AgentSys
A modular runtime and orchestration system for AI agents that automates software development workflows from task discovery to deployment.
What is AgentSys?
AgentSys is a modular runtime and orchestration system designed to automate the entire software development lifecycle using specialized AI agents. It handles tasks beyond code generation—such as task selection, branch management, code review, artifact cleanup, CI, PR comments, and deployment—through structured, phase-gated pipelines with persistent state that survives session interruptions.
Developers and teams using AI coding assistants (like Claude Code, OpenCode, Codex CLI, Cursor, or Kiro) who want to automate and orchestrate the complete development workflow, from task discovery to deployment, with minimal manual oversight.
Developers choose AgentSys for its comprehensive, automated pipeline that enforces quality gates and reduces token usage by up to 77% through deterministic tools for detection and single LLM calls for judgment. Its modular architecture with 47 specialized agents and persistent state allows for reliable, multi-session automation without babysitting.
Overview
AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro.
Use Cases
Best For
- Automating the complete task-to-production workflow, including discovery, implementation, review, and merging via the `/next-task` command.
- Enforcing pre-ship quality gates with automated code review, deslopping, test validation, and documentation sync using `/prepare-delivery` or `/gate-and-ship`.
- Linting and validating AI agent configurations (like SKILL.md or CLAUDE.md) across multiple platforms with the integrated `/agnix` command to prevent silent failures.
- Performing structured, evidence-backed performance investigations with baselines, profiling, and hypothesis testing using the `/perf` command.
- Detecting drift between documentation/plans and actual code implementation efficiently with the token-optimized `/drift-detect` command.
- Orchestrating multi-agent, iterative code reviews with role-based specialists (security, performance, architecture) via `/audit-project`.
Not Ideal For
- Projects exclusively using GitHub Copilot or other AI assistants not natively supported by AgentSys's core runtime (e.g., without Claude Code, OpenCode, Codex CLI, Cursor, or Kiro).
- Small teams or solo developers working on simple, short-lived projects where the overhead of setting up and maintaining 47 specialized agents isn't justified.
- Environments with strict compliance or audit requirements that necessitate manual approval at every step, as AgentSys automates many phases including code review and merging.
- Teams with limited resources or infrastructure, as it requires Node.js 18+, Git, and additional CLIs like agnix and agent-analyzer for full functionality.
Pros & Cons
Pros
With 19 plugins, 47 agents, and 40 skills, AgentSys allows teams to build customized pipelines for software development, enabling standalone use of commands like `/deslop` or integrated workflows via `/next-task`.
By using deterministic tools like regex and AST analysis for detection and single LLM calls for judgment, AgentSys reduces token usage by up to 77%, as demonstrated in the `/drift-detect` benchmark.
It runs on Claude Code, OpenCode, Codex CLI, Cursor, and Kiro with consistent behavior, and tools like `/agnix` extend support to more AI assistants, ensuring broad usability.
Commands like `/prepare-delivery` enforce pre-ship checks including deslopping, multi-agent review, and documentation sync, preventing skipped steps and ensuring code quality.
Cons
Installation requires Node.js 18+, Git, and additional CLIs like agnix and agent-analyzer, with platform-specific configurations for AI tools, which can be a barrier to entry and maintenance.
The system is optimized for Claude models (Opus, Sonnet, Haiku) with specific model assignments, and while it supports other platforms, core functionality and token savings are tied to this ecosystem, limiting flexibility.
Understanding the architecture of 47 specialized agents, 40 skills, and how commands compose requires significant time investment, as highlighted in the design philosophy section about research-backed prompt engineering.
Frequently Asked Questions
Related Projects
SuperpowersAn agentic skills framework & software development methodology that works.
Everything Claude CodeThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Learn Claude CodeBash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Claude Scientific SkillsTurn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.