Category
Coding Agents
Tools that take a coding task and try to land a working diff — from one-shot completions to full-repo autonomous engineers.
#1
84
/100
Claude Code
VerifiedAnthropic's terminal-native coding agent. Reads, edits, and runs code across full repositories with explicit user approval for destructive actions.
Coding Agents
Strong
#2
82*
/100
Cursor
ProvisionalAI-first IDE forked from VS Code with inline completions, chat, and an agent mode that executes multi-file edits.
Coding Agents
Strong
#3
78*
/100
Windsurf
ProvisionalAI-first IDE from the team behind Codeium. Cascade agent flow blends inline edits with multi-step actions.
Coding Agents
Useful but limited
#4
76*
/100
Aider
ProvisionalOpen-source command-line coding assistant that pairs with you in your terminal and commits changes via git.
Coding Agents
Useful but limited
#5
75*
/100
OpenAI Codex CLI
ProvisionalOpenAI's open-source terminal coding agent. Runs locally, executes code, and edits files with user approval.
Coding Agents
Useful but limited
#6
74*
/100
Cline
ProvisionalOpen-source VS Code extension that runs an agentic coding loop with your choice of model.
Coding Agents
Useful but limited
#7
73*
/100
GitHub Copilot Coding Agent
ProvisionalGitHub's coding agent that picks up assigned issues and opens PRs from the GitHub UI, in addition to in-IDE Copilot features.
Coding Agents
Useful but limited
#8
71*
/100
Replit Agent
ProvisionalReplit's in-browser agent that scaffolds and ships apps end-to-end inside the Replit workspace.
Coding AgentsNo-Code Agent Builders
Useful but limited
#9
68*
/100
OpenHands
ProvisionalOpen-source coding agent (formerly OpenDevin) from All Hands AI. Runs locally or self-hosted, model-agnostic.
Coding Agents
Risky / inconsistent
#10
67*
/100
Devin
ProvisionalCognition's autonomous AI software engineer. Runs in its own cloud sandbox and aims to complete tickets end-to-end.
Coding Agents
Risky / inconsistent