Claude Code in Rust, Python, Go, Open source

Open-source Claude Code alternative — multi-provider AI coding agent CLI. Single file, 13 providers, zero native deps. # npm (recommended) npm install -g cloclo # Or run directly npx cloclo # Or clone and run git clone https://github.com/SeifBenayed/claude-code-sdk.git cd claude-code-sdk && node claude-native.mjs # Login (opens browser, saves token to macOS keychain) cloclo --login # Anthropic (Pro/Max subscription) cloclo --openai-login # OpenAI (ChatGPT Plus/Pro subscription) # Interactive REPL cloclo # Default: Claude Sonnet cloclo -m codex # OpenAI Codex cloclo -m ollama/llama3.2 # Local Ollama # One-shot cloclo -p "explain this code" cloclo -m gpt-5.4 -p "fix the bug in main.js" cat error.log | cloclo -p "explain this error" # Programmatic (NDJSON bridge) echo '{"type":"message","content":"hello"}' | cloclo --ndjson | Provider | Models | Auth | Status | |---|---|---|---| | Anthropic | claude-sonnet-4-6, claude-opus-4-6, claude-haiku-4-5 | ANTHROPIC_API_KEY or --login | Tested | | OpenAI Chat | gpt-5.4, gpt-4.1, gpt-4o, o3, o4-mini | OPENAI_API_KEY or --openai-login | Tested | | OpenAI Responses | gpt-5.3-codex | OPENAI_API_KEY or --openai-login | Tested | | Google Gemini | gemini-2.5-flash, gemini-2.5-pro | GOOGLE_API_KEY | Supported | | DeepSeek | deepseek-chat, deepseek-coder | DEEPSEEK_API_KEY | Supported | | Mistral | mistral-small-latest, codestral-latest | MISTRAL_API_KEY | Supported | | Groq | llama-3.3-70b-versatile, mixtral-8x7b | GROQ_API_KEY | Supported | | Ollama | ollama/* (any pulled model) | None (local) | Supported | | LM Studio | lmstudio/* | None (local) | Supported | | vLLM | vllm/* | None (local) | Supported | | Jan | jan/* | None (local) | Supported | | llama.cpp | llamacpp/* | None (local) | Supported | Switch providers live in the REPL: /model codex , /model sonnet , /model ollama/llama3.2 | Alias | Resolves to | Backend | |---|---|---| sonnet | claude-sonnet-4-6 | Anthropic | opus | claude-opus-4-6 | Anthropic | haiku | claude-haiku-4-5 | Anthropic | codex | gpt-5.3-codex | OpenAI Responses | gpt5 / 5.4 | gpt-5.4 | OpenAI Chat | 4o | gpt-4o | OpenAI Chat | o3 | o3 | OpenAI Chat | o4-mini | o4-mini | OpenAI Chat | - Multi-provider: 13 backends, one CLI. Switch mid-conversation. - Full agent loop: streaming, tool calling, multi-turn, sub-agents with fork mode - Built-in tools: Bash, Read, Write, Edit, Glob, Grep, WebFetch, WebSearch, Agent, MemoryShare - Extended thinking: --thinking 8192 for Claude Sonnet/Opus - MCP integration: --mcp-config servers.json for external tool servers - Permissions: 6 modes from auto tobypassPermissions , with LLM security classifier - Session management: resume, checkpoints, rewind - Memory system: persistent cross-session memory with auto-suggest - Shareable moments: capture and share interesting exchanges ( /share ) as markdown, HTML, SVG - Skills marketplace: browse and install 45+ skills ( /marketplace ) - Skills & hooks: extensible slash commands, 13 lifecycle hooks (command, webhook, prompt, agent) - NDJSON bridge: programmatic use from any language - Ink UI: rich terminal interface with streaming output, markdown rendering, permission dialogs, tool spinners, syntax highlighting, history navigation, and context tracking - Prompt caching: automatic cache_control on system prompt and last user message for 60-70% cost reduction - Security: 2-stage LLM classifier (28 BLOCK rules, 7 ALLOW exceptions, user intent analysis), sandbox support /model [name] Switch model (live backend switching) /thinking [budget] Toggle extended thinking /compact Compress conversation to save context /permissions Change permission mode /memory Show saved memories /share [N] Capture last exchange as shareable moment (md/html/svg) /shares Browse past shared moments /marketplace Browse and install skills from the registry /catalog Browse and install tools from the catalog /checkpoints List file checkpoints /rewind Restore files to a checkpoint /sessions List recent sessions /cost Show session cost /webhook Manage webhook hooks /clear New session /login Login to Anthropic /openai-login Login to OpenAI /exit Quit -p, --print One-shot mode -m, --model Model name or alias --provider Force a specific provider --ndjson NDJSON bridge mode (stdin/stdout) --output Output format: text (default) or json --json Shorthand for --output json --output-version Lock JSON output schema version (default: 1) -y, --yes Skip all permission prompts --timeout Global timeout (exit code 5 if exceeded) --login Anthropic OAuth login --openai-login OpenAI OAuth login --api-key Anthropic API key --openai-api-key OpenAI API key --permission-mode auto|default|plan|acceptEdits|bypassPermissions|dontAsk --max-turns Max agent turns (default: 25) --max-tokens Max output tokens (default: 16384) --thinking Extended thinking token budget --mcp-config MCP servers config file --resume Resume most recent session --session-id Resume specific session --verbose Debug logging | Code | Meaning | |---|---| | 0 | Success |