GitHub

The dominant code hosting and collaboration platform. Agents interact via CLI, API, or MCP integrations. Key for issue tracking, PRs, and CI/CD.

Skills

Categories

Native agent support

GitHub has strong API and CLI support. Copilot is the native AI layer but is focused on IDE completion rather than autonomous agent workflows.

Skills on this platform

OpenHands

active

Category leader. No other tool has the combination of open-source community (69K stars, 455 contributors), real download volume (1M/month), venture backing ($18.8M), hardware partnerships (AMD), and benchmark leadership (SWE-bench Verified 72%). Gap to #2 is enormous.

Community · OpenHands/OpenHands

SWE-agent

stale

Research/academic reference only. Princeton pedigree and 79.2% SWE-bench Verified on Opus 4.5 scaffold give it strong benchmark credibility. But no release in 10 months (last: v1.1.0, 2025-05-22) puts it outside the production cadence of all active tools. Use as a benchmark scaffold reference, not as a production coding CLI.

Community · SWE-agent/SWE-agent

Claude Code

active

The #1 coding CLI agent. Leads SWE-bench Pro standardized (45.89%), wins independent head-to-heads on reasoning depth, ~4% of GitHub commits. Rate limits are the #1 complaint. Costs 2-3x more per task than Codex CLI due to higher token consumption.

Official · anthropics/claude-code

See how these skills rank.

Category-level rankings with evidence and head-to-head comparisons.

VIEW CATEGORIES →

Related categories

Coding CLIs / Code Agents

The hottest category right now. Ten+ serious CLI agents competing across three tiers. SWE-bench Pro (standardized) is necessary but no longer sufficient — METR found ~50% of SWE-bench-passing PRs would NOT be merged by real maintainers. Rankings weight benchmarks alongside practical tests, adoption, safety, and independent evaluations.

Teams of Agents / Multi-Agent Orchestration

Four distinct buyer segments with almost no cross-over: (1) Agent frameworks/SDKs — build multi-agent systems in code (LangGraph, CrewAI, OpenAI Agents SDK, Mastra); (2) Autonomous coding agents — delegate software development to an agent (OpenHands, Factory AI); (3) Parallel agent IDEs — run multiple coding agents simultaneously and compare results (Emdash, Superset); (4) Workflow automation with agents — orchestrate integrations visually (n8n). Ranking all on a single list is misleading — each serves a different buyer.