Source Project
agent-sh/agentsys
AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro.
Alternatives Engine
Compare open-source alternatives to agent-sh/agentsys by fit, deployment, maintenance, quality, and agent readiness.
Decision Summary
Source Project
AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro.
Best For
Not Best For
Comparison Table
Skyvern-AI/skyvern has the strongest combined agent score and maintenance profile in this comparison.
Alternative Match
Same workflow automation intent with workflow overlap.
Fit: Strong replacement candidate with overlapping indexed use cases.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
Alternative Match
Same workflow automation intent with coding_agent, workflow overlap.
Fit: Strong replacement candidate with overlapping indexed use cases.
The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.
Alternative Match
Same workflow automation intent with coding_agent, workflow overlap.
Fit: Strong replacement candidate with overlapping indexed use cases.
Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.
Alternative Match
Same workflow automation intent with coding_agent, workflow overlap.
Fit: Strong replacement candidate with overlapping indexed use cases.
Development workflows for Claude Code that keep broad exploration focused on the outcome you approved.
Alternative Match
Same workflow automation intent with workflow overlap.
Fit: Strong replacement candidate with overlapping indexed use cases.
Automate browser based workflows with AI
Alternative Match
Same workflow automation intent with workflow overlap.
Fit: Strong replacement candidate with overlapping indexed use cases.
An intelligence orchestra
Alternative Match
Same workflow automation intent with workflow overlap.
Fit: Strong replacement candidate with overlapping indexed use cases.
The self-hosted AI workflow automation platform for Git repositories.
Alternative Match
Same workflow automation intent with workflow overlap.
Fit: Strong replacement candidate with overlapping indexed use cases.
An AI agent that applies to jobs for you. It finds openings, tailors your resume, and fills out applications in a real browser on your own machine. Runs on your Claude Code or Codex subscription.
Alternative Match
Same workflow automation intent with coding_agent, workflow overlap.
Fit: Strong replacement candidate with overlapping indexed use cases.
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.
Alternative Match
Same workflow automation intent with coding_agent, workflow overlap.
Fit: Strong replacement candidate with overlapping indexed use cases.
The agent control plane: run Claude Code, Codex and Gemini CLI agents in parallel with a shared task board, schedules and usage-limit recovery. Native iPhone, iPad and Mac apps plus a web dashboard. Self-host (Rust + SQLite, Tailscale remote access) or use amux Cloud. MIT + Commons Clause.
Alternative Match
Same workflow automation intent with coding_agent, workflow overlap.
Fit: Strong replacement candidate with overlapping indexed use cases.
Agent Skills marketplace: framework-aware skills for code review, documentation, test-plan generation, AI-writing detection, architectural analysis, and git workflows — for Python, Go, Rust, Elixir, React, Remix, and iOS/Swift. Works with Claude Code, Codex, and any agent that supports Agent Skills.
Alternative Match
Same workflow automation intent with coding_agent, workflow overlap.
Fit: Strong replacement candidate with overlapping indexed use cases.
oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an adversarial review loop: a second agent that never sees the first one's reasoning. MIT.
Data Source
1226 loaded projects. Generated at 2026-11-11T03:05:13.980Z.