agents that manage long-term projects, maintain context and memory over extended periods, and coordinate complex multi-agent workflows. Real-world use cases include automated software development, continuous research and analysis, personal AI assistants with persistent memory, and self-improving automation pipelines. The ceiling is high: the agent can theoretically evolve its own capabilities, integrate new tools, and adapt to new domains without manual reprogramming.
结论
Ouroboros is for developers and researchers who want to experiment with self-evolving, persistent AI agents and are comfortable with the associated risks. It should be avoided by those needing stable, predictable behavior or who are concerned about autonomous self-modification. The key trade-off is between the potential for rapid, autonomous improvement and the loss of human oversight and control.