ByteZone
Back to listClaim this project

razzantAI apps

ouroboros

Ouroboros is an open-source, general-purpose AI agent with durable cross-restart memory that coordinates specialist swarms and rewrites its own implementation.

  • Full stack
  • Backend
  • DevOps
  • AI coding
  • Automation
  • Productivity
  • Collaboration
  • Desktop
  • CLI
  • Windows
  • macOS
  • Linux
  • Self-hostable
  • Runs locally
  • Docker supported
  • Needs API key
Open websiteView on GitHub
ouroboros screenshot
Popularity
1.2k Stars
GitHub stars
Recent activity
8/28/2026
Updated in the last 30 days
License
MIT
Permissive

Why it matters

We look beyond stars: what problem it solves, whether it creates real utility, and what makes its approach worth noticing.

Last 90 days

Problem

Addresses the limitation of AI coding agents lacking persistent memory and self-evolution capabilities across tasks and restarts.

Practical value

Provides desktop and headless CLI runtimes supporting remote APIs or local GGUF models, executing coding tasks via Claudexor.

Innovation / differentiation

Enables the agent to autonomously modify its core code, prompts, tools, and dependencies while maintaining identity and memory continuity.

Leverage potential

Includes multi-platform installation packages and optional CLI installer commands to lower the barrier for local deployment.

Why now

Arrives during a period of rapid growth for coding agents and autonomous systems, targeting long-running and self-improving workflows.

Community activity

In the last 90 days there were 149 new issues and 163 pull requests; the bounded issue/PR samples include 13 issue authors and 16 PR contributors, with at least 50 releases.

Maintainer responsiveness

The 100-issue window sample had a 15% close rate, and the 100-pull-request sample had a 89% merge rate. Maintainer-response observations covered 100% of that issue sample, with a 21% response rate and median first response of 2.2 days.

16 contributors in PR sampleAt least 50 releasesIssue response rate 21% · sample 100 (100% coverage)Median first response 2.2dPR merge rate 89% · 100 sampled in window

Key highlights

  • Modifies its own implementation including application code, architecture, prompts, tools, and dependencies, while reflection reshapes self-understanding.
  • Maintains durable memory and historical identity across tasks and system restarts.
  • Runs as a native desktop application or headless CLI using remote APIs or local GGUF models.

Quick start

How it is installed, how hard it is, and where to start.

Where it runs

To be confirmed

Difficulty

Easy — follow the steps

Docker supportedSelf-hostableRuns locally
  1. 01Download the desktop installer package for your operating system (.dmg for macOS or .zip for Windows).
  2. 02Move the app to your applications folder or extract the archive, then configure model access and review policies through the first-run wizard.

Best for

  • Teams that want data on their own servers
  • Developers who want to try it on their machine
  • People who prefer Docker deploys

More about it

Ouroboros is an open-source, general-purpose AI agent designed to maintain identity, durable memory, and history across tasks and restarts. It works on external projects while coordinating a live swarm of specialist agents in parallel.

The runtime operates as a native desktop application or headless CLI, keeping repositories, durable memory, and history locally on your machine while utilizing configured remote APIs or local GGUF models for inference.

Sources

Each field shows its status and source — expand to review.

15 · Expand

  • capability tags

    Verified

    ai_coding, automation, productivity, collaboration

    Source: admin_cms · cms editor · 8/27/2026

  • editor note

    Verified

    {"en":"The project runs as a native desktop application or headless CLI, supporting remote provider APIs or local GGUF models. Its defining characteristic is enabling agents to modify their own implementation and maintain continuity across restarts.","zh":"该项目兼具原生桌面端与命令行运行时，支持连接远程 API 或本地 GGUF 模型。其核心特性在于允许代理自主修改自身的应用代码、提示词、工具和依赖项，并保持跨重启的身份连续性。"}

