{"id":34645224,"url":"https://github.com/autohandai/code-cli","last_synced_at":"2026-02-27T09:55:55.133Z","repository":{"id":329104406,"uuid":"1114841676","full_name":"autohandai/code-cli","owner":"autohandai","description":"Autohand Code CLI - Ultra fast coding agent that runs in your terminal","archived":false,"fork":false,"pushed_at":"2026-02-16T02:34:58.000Z","size":23957,"stargazers_count":66,"open_issues_count":0,"forks_count":9,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-02-16T08:36:18.399Z","etag":null,"topics":["agentic-ai","ai","ai-agents-cli","autonomous-agents","code-cli","code-generation","llms"],"latest_commit_sha":null,"homepage":"https://www.autohand.ai/cli/","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/autohandai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-12-12T01:01:40.000Z","updated_at":"2026-02-16T02:32:14.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/autohandai/code-cli","commit_stats":null,"previous_names":["autohandai/code-cli"],"tags_count":55,"template":false,"template_full_name":null,"purl":"pkg:github/autohandai/code-cli","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autohandai%2Fcode-cli","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autohandai%2Fcode-cli/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autohandai%2Fcode-cli/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autohandai%2Fcode-cli/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/autohandai","download_url":"https://codeload.github.com/autohandai/code-cli/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/autohandai%2Fcode-cli/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29890638,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-27T09:48:51.284Z","status":"ssl_error","status_checked_at":"2026-02-27T09:48:43.992Z","response_time":57,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agentic-ai","ai","ai-agents-cli","autonomous-agents","code-cli","code-generation","llms"],"created_at":"2025-12-24T17:39:47.613Z","updated_at":"2026-02-27T09:55:55.087Z","avatar_url":"https://github.com/autohandai.png","language":"TypeScript","funding_links":[],"categories":["Tools and Code","Applications","Learning","CLI Tools"],"sub_categories":["Vibe Coding and AI Coding Assistants","Autonomous Agent Task Solver Projects","Repositories"],"readme":"# Autohand Code CLI\n\n[![Bun](https://img.shields.io/badge/Bun-%23c61f33?style=flat\u0026logo=bun\u0026logoColor=white)](https://bun.sh)\n[![Discord](https://img.shields.io/badge/Discord-Join%20Us-%235865F2?style=flat\u0026logo=discord\u0026logoColor=white)](https://discord.com/invite/MWTNudaj8E)\n\n**An coding agentic CLI that reads, reasons, and writes code across your entire project. No context switching. No copy-paste, No you're absolute right!.**\n\nAutohand Code CLI is an autonomous LLM-powered coding agent that lives in your terminal. It uses the ReAct (Reason + Act) pattern to understand your codebase, plan changes, and execute them with your approval. It's blazing fast, intuitive, and extensible with a modular skill system.\n\nWe built with a very minimalistic design philosophy to keep the focus on coding. Just install, run `autohand`, and start giving instructions in natural language. Autohand handles the rest.\n\nScale Autohand across your team and CI/CD pipelines to automate repetitive coding tasks, enforce code quality, and accelerate development velocity.\n\n![Alt Autohand in the terminal](docs/gif/autohand-intro.gif)\n\n## Installation\n\n### Quick Install (Recommended)\n\n```bash\ncurl -fsSL https://autohand.ai/install.sh | bash\n```\n\n### Manual Installation\n\n```bash\n# Clone and build\ngit clone https://github.com/autohandai/cli.git\ncd cli\nbun install\nbun run build\n\n# Install globally\nbun add -g .\n```\n\n### Requirements\n\n- Bun ≥1.0 (`curl -fsSL https://bun.sh/install | bash`)\n- Git (for version control features)\n- ripgrep (optional, for faster search)\n\n## Quick Start\n\n```bash\n# Interactive mode - start a coding session\nautohand\n\n# Command mode - run a single instruction\nautohand -p \"add a dark mode toggle to the settings page\"\n\n# With auto-confirmation\nautohand -p \"fix the TypeScript errors\" -y\n\n# Auto-commit changes after task completion\nautohand -p \"refactor the auth module\" -c\n```\n\n## Editor Extensions\n\nUse Autohand directly in your favorite editor:\n\n### VS Code\n\nInstall the extension from the [VS Code Marketplace](https://marketplace.visualstudio.com/items?itemName=AutohandAI.vscode-autohand) or via command line:\n\n```bash\ncode --install-extension AutohandAI.vscode-autohand\n```\n\n### Zed Editor\n\nInstall from the [Zed Extensions](https://zed.dev/extensions/autohand-acp) marketplace.