Use OpenCode as an IDE and CLI interface for your Orq.ai workspace. Query traces, run evals, inspect deployments, and debug production LLM behavior without leaving your coding environment, with the Orq.ai dashboard available for deeper drill‑down.
Open Code
Use OpenCode as an IDE and CLI interface for your Orq.ai workspace. Query traces, run evals, inspect deployments, and debug production LLM behavior without leaving your coding environment, with the Orq.ai dashboard available for deeper drill‑down.
Quick setup once OpenCode is installed/configured in your editor and an Orq API key is set.
Auth
Orq.ai API key (workspace‑ or project‑level) passed as a bearer token via environment variables or OpenCode’s tool / MCP configuration, depending on how you register the server.
Skills support
OpenCode can call Orq MCP tools when the Orq server is registered and enabled in its tool configuration.
Cloud-based
OpenCode runs inside your editor, while MCP requests from the assistant call Orq’s cloud APIs for workspace data.
Multi‑workspace
Define multiple Orq configurations (for example, different tool entries or env vars) with different API keys to point OpenCode at different Orq workspaces or environments.
Vendor
OpenCode
Pricing
Included with supported Orq.ai workspaces. OpenCode is open‑source; confirm availability of MCP‑style tool integrations in your OpenCode setup and Orq plan.
Why Connect OpenCode to Orq.ai?
Keep your team in one editor
Stop switching between OpenCode, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same environment your team already uses to run OpenCode.
Ask operational questions in natural language
Ask questions like “Show me yesterday’s failed agent runs grouped by error type” and let OpenCode turn that intent into Orq MCP tool calls. No SDKs to learn and no Orq API URLs to memorize.
Connect evals to your development workflow
Use Orq.ai inside your existing OpenCode workflows. From the CLI or the editor integration, pull trace data, design and run evals, and kick off experiments as part of your normal coding sessions.
Keep production behavior visible
Orq.ai gives teams visibility into MCP‑driven activity, including which tools ran, when they ran, and which key or workspace triggered them. OpenCode brings that visibility into the same environment where you write, run, and review code.
Keep your team in one editor
Stop switching between OpenCode, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same environment your team already uses to run OpenCode.
Ask operational questions in natural language
Ask questions like “Show me yesterday’s failed agent runs grouped by error type” and let OpenCode turn that intent into Orq MCP tool calls. No SDKs to learn and no Orq API URLs to memorize.
Connect evals to your development workflow
Use Orq.ai inside your existing OpenCode workflows. From the CLI or the editor integration, pull trace data, design and run evals, and kick off experiments as part of your normal coding sessions.
Keep production behavior visible
Orq.ai gives teams visibility into MCP‑driven activity, including which tools ran, when they ran, and which key or workspace triggered them. OpenCode brings that visibility into the same environment where you write, run, and review code.
Keep your team in one editor
Stop switching between OpenCode, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same environment your team already uses to run OpenCode.
Ask operational questions in natural language
Ask questions like “Show me yesterday’s failed agent runs grouped by error type” and let OpenCode turn that intent into Orq MCP tool calls. No SDKs to learn and no Orq API URLs to memorize.
Connect evals to your development workflow
Use Orq.ai inside your existing OpenCode workflows. From the CLI or the editor integration, pull trace data, design and run evals, and kick off experiments as part of your normal coding sessions.
Keep production behavior visible
Orq.ai gives teams visibility into MCP‑driven activity, including which tools ran, when they ran, and which key or workspace triggered them. OpenCode brings that visibility into the same environment where you write, run, and review code.
Keep your team in one editor
Stop switching between OpenCode, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same environment your team already uses to run OpenCode.
Ask operational questions in natural language
Ask questions like “Show me yesterday’s failed agent runs grouped by error type” and let OpenCode turn that intent into Orq MCP tool calls. No SDKs to learn and no Orq API URLs to memorize.
Connect evals to your development workflow
Use Orq.ai inside your existing OpenCode workflows. From the CLI or the editor integration, pull trace data, design and run evals, and kick off experiments as part of your normal coding sessions.
Keep production behavior visible
Orq.ai gives teams visibility into MCP‑driven activity, including which tools ran, when they ran, and which key or workspace triggered them. OpenCode brings that visibility into the same environment where you write, run, and review code.
Setup
1: Install OpenCode
Install OpenCode according to its docs (CLI and/or editor integration), then verify you can start it in a project directory. For example, from your project: bash opencode OpenCode will automatically load configuration from a global config and from opencode.json in the current project if present
Ensure the following:
OpenCode’s configuration file or settings for tools / MCP servers is accessible
You know where to define new tool / server entries
The environment where OpenCode runs can reach https://my.orq.ai over the network
2: Create an Orq.ai API key
In Orq.ai, create an API key for the workspace or project you want OpenCode to access. Keep this key handy; you can either: export it as an environment variable: bash export ORQ_API_KEY=”<your-orq-api-key>“ or embed it in the mcp configuration in opencode.json (recommended to scope per project).
Keep this key handy; you’ll reference it in OpenCode’s configuration or via an environment variable,
for example:
export ORQ_API_KEY="<your-orq-api-key>"
3: Add the Orq MCP server to OpenCode
OpenCode supports MCP servers via an mcp configuration block, with both global and per‑project config supported. Open (or create) ~/.config/opencode/opencode.json and add an Orq entry to the mcp section, using a remote transport that points at Orq’s MCP endpoint (for example, Streamable HTTP via a client or proxy): json { “mcp”: { “servers”: { “orq”: { “type”: “remote”, “url”: “https://my.orq.ai/v2/mcp”, “env”: { “ORQ_API_KEY”: “<your-orq-api-key>“ } } } } } This pattern mirrors how OpenCode integrates with other remote MCP servers, such as Bright Data Web MCP. Option B – Project config (opencode.json in your repo) Project config is useful when each repo defines its own MCP setup. At the root of your project, create or edit opencode.json: json { “mcp”: { “servers”: { “orq”: { “type”: “remote”, “url”: “https://my.orq.ai/v2/mcp”, “env”: { “ORQ_API_KEY”: “<your-orq-api-key>“ } } } } } When you run opencode in this directory, it will load these settings and connect to Orq as a remote MCP server. After updating config, restart OpenCode or reload the agent so the new MCP server is picked up.
A typical configuration pattern looks like:
Name: orq; Type / transport: HTTP or Streamable HTTP; URL / endpoint: https://my.orq.ai/v2/mcp; Auth: Authorization: Bearer <your-orq-api-key> (often provided via ORQ_API_KEY)
Restart OpenCode or reload your editor’s extension so the assistant picks up the new server.
4: Start using Orq.ai tools from OpenCode
From your project directory: bash opencode Then, in the OpenCode session, ask: “What MCP tools do you have access to?” or “Use Orq to list recent failed agent runs grouped by error type.” If everything is configured correctly, OpenCode will call Orq’s MCP tools and show results inline in your session or editor integration
“What tools do you have access to?” or
“Use Orq to list yesterday’s failed agent runs grouped by error type.”
If configured correctly, OpenCode will call Orq’s MCP tools and show results inline in your IDE.
What Can You Do with Orq.ai + OpenCode
Query observability data in natural language
Use OpenCode to “talk” to your Orq.ai traces. Ask for failed agent runs, slowest requests over the last 24 hours, or errors grouped by model, then apply those insights directly in your coding workflow.
Design and run evaluations
Describe the behavior you want to test, let OpenCode and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without moving into a separate tool.
Compare prompts, models, and configs
From OpenCode, create experiments that compare prompts, models, or configurations, run them on real or synthetic datasets, and inspect results in Orq.ai when you need more detail.
Generate reusable synthetic datasets
Ask OpenCode’s agent to create challenging synthetic test cases for workflows such as contract analysis or support tickets, and save them as reusable Orq.ai datasets.
Debug production regressions as a team
When something breaks, stay in OpenCode. Pull recent traces for a deployment via Orq, filter by failure pattern, and use those examples to guide prompt or model changes backed by experiments and evals.
Query observability data in natural language
Use OpenCode to “talk” to your Orq.ai traces. Ask for failed agent runs, slowest requests over the last 24 hours, or errors grouped by model, then apply those insights directly in your coding workflow.
Design and run evaluations
Describe the behavior you want to test, let OpenCode and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without moving into a separate tool.
Compare prompts, models, and configs
From OpenCode, create experiments that compare prompts, models, or configurations, run them on real or synthetic datasets, and inspect results in Orq.ai when you need more detail.
Generate reusable synthetic datasets
Ask OpenCode’s agent to create challenging synthetic test cases for workflows such as contract analysis or support tickets, and save them as reusable Orq.ai datasets.
Debug production regressions as a team
When something breaks, stay in OpenCode. Pull recent traces for a deployment via Orq, filter by failure pattern, and use those examples to guide prompt or model changes backed by experiments and evals.
Query observability data in natural language
Use OpenCode to “talk” to your Orq.ai traces. Ask for failed agent runs, slowest requests over the last 24 hours, or errors grouped by model, then apply those insights directly in your coding workflow.
Design and run evaluations
Describe the behavior you want to test, let OpenCode and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without moving into a separate tool.
Compare prompts, models, and configs
From OpenCode, create experiments that compare prompts, models, or configurations, run them on real or synthetic datasets, and inspect results in Orq.ai when you need more detail.
Generate reusable synthetic datasets
Ask OpenCode’s agent to create challenging synthetic test cases for workflows such as contract analysis or support tickets, and save them as reusable Orq.ai datasets.
Debug production regressions as a team
When something breaks, stay in OpenCode. Pull recent traces for a deployment via Orq, filter by failure pattern, and use those examples to guide prompt or model changes backed by experiments and evals.
Query observability data in natural language
Use OpenCode to “talk” to your Orq.ai traces. Ask for failed agent runs, slowest requests over the last 24 hours, or errors grouped by model, then apply those insights directly in your coding workflow.
Design and run evaluations
Describe the behavior you want to test, let OpenCode and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without moving into a separate tool.
Compare prompts, models, and configs
From OpenCode, create experiments that compare prompts, models, or configurations, run them on real or synthetic datasets, and inspect results in Orq.ai when you need more detail.
Generate reusable synthetic datasets
Ask OpenCode’s agent to create challenging synthetic test cases for workflows such as contract analysis or support tickets, and save them as reusable Orq.ai datasets.
Debug production regressions as a team
When something breaks, stay in OpenCode. Pull recent traces for a deployment via Orq, filter by failure pattern, and use those examples to guide prompt or model changes backed by experiments and evals.
OpenCode Direct vs With Orq.ai MCP
Capability
OpenCode alone
OpenCode + Orq.ai MCP
Query production LLM traces
No built‑in view into Orq.ai’s observability data.
Ask OpenCode to list, filter, and group Orq.ai traces (failures, slow runs, agent tool calls, etc.) from inside the IDE.
Run experiments on prompts
Teams can iterate on prompts manually in chat, but no native experiment tracking in Orq.ai.
Create and run Orq.ai experiments comparing prompts, models, or configs against datasets, directly from OpenCode sessions.
Generate synthetic eval data
You can prompt OpenCode to generate examples, then copy/paste them elsewhere.
Generate synthetic test cases and save them as reusable Orq.ai datasets for evals and experiments.
Pull cost and usage analytics
No view into Orq router or deployment analytics.
Query Orq.ai’s cost, usage, and performance metrics for models and deployments via MCP tools, then inspect them alongside your code in OpenCode.
Run evaluators on datasets
No built‑in concept of Orq evaluators or datasets.
Work with Orq evaluators and datasets from OpenCode, depending on the MCP tools enabled.
FAQs
Do I have to use OpenCode to get value from Orq.ai?
No. Orq.ai works on its own through the UI and API. OpenCode is an optional coding agent front‑end for your workspace. You get the same experiments, evals, and observability in Orq; OpenCode simply lets teams drive them from their CLI or editor using natural language.
What can OpenCode see in my Orq.ai workspace, and how is access controlled?
OpenCode only sees what the Orq API key you configure is allowed to access. If you use a project‑level key scoped to a specific workspace or environment, OpenCode can only query traces, experiments, datasets, and deployments inside that scope. Rotate or revoke the key in Orq to instantly cut off access.
Can I point OpenCode at different Orq environments (dev, staging, prod)?
Yes. You can create separate Orq entries in global opencode.json and/or per‑project opencode.json, or use different API keys per project, then run OpenCode in the context you need. That way, you can run evals and inspect traces in dev or staging first, then switch the same OpenCode install to the production environment.
Does OpenCode connect to Orq directly from my machine?
Yes. OpenCode runs on your local machine (CLI and editor integrations) and connects to remote MCP servers over the network. Your Orq MCP endpoint must be reachable over the public internet (or via your network/VPN), and Orq handles authentication and scoping via your API key.