    Source: admin_cms · cms editor · 8/27/2026

  • how to use

    Verified

    {"steps":[{"en":"Download the desktop installer package for your operating system (.dmg for macOS or .zip for Windows).","zh":"下载对应您操作系统的桌面安装包（如 macOS 的 .dmg 或 Windows 的 .zip）。"},{"en":"Move the app to your applications folder or extract the archive, then configure model access and review policies through the first-run wizard.","zh":"将应用程序移动至系统目录或解压后直接运行，通过首次运行向导配置模型访问和密钥。"}],"installAt":"unknown","difficulty":"easy"}

    Source: admin_cms · cms editor · 8/27/2026

  • intro

    Verified

    {"en":"Ouroboros is an open-source, general-purpose AI agent designed to maintain identity, durable memory, and history across tasks and restarts. It works on external projects while coordinating a live swarm of specialist agents in parallel.\n\nThe runtime operates as a native desktop application or headless CLI, keeping repositories, durable memory, and history locally on your machine while utilizing configured remote APIs or local GGUF models for inference.","zh":"Ouroboros 是一个开源的通用 AI 代理，其设计初衷是让身份、持久记忆和历史在多个任务与重启过程中得以延续。它不仅能在外部项目上工作，还能协调一个活跃的专业子代理集群并行处理任务。\n\n该运行时提供原生桌面应用程序和无头命令行工具，所有仓库、记忆、历史和界面均保存在本地机器上，模型推理则可使用用户配置的远程 API 或本地 GGUF 模型。"}

    Source: admin_cms · cms editor · 8/27/2026

  • Latest release

    Verified

    v6.109.0

    Source: GitHub API · latest_release=v6.109.0 · 8/28/2026

  • License

    Verified

    MIT

    Source: GitHub API · license.spdx_id=MIT · 8/28/2026

  • needs api key

    Verified

    Yes

    Source: admin_cms · cms editor · 8/27/2026

  • One-liner

    Verified

    {"en":"Ouroboros is an open-source, general-purpose AI agent with durable cross-restart memory that coordinates specialist swarms and rewrites its own implementation.","zh":"Ouroboros 是一个开源、通用的自建构 AI 代理，具备跨任务和重启的持久记忆，能够自主协调专业代理集群并重写自身代码与架构。"}

    Source: admin_cms · cms editor · 8/27/2026

  • Platforms

    Verified

    windows, macos, linux

    Source: admin_cms · cms editor · 8/27/2026

  • Category hint

    Inferred from materials

    ai-apps

    Source: Project README · hint=ai-apps · 8/25/2026

  • product forms

    Verified

    desktop, cli

    Source: admin_cms · cms editor · 8/27/2026

  • role tags

    Verified

    fullstack, backend, devops

    Source: admin_cms · cms editor · 8/27/2026

  • supports docker

    Verified

    Yes

    Source: Repository file · dockerfile=true; compose=false · 8/28/2026

  • supports local

    Verified

    Yes

    Source: admin_cms · cms editor · 8/27/2026

  • supports self host

    Verified

    Yes

    Source: admin_cms · cms editor · 8/27/2026

Related projects

Other verified projects matched by category, capabilities, and intended roles.

sutando

An open-source local AI agent that responds via voice and screen by day, and runs an autonomous build loop by night.

Same AI apps categoryBoth support AI coding

ragflow

An open-source RAG engine fusing deep document understanding and agent capabilities to build grounded context layers for LLMs.

Same AI apps categoryBoth support Automation

omnigent

An open-source orchestration layer for running, switching, and collaborating across multiple AI agents through terminal, web, desktop, and cloud-sandbox sessions.

Same AI apps categoryBoth support AI coding

hermes-agent

A personal AI agent that runs locally or on remote infrastructure with terminal, messaging, memory, skills, and scheduled automation.

Same AI apps categoryBoth support AI coding

Box

An advanced, fully offline on-device AI suite for Android supporting chat, image generation, and voice features.

Same AI apps categoryBoth support AI coding

OpenBiliClaw

A local-first, cross-platform AI content discovery agent that builds deep psychological profiles to proactively find content you'll love.

Same AI apps categoryBoth support AI coding