The amux control plane coordinates AI coding agents across shared boards, atomic tasks, schedules, and model switching.
Ouroboros
The Ouroboros project describes a self-creating AI agent created in 2026.
About Ouroboros
Ouroboros is an open-source, general-purpose AI agent that retains identity, durable memory and history across tasks and restarts. It works on external projects, coordinates specialist agents, and can rewrite its own code, architecture, prompts, tools and dependencies.
It runs as a native desktop app or headless CLI with its repository, memory, history and interface kept on the local machine. Model inference uses a configured remote API or a local GGUF model, and running tasks requires a Codex account, provider key, or local model.
Key features
- Retains identity, memory and history across restarts
- Works on external projects
- Coordinates a live swarm of specialist agents
- Rewrites its own code, prompts, tools and dependencies
- Runs as desktop app or headless CLI
- Uses configured remote APIs or local GGUF model
Best for: Technical users who want to run an open-source agent locally on their own projects.
Good for
- Open-source with repository, memory, history and interface kept on the local machine
- Sends no telemetry by default with no official usage or crash-report collection
- Ships native packages for macOS, Windows and multiple Linux distributions with optional CLI
Watch out for
- Requires a Codex account, remote provider API key, or local GGUF model to run tasks
- Claude Code and Cursor subscriptions cannot be used as Main model sources
- Android build is experimental and requires Magisk-rooted ARM64 plus Python and adb for USB setup
Ouroboros at a glance
- Website
- github.com/razzant/ouroboros
- Category
- AI & Machine Learning › AI Agents & Automation
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
Ouroboros alternatives
Tools and sites you could use instead, ranked by how closely they match.
Local Deep Research searches sources such as arXiv, PubMed, and private documents with local or cloud LLMs.
Open source
24 alternatives
The agent-qa repository describes a self improving test agent for web and mobile software teams.
Hermes Agent runs as an open-source, self-hosted AI agent with memory, skills, and messaging integrations.
Open source
24 alternatives
Agent Teams AI coordinates agents that work on tasks, message each other, and review work through a kanban board.
Open source
24 alternatives
Tura builds an AI agent that aims to reduce token use while completing tasks.
Open source
24 alternativesPopular in AI Agents & Automation
Well-known listings from the same topic.
Simsim.aiMaya AI.smartmaya.aiMakeformsmakeforms.ioAgent Skillsagentskills.ioGenFuse AIgenfuseai.comBeambeam.ai
Ouroboros FAQ
What is needed to run tasks?
Choose a connected Codex account as the Main model source, configure a supported remote provider API key, or use a local GGUF model.
Can Claude Code or Cursor subscriptions be the main model?
No. They can run delegated coding and review, but they are not Main model sources.
Does Ouroboros send telemetry?
It sends no telemetry by default and the project operates no usage or crash-report collection. Local history stays on the machine, while requests through OpenRouter carry the app name for public statistics.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.