Ross ROSS = Recommend OSS · open-source software intelligence for agents

razzant/ouroboros

Ouroboros — self-creating AI agent. Born Feb 16, 2026. observed · 2026-09-03

github.com/razzant/ouroboros · homepage · Python · MIT (permissive) observed · 2026-09-03

Health v2 · maintenance only

79/100

  • Activity 100
  • Release rhythm 88
  • Longevity 14
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 0.0
  • age_days: 203
  • days_rel: 1
  • days_push: 0
  • n_releases_24m: 93

Full methodology

Adoption not part of the score

1258 stars · 613 forks observed · 2026-09-03

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Ouroboros is an open-source, general-purpose AI agent with persistent identity, durable memory, and the ability to rewrite its own implementation (code, prompts, tools, and dependencies). It runs as a native desktop app or headless CLI, coordinates a swarm of specialist agents, and supports remote LLM APIs or local GGUF models.

Use cases

  • run an autonomous AI agent that works on coding projects end to end
  • self-host an AI agent with persistent memory across tasks and restarts
  • coordinate a swarm of specialist AI agents on one task
  • use a local GGUF model for offline agent inference
  • let an AI agent control the desktop and use the computer
  • give an AI agent MCP tools and external workspaces
  • run a coding agent that can test and verify its own changes

When to choose

  • you want a self-hosted, MIT-licensed general-purpose agent with durable memory and identity
  • you need multi-agent coordination with verification and review evidence
  • you want to run inference locally with GGUF models or your own API keys
  • you need both a desktop app and a headless CLI for automation
  • you want an agent that can inspect, build, and verify external projects in isolated workspaces

When to avoid

  • you only need a simple chatbot or single-shot LLM wrapper
  • you require a cloud-managed agent service with no local runtime
  • you are uncomfortable with software that can modify its own implementation
  • you need a lightweight library to embed agent logic in your own codebase
  • you need mobile or browser-based agent execution

Facets

application · maturity active

agent-framework llm-inference mcp developer-tools cli gui chat-interface artificial-intelligence large-language-models developer-tools self-hosted windows cli python self-hosted autonomous-agent self-modifying-ai multi-agent-swarm persistent-memory computer-use local-llm gguf coding-agent desktop-agent agentic-ai ai-agents automation macos linux desktop

4 sources

Member repositories

RepositoryRoleHealth v2
razzant/ouroborosmain79

For agents

markdown · JSON · MCP: product_card(name="razzant/ouroboros")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem