Claw Code
Pour une evaluation pratique : Claw Code is an open-source AI coding agent framework described as a clean-room Python and Rust rewrite of Claude Code-style agent harness architecture.
300
Claude Code
Pour une evaluation pratique : Claude Code is Anthropic's terminal-native coding agent for reading repositories, editing files, running commands, using MCP tools, and carrying software tasks through a plan-edit-test loop.
2 views0 likes0 uses
Capabilities
- Pour une evaluation pratique : Terminal-native coding workflow that can inspect a real repository, modify files, run commands, and summarize changes.
- Pour une evaluation pratique : Deep MCP support for connecting design docs, issue trackers, custom tools, and internal developer systems.
- Pour une evaluation pratique : Composable CLI style that fits shell workflows, scripts, CI experiments, and local engineering habits.
- Pour une evaluation pratique : Strong fit for large codebase navigation, refactoring, debugging, test repair, and multi-file implementation.
- Pour une evaluation pratique : Works best with explicit permissions, repository-specific instructions, and human review before merge.
- Pour une evaluation pratique : Should be evaluated against Codex, Cursor, Copilot coding agent, Cline, Aider, and OpenHands.
Use Cases
- Scenario d'essai: Pour une evaluation pratique : Ask Claude Code to map a new repository, identify architecture boundaries, and propose a small first task before editing.
- Scenario d'essai: Pour une evaluation pratique : Give it a failing test in a toy repo, let it inspect code, patch files, run the test, and explain the diff.
- Scenario d'essai: Pour une evaluation pratique : Use MCP to connect read-only docs or issue data, then verify whether it uses that context without inventing requirements.
- Scenario d'essai: Pour une evaluation pratique : Trial a dependency upgrade with lockfile changes and require a rollback plan.
- Scenario d'essai: Pour une evaluation pratique : Use it for security review on non-sensitive code, then compare findings with static analysis and human review.
- Scenario d'essai: Pour une evaluation pratique : Measure how often it asks for permission before risky shell commands or broad file changes.
Examples and Source Notes
- Site officiel: https://claude.com/claude-code
- Documentation: https://docs.anthropic.com/en/docs/claude-code/overview
- Controle des risques: Do not give broad filesystem or credential access without a permissions policy, repo instructions, and mandatory review gates.
Related Agents
coding-agent
OpenAI Codex
Pour une evaluation pratique : OpenAI Codex is OpenAI's software-engineering agent family spanning Codex CLI, IDE, desktop, and cloud task workflows for coding, bug fixing, and code review.
200
Google Jules
Pour une evaluation pratique : Google Jules is Google's autonomous coding agent for asynchronous software tasks, running work in cloud virtual machines and returning verified changes.
200