anus-dev/ANUS

A free coding agent in your terminal. It runs on the smartest free model that is up today.

View on GitHub ↗Jump to charts ↓Open shareable report →

anus-dev/ANUS has 6.5k+ stars and 900+ forks on GitHub, is written in JavaScript, and was last pushed on Oct 1, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 2 hours ago
Added to GitGenius on September 24th, 2026
Created on March 9th, 2025
Open Issues & Pull Requests: 73 (+0)
GitHub issues: Enabled
Number of forks: 929
Total Stargazers: 6,549 (+0)
Total Subscribers: 82 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 3.4 hours
Mean response time: 19.1 days
90th percentile: 101.3 days
Tracked items: 49

How this project is maintained

99% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Three people close 64% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 68
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 524 days
Stale 30+ days: 64
Stale 90+ days: 64

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

ANUS is an AI agent that contributes to its own development through autonomous code generation and repository maintenance.

The tool addresses the challenge of automating software development by creating an AI agent capable of analyzing its own codebase, proposing improvements, and implementing features with minimal human oversight. It operates as a Grok-powered command-line agent that uses the Model Context Protocol for extensibility, integrating file system operations and sandboxed shell execution. The project is distinguished by its entirely AI-generated codebase and its explicit goal of achieving autonomous repository maintenance where the agent itself becomes a core contributor to its own evolution.

Developers considering adoption should understand that this is fundamentally an experiment in AI-driven software creation rather than a conventional tool. It suits teams interested in exploring autonomous development workflows, AI-generated code practices, and the feasibility of self-maintaining systems. The project requires Node.js and uses OpenRouter.ai for API access. The contribution philosophy is distinctive: the project enforces a requirement that at least eighty percent of submitted code must be AI-generated, reflecting its commitment to exploring AI-first development practices.

The project maintains active community engagement through Telegram discussion channels. Development activity shows ongoing evolution of the codebase with continued refinement of the agent's capabilities across its stated phases, from foundational agent construction through meta-cognitive analysis toward full autonomous repository maintenance.