\n\n## Usage Modes\n\n### Interactive Mode\n\nLaunch without arguments for a full REPL experience:\n\n```bash\nautohand\n```\n\nFeatures:\n\n- Type `/` for slash command suggestions\n- Type `@` for file autocomplete (e.g., `@src/index.ts`)\n- Type `!` to run terminal commands (e.g., `! git status`, `! ls -la`)\n- **Smart Paste**: Paste any amount of code (5+ lines shows compact indicator, full content sent to LLM)\n- Press `ESC` to cancel in-flight requests\n- Press `Ctrl+C` twice to exit\n\n### Command Mode (Non-Interactive)\n\nRun single instructions for CI/CD, scripts, or quick tasks:\n\n```bash\n# Basic usage\nautohand --prompt \"add tests for the user service\"\n\n# Short form\nautohand -p \"fix linting errors\"\n\n# With options\nautohand -p \"update dependencies\" --yes --auto-commit\n\n# Dry run (preview changes without applying)\nautohand -p \"refactor database queries\" --dry-run\n```\n\n### CLI Options\n\n| Option                  | Short | Description                                     |\n| ----------------------- | ----- | ----------------------------------------------- |\n| `--prompt \u003ctext\u003e`       | `-p`  | Run a single instruction in command mode        |\n| `--yes`                 | `-y`  | Auto-confirm risky actions                      |\n| `--auto-commit`         | `-c`  | Auto-commit changes after completing tasks      |\n| `--dry-run`             |       | Preview actions without applying mutations      |\n| `--model \u003cmodel\u003e`       |       | Override the configured LLM model               |\n| `--path \u003cpath\u003e`         |       | Workspace path to operate in                    |\n| `--auto-skill`          |       | Auto-generate skills based on project analysis  |\n| `--unrestricted`        |       | Run without approval prompts (use with caution) |\n| `--restricted`          |       | Deny all dangerous operations automatically     |\n| `--config \u003cpath\u003e`       |       | Path to config file                             |\n| `--temperature \u003cvalue\u003e` |       | Sampling temperature for LLM                    |\n| `--login`               |       | Sign in to your Autohand account                |\n| `--logout`              |       | Sign out of your Autohand account               |\n\n## Agent Skills\n\nSkills are modular instruction packages that extend Autohand with specialized workflows. They work like on-demand `AGENTS.md` files for specific tasks.\n\n### Using Skills\n\n```bash\n# List available skills\n/skills\n\n# Activate a skill\n/skills use changelog-generator\n\n# Create a new skill interactively\n/skills new\n\n# Auto-generate project-specific skills\nautohand --auto-skill\n```\n\n### Auto-Skill Generation\n\nAnalyze your project and generate tailored skills automatically:\n\n```bash\n$ autohand --auto-skill\nAnalyzing project structure...\nDetected: typescript, react, nextjs, testing\nPlatform: darwin\nGenerating skills...\n  ✓ nextjs-component-creator\n  ✓ typescript-test-generator\n  ✓ changelog-generator\n\n✓ Generated 3 skills in .autohand/skills\n```\n\nSkills are discovered from:\n\n- `~/.autohand/skills/` - User-level skills\n- `\u003cproject\u003e/.autohand/skills/` - Project-level skills\n- Compatible with Codex and Claude skill formats\n\nSee [Agent Skills Documentation](docs/agent-skills.md) for creating custom skills.\n\n## Slash Commands\n\n| Command        | Description                          |\n| -------------- | ------------------------------------ |\n| `/help`        | Display available commands           |\n| `/quit`        | Exit the session                     |\n| `/model`       | Switch LLM models                    |\n| `/new`         | Start fresh conversation             |\n| `/undo`        | Revert last changes                  |\n| `/session`     | Show current session details         |\n| `/sessions`    | List past sessions                   |\n| `/resume`      | Resume a previous session            |\n| `/memory`      | View/manage stored memories          |\n| `/init`        | Create `AGENTS.md` file              |\n| `/agents`      | List sub-agents                      |\n| `/agents-new`  | Create new agent via wizard          |\n| `/skills`      | List and manage skills               |\n| `/skills new`  | Create a new skill                   |\n| `/feedback`    | Send feedback                        |\n| `/formatters`  | List code formatters                 |\n| `/lint`        | List code