HN 표시: 모든 LLM을 위한 OpenHarness 오픈 소스 터미널 코딩 에이전트

___ / \ ( ) ___ ___ ___ _ _ _ _ _ ___ _ _ ___ ___ ___ `~w~` / _ \| _ \| __| \| | || | /_\ | _ \ \| | __/ __/ __| (( )) | (_) | _/| _|| .` | __ |/ _ \| / .` | _|\__ \__ \ ))(( \___/|_| |___|_|\_|_||_/_/ \_\_|_\_|\_|___|___/___/ (( )) `--` AI coding agent in your terminal. Works with any LLM -- free local models or cloud APIs. openharnessv0.1.1-2.mp4 OpenHarness reading files, running commands, and editing code — powered by a local Ollama model. npm install -g @zhijiewang/openharness oh That's it. OpenHarness auto-detects Ollama and starts chatting. No API key needed. oh # auto-detect local model oh --model ollama/qwen2.5:7b # specific model oh --model gpt-4o # cloud model (needs OPENAI_API_KEY) oh --trust # auto-approve all tool calls oh run "fix the tests" --json # headless mode for CI/CD Most AI coding agents are locked to one provider or cost $20+/month. OpenHarness works with any LLM -- run it free with Ollama on your own machine, or connect to any cloud API. Every AI edit is git-committed and reversible with /undo . | OpenHarness | Claude Code | Aider | OpenCode | | |---|---|---|---|---| | Any LLM | Yes (Ollama, OpenAI, Anthropic, OpenRouter, any OpenAI-compatible) | Anthropic only | Yes | Yes | | Free local models | Ollama native | No | Yes | Yes | | Tools | 17 with permission gates | 40+ | File-focused | 20+ | | Git integration | Auto-commit + /undo | Yes | Deep git | Basic | | Slash commands | 16 built-in | 80+ | Some | Some | | Headless/CI mode | oh run --json | Yes | Yes | Yes | | Terminal UI | React + Ink | React + Ink | Basic | BubbleTea | | Language | TypeScript | TypeScript | Python | Go | | License | MIT | Proprietary | Apache 2.0 | MIT | | Price | Free (BYOK) | $20+/month | Free (BYOK) | Free (BYOK) | | Tool | Risk | Description | |---|---|---| | Bash | high | Execute shell commands with timeout | | Read | low | Read files with line ranges | | Write | medium | Create or overwrite files | | Edit | medium | Search-and-replace edits | | Glob | low | Find files by pattern | | Grep | low | Regex content search | | WebFetch | medium | Fetch URL content (SSRF-protected) | | WebSearch | medium | Search the web | | TaskCreate | low | Create structured tasks | | TaskUpdate | low | Update task status | | TaskList | low | List all tasks | | AskUser | low | Ask user a question with options | | Skill | low | Invoke a skill from .oh/skills/ | | Agent | medium | Spawn a sub-agent for delegation | | EnterPlanMode | low | Enter structured planning mode | | ExitPlanMode | low | Exit planning mode | | NotebookEdit | medium | Edit Jupyter notebooks | Low-risk read-only tools auto-approve. Medium and high risk tools require confirmation in ask mode. Use --trust to skip all prompts. Type these during a chat session: | Command | Description | |---|---| /help | Show all available commands | /clear | Clear conversation history | /cost | Show session cost and token usage | /status | Show model, mode, git branch, session info | /diff | Show uncommitted git changes | /undo | Undo last AI commit | /commit [msg] | Create a git commit | /log | Show recent git commits | /files | List files in context | /model | Switch model mid-session | /compact | Compress conversation to free context | /export | Export conversation to markdown | /plan | Enter plan mode | /review | Review recent code changes | /config | Show configuration | /memory | View memories | OpenHarness auto-commits AI edits in git repos: oh: Edit src/app.ts # auto-committed with "oh:" prefix oh: Write tests/app.test.ts - Every AI file change is committed automatically /undo reverts the last AI commit (only OH commits, never yours)/diff shows what changed- Your dirty files are safe — committed separately before AI edits Run a single prompt without interactive UI — perfect for CI/CD: oh run "fix the failing tests" --model ollama/llama3 --trust oh run "add error handling to api.ts" --json # JSON output oh run "explain this codebase" --model gpt-4o Exit code 0 on success, 1 on failure. # Local (free, no API key needed) oh --model ollama/llama3 oh --model ollama/qwen2.5:7b-instruct # Cloud OPENAI_API_KEY=sk-... oh --model gpt-4o ANTHROPIC_API_KEY=sk-ant-... oh --model claude-sonnet-4-6 OPENROUTER_API_KEY=sk-or-... oh --model openrouter/deepseek-chat # Any OpenAI-compatible endpoint oh --model deepseek/deepseek-chat Create .oh/RULES.md in any repo (or run oh init ): - Always run tests after changes - Use strict TypeScript - Never commit to main directly Rules load automatically into every session. Requires Node.js 18+. # From npm npm install -g @zhijiewang/openharness # From source git clone https://github.com/zhijiewong/openharness.git cd openharness npm install && npm install -g . npm install npx tsx src/main.tsx # run in dev mode npx tsc --noEmit # type check npm test # run tests Create src/tools/YourTool/index.ts implementing the Tool interface with a Zod input schema, register it in src/tools.ts . Create src/providers/yourprovider.ts implementing the Provider interf