OpenCode logo

OpenCode

OpenCode AI Agent
Rating:
Rate it!
Category:Programming Assistants

Overview

Open-source AI coding agent for terminal, desktop, and IDEs—plans changes, edits code, and can run tasks in GitHub via comments.

Visit website
One more linkOne more linkOne more link

Best For Professions:

software developersautomation engineersDevOps engineersSDETsQA engineers

OpenCode is an open-source AI coding agent designed to help developers plan, implement, and refactor code from a terminal-first workflow, with options to use it as a desktop app or IDE extension. It can connect to multiple model providers (or use included free models), apply changes across a codebase, and support common developer flows like asking questions, adding features, making edits, and undoing changes. OpenCode also integrates with GitHub workflows: you can mention a command in issues or pull requests to have it execute tasks inside a GitHub Actions runner.

AI Agent Store research

What the evidence says about OpenCode

OpenCode is an open-source coding agent and agent harness available in the terminal, desktop apps, IDEs, and GitHub Actions. It can inspect and edit repositories, run commands, delegate searches, use configurable tools, and connect to more than 75 hosted or local model providers.

Last reviewed August 18, 2026

Verified capabilities

  • Configurable coding agents

    Built-in build and plan agents can be extended with custom primary agents and subagents, distinct prompts, models, tool access, and permission policies.[2]

  • Broad model-provider support

    OpenCode supports more than 75 providers, custom OpenAI-compatible endpoints, and local models, while optional Zen supplies a curated pay-as-you-go model set.[3], [5]

  • GitHub issue and pull-request automation

    GitHub Actions can trigger OpenCode from issue or review comments, schedules, pull requests, or manual workflows to investigate, implement changes, review code, and open pull requests.[4]

Research coverageExact counts from this profile; bars are relative to the largest count shown.

Where it fits best

  • Developers who want a terminal-first, provider-agnostic coding agent with optional desktop, IDE, local-model, and GitHub automation surfaces.[1], [4]

Buying and deployment notes

The MIT-licensed OpenCode client is free. Users pay their chosen model provider or run local models. Optional OpenCode Zen starts by adding a $20 pay-as-you-go balance plus card processing and charges provider prices per request with no markup.[1], [5]

Platforms: Terminal UI, macOS desktop, Windows desktop, Linux desktop, IDE extension, GitHub Actions[1], [3], [4]

Deployment: Local binary, Docker container, GitHub-hosted or self-hosted Actions runner, Local or hosted model endpoints[1], [3], [4]

What users repeatedly mention

Two independent hands-on reviews consistently highlight model-provider choice, open-source control, and native plan-versus-build modes. They also emphasize that results and cost depend on the selected model and that terminal-first operation remains a deliberate tradeoff.[6], [7]

  • Output quality varies by model[6], [7]
  • Terminal-first workflow has a learning curve[6], [7]
  • Provider and token costs remain separate[6], [7]
Important considerations
  • The open-source client does not include model inference: users must configure provider credentials, a subscription integration, OpenCode Zen or Go, or a capable local model.[1], [3], [5]
  • Build agents can edit files and run shell commands, so repository, external-directory, web, and tool permissions must be configured to match the desired safety boundary.[2]
  • Independent reviews praise provider choice and the plan/build split but also describe model-dependent quality and a terminal-centered workflow that will not suit every developer.[6], [7]
Sources and research method (7)

We record only claims tied to public sources checked by our team or listing workflow. Counts above are derived directly from this profile, not a subjective rating.

  1. Intro | OpenCode DocumentationDocumentation · checked 2026-08-18
  2. Agents | OpenCode DocumentationDocumentation · checked 2026-08-18
  3. Providers | OpenCode DocumentationDocumentation · checked 2026-08-18
  4. GitHub | OpenCode DocumentationDocumentation · checked 2026-08-18
  5. OpenCode ZenPricing page · checked 2026-08-18
  6. OpenCode review 2026: the open-source terminal coding agentIndependent review · checked 2026-08-18
  7. Is OpenCode Actually Good? A Deep DiveIndependent review · checked 2026-08-18

Autonomy level

74%

Reasoning: OpenCode demonstrates substantial autonomous capabilities as a terminal-based AI coding agent. It operates through an agentic loop where it iterates autonomously by analyzing tasks, calling available tools (file operations, bash commands, web fetching, LSