Guides
Answers to the questions people ask before and after installing a coding agent: running one offline, what it costs, MCP with any model, CI, permissions — and how OHarness compares.
Run an AI coding agent fully offline with Ollama or LM Studio
Point OHarness at Ollama or LM Studio and the whole agent loop runs on your machine: no key, no per-token bill, no code leaving the laptop.
The cheapest way to run a Claude Code-style coding agent
What an agent session actually costs on DeepSeek, GLM, Kimi, Gemini, GPT and Claude — and the free option. One harness, any model, list prices compared.
Use MCP servers with GPT, Gemini, DeepSeek or a local model
MCP is a harness feature, not a model feature. Configure a server once in OHarness and every model — GPT, Gemini, DeepSeek, Ollama — can call its tools.
Switch models mid-session without losing context
Move a coding session from Claude to GPT to DeepSeek to a local model with one command. Why most tools restart or convert history, and why OHarness does neither.
Run an AI coding agent headless in CI
oharness-headless runs the agent with no UI and writes JSONL to stdout. Permissions that would prompt are denied, so an unattended run is never less safe than an attended one.
Coding agent permissions: modes, allow and deny rules
An agent runs with your authority. How OHarness decides what runs without asking: five modes, allow/ask/deny rules, where they are stored, and why deny beats bypass.
Use DeepSeek V4 in a coding agent
Run DeepSeek V4 Flash or V4 Pro as a Claude Code-style agent: 1M context, tool calling, from $0.15 per million input tokens. Setup, model ids and prices.
Comparisons
One tool at a time, checked against each project’s own documentation, with where it is stronger stated first. The overview of what to check before switching is Claude Code alternatives.
Codex alternatives: keep GPT, add every other model
Looking for an OpenAI Codex alternative? What to check, the options, and how to keep your ChatGPT plan while adding Claude, Gemini, DeepSeek and local models.
Claude Cowork alternatives: an agent desktop that runs any model
Looking for a Claude Cowork alternative? What Cowork does, what to check, the options — and where OHarness's desktop agent fits, with any model and your own key.
OHarness vs OpenCode
Choose OpenCode if you want a mature, fully open source terminal agent with the widest set of subscription logins. Choose OHarness if switching models mid-session without converting history, or one engine behind terminal, browser and desktop, matters more.
OHarness vs OpenAI Codex CLI
Choose Codex CLI if you mostly use OpenAI models, want an OS-level sandbox with the network off by default, or want usage included in a ChatGPT plan. Choose OHarness if you want Anthropic, Gemini, DeepSeek and Chat Completions endpoints first-class in the same session.
OHarness vs Aider
Choose Aider if you want pair programming built around git — automatic commits, `/undo`, a repository map — with a light footprint. Choose OHarness if you need an agent with MCP tools, subagents, permission rules and a browser or desktop UI.
OHarness vs Cline
Choose Cline if you want the agent inside VS Code or JetBrains with Plan/Act modes and checkpoints. Choose OHarness if you work from the terminal or browser, switch vendors mid-task, and want deny rules that hold in every mode.
OHarness vs Gemini CLI
Choose Gemini CLI if you work on Gemini and want its free tier — 1,000 requests a day with a Google account — and built-in sandboxing. Choose OHarness if you need Claude, GPT, DeepSeek or local models alongside Gemini in one session.