# CLI Tools Overview & Comparison URL: https://research-memex.org/docs/implementation/ai-environment-setup/cli-setup-guide Description: The right agentic CLI depends on the research task, model access, and tolerance for setup complexity. *The best CLI agent is not the most powerful one, but the one that fits your research workflow.* ## Overview [#overview] The Research Memex workflow works with both GUI and CLI tools. GUI tools suit early exploration and teaching; CLI tools suit file-based, repeatable, auditable work. Most researchers should start with one of each: Cherry Studio for model comparison and knowledge bases, plus a CLI agent for project files, scripts, and long-running workflows. ## Current CLI options [#current-cli-options] ### Cherry Studio [#cherry-studio] * Visual multi-model workspace * Good first interface for API keys, knowledge bases, and MCP servers * Useful for teaching, comparison, and non-terminal researchers * Full guide: [Cherry Studio Setup](/docs/implementation/agentic-ai-tools/cherry-studio-setup-guide) ### Claude Code [#claude-code] * Anthropic's terminal agent * Strong fit for deep project work, code, and research-writing infrastructure * Best when you want Claude as the main workspace model * Full guide: [Claude Code Setup](/docs/implementation/agentic-ai-tools/claude-code-setup-guide) ### Antigravity CLI [#antigravity-cli] * Google's current terminal-agent path for consumer and free Gemini CLI users * Good fit for Google-account workflows, SSH use, and Antigravity 2.0 continuity * Best for terminal-agent workflows, not general Gemini API access * Full guide: [Antigravity CLI Setup](/docs/implementation/agentic-ai-tools/antigravity-cli-setup-guide) ### OpenCode [#opencode] * Multi-provider terminal UI * Good fit for comparing GPT, Claude, Gemini, DeepSeek, Kimi, GLM, Qwen, xAI, and local models * Best when model choice is the experiment * Full guide: [OpenCode Setup](/docs/implementation/agentic-ai-tools/opencode-setup-guide) ## Comparison table [#comparison-table] | Feature | Cherry Studio | Claude Code | Antigravity CLI | OpenCode | | --------------- | ------------------------- | ----------------------------------- | -------------------------------------------- | ------------------------------- | | Interface | GUI | CLI | CLI | TUI | | Provider model | Many providers | Claude | Google Antigravity/Gemini paths | Many providers | | Best role | Exploration and teaching | Primary project workspace | Google terminal-agent workflow | Provider comparison | | Direct API keys | Yes | Usually no | No for normal sign-in flow | Yes | | MCP support | Full | Full | Use documented settings/plugin paths only | Depends on host/provider config | | Project memory | Knowledge bases and chats | Project files + Claude config | Project files + Antigravity settings/plugins | Project config | | Cost shape | Provider API usage | Subscription/API, depending on plan | Google account/enterprise path | Provider API usage | | Best for | Starting out | Deep work | Google-agent continuity | Model experimentation | ## Which one should you use? [#which-one-should-you-use] ### If you are new to the workflow [#if-you-are-new-to-the-workflow] Start with Cherry Studio. It makes providers, API keys, knowledge bases, and MCP servers visible. Add a CLI only after you have a real project folder and repeated tasks. ### If you want the strongest single-agent workspace [#if-you-want-the-strongest-single-agent-workspace] Use Claude Code. It is the default workspace on this site because it handles repository context, file edits, command execution, and research infrastructure cleanly. ### If you used Gemini CLI [#if-you-used-gemini-cli] Move the terminal-agent workflow to Antigravity CLI. Keep direct Gemini API work with Google AI Studio, Cherry Studio, OpenCode, Vox, or another provider client. ### If you want to compare models [#if-you-want-to-compare-models] Use OpenCode. It keeps the tool constant while you vary the model or provider. This approach works well for model-selection experiments. ## Research phases [#research-phases] | Research phase | Recommended surface | Reason | | -------------------------------- | ------------------------------ | ----------------------------------------------------- | | First setup | Cherry Studio | Lowest friction for provider keys and knowledge bases | | Literature exploration | Cherry Studio or OpenCode | Easy model comparison and corpus experiments | | File-based analysis | Claude Code or Antigravity CLI | Agents can work inside a project folder | | Multi-model challenge | OpenCode or Vox MCP | Same prompt across different providers | | Final writing and infrastructure | Claude Code | Strong project reasoning and repo operations | ## Terminal basics [#terminal-basics] If you are new to terminals, these commands are enough to begin: ```bash cd ~/Documents/Research-Project pwd ls ``` Launch the CLI you installed: ```bash claude agy opencode ``` Exit most terminal tools with `exit`, `/exit`, or `Ctrl+D`, depending on the tool. ## API keys vs sign-in [#api-keys-vs-sign-in] Do not use the same authentication pattern for every tool. | Auth pattern | Used by | Notes | | -------------------------- | ------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------- | | Provider API key | Cherry Studio, OpenCode, Vox | Use `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `GOOGLE_API_KEY`, `GEMINI_API_KEY`, etc. only when the client calls that provider directly. | | Product sign-in | Claude Code, Antigravity CLI | The tool handles the session. Do not invent provider env vars unless the official docs say to. | | Enterprise project binding | Antigravity CLI, some Claude/Google setups | Follow your organization's onboarding path. | ## Setup guides [#setup-guides] * [Cherry Studio Setup](/docs/implementation/agentic-ai-tools/cherry-studio-setup-guide) * [Claude Code Setup](/docs/implementation/agentic-ai-tools/claude-code-setup-guide) * [Antigravity CLI Setup](/docs/implementation/agentic-ai-tools/antigravity-cli-setup-guide) * [OpenCode Setup](/docs/implementation/agentic-ai-tools/opencode-setup-guide) ## Troubleshooting [#troubleshooting] ### Large-context Gemini model access [#large-context-gemini-model-access] Use the Gemini API path in [API Keys Setup](/docs/implementation/ai-environment-setup/api-keys-setup-guide), or use a client such as Cherry Studio, OpenCode, or Vox. Antigravity CLI is the terminal-agent product path, not the general Gemini API setup page. ### Old Gemini CLI notes [#old-gemini-cli-notes] If the note is about terminal-agent usage, migrate it to Antigravity CLI. If it is about model/API access, keep the Gemini API-key guidance. ### Choosing a single CLI [#choosing-a-single-cli] Use Claude Code if you want one primary workspace. Use OpenCode if provider comparison matters more than a single polished agent. Use Antigravity CLI if you specifically want the Google Antigravity path. ## External references [#external-references] * [Claude Code docs](https://docs.claude.com/en/docs/claude-code/) * [Antigravity CLI docs](https://antigravity.google/docs/cli-overview) * [OpenCode docs](https://opencode.ai/docs/) * [Cherry Studio docs](https://docs.cherry-ai.com/docs/en-us)