linters                    |\n| `/completion`  | Generate shell completion scripts    |\n| `/export`      | Export session to markdown/JSON/HTML |\n| `/status`      | Show workspace status                |\n| `/login`       | Authenticate with Autohand API       |\n| `/logout`      | Sign out                             |\n| `/permissions` | Manage tool permissions              |\n\n## Tool System\n\nAutohand includes 40+ tools for autonomous coding:\n\n### File Operations\n\n`read_file`, `write_file`, `append_file`, `apply_patch`, `search`, `search_replace`, `semantic_search`, `list_tree`, `create_directory`, `delete_path`, `rename_path`, `copy_path`, `multi_file_edit`\n\n### Git Operations\n\n`git_status`, `git_diff`, `git_commit`, `git_add`, `git_branch`, `git_switch`, `git_merge`, `git_rebase`, `git_cherry_pick`, `git_stash`, `git_fetch`, `git_pull`, `git_push`, `auto_commit`\n\n### Commands \u0026 Dependencies\n\n`run_command`, `custom_command`, `add_dependency`, `remove_dependency`\n\n### Planning \u0026 Memory\n\n`plan`, `todo_write`, `save_memory`, `recall_memory`\n\n## Configuration\n\nCreate `~/.autohand/config.json`:\n\n```json\n{\n  \"provider\": \"openrouter\",\n  \"openrouter\": {\n    \"apiKey\": \"sk-or-...\",\n    \"model\": \"anthropic/claude-sonnet-4-20250514\"\n  },\n  \"workspace\": {\n    \"defaultRoot\": \".\",\n    \"allowDangerousOps\": false\n  },\n  \"ui\": {\n    \"theme\": \"dark\",\n    \"autoConfirm\": false\n  }\n}\n```\n\n### Supported Providers\n\n| Provider   | Config Key   | Notes                               |\n| ---------- | ------------ | ----------------------------------- |\n| OpenRouter | `openrouter` | Access to Claude, GPT-4, Grok, etc. |\n| Anthropic  | `anthropic`  | Direct Claude API access            |\n| OpenAI     | `openai`     | GPT-4 and other models              |\n| Ollama     | `ollama`     | Local models                        |\n| llama.cpp  | `llamacpp`   | Local inference                     |\n| MLX        | `mlx`        | Apple Silicon optimized             |\n\n## Session Management\n\nSessions are auto-saved to `~/.autohand/sessions/`:\n\n```bash\n# Resume via command\nautohand resume \u003csession-id\u003e\n\n# Or in interactive mode\n/resume\n```\n\n## Security \u0026 Permissions\n\nAutohand includes a permission system for sensitive operations:\n\n- **Interactive** (default): Prompts for confirmation on risky actions\n- **Unrestricted** (`--unrestricted`): No approval prompts\n- **Restricted** (`--restricted`): Denies all dangerous operations\n\nConfigure granular permissions in `~/.autohand/config.json`:\n\n```json\n{\n  \"permissions\": {\n    \"whitelist\": [\"run_command:npm *\", \"run_command:bun *\"],\n    \"blacklist\": [\"run_command:rm -rf *\", \"run_command:sudo *\"]\n  }\n}\n```\n\n## Platform Support\n\n- macOS\n- Linux\n- Windows\n\n## Telemetry \u0026 Feedback\n\nTelemetry is disabled by default. Opt-in to help improve Autohand:\n\n```json\n{\n  \"telemetry\": {\n    \"enabled\": true\n  }\n}\n```\n\nWhen enabled, Autohand collects anonymous usage data (no PII, no code content). See [Telemetry Documentation](docs/telemetry.md) for details.\n\nThe backend API is available at: https://github.com/autohandai/api\n\n## Development\n\n```bash\n# Install dependencies\nbun install\n\n# Development mode\nbun run dev\n\n# Build\nbun run build\n\n# Type check\nbun run typecheck\n\n# Run tests\nbun test\n```\n\n## Docker\n\n```dockerfile\nFROM oven/bun:1\nWORKDIR /app\nCOPY . .\nRUN bun install \u0026\u0026 bun run build\nCMD [\"./dist/cli.js\"]\n```\n\n```bash\ndocker build -t autohand .\ndocker run -it autohand\n```\n\n## Documentation\n\n- [Playbook](AUTOHAND_PLAYBOOK.md) - 20 use cases for the software development lifecycle\n- [Features](docs/features.md) - Complete feature list\n- [Agent Skills](docs/agent-skills.md) - Skills system guide\n- [Configuration Reference](docs/config-reference.md) - All config options\n\n## License\n\nApache License 2.0 - Free for individuals, non-profits, educational institutions, open source projects, and companies with ARR under $5M. See [LICENSE](LICENSE) and [COMMERCIAL.md](COMMERCIAL.md) for details.\n\n## Links\n\n- Website: https://autohand.ai\n- CLI Install: https://autohand.ai/cli/\n- GitHub: https://github.com/autohandai/cli\n- API Backend: https://github.com/autohandai/api\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fautohandai%2Fcode-cli","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fautohandai%2Fcode-cli","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fautohandai%2Fcode-cli/lists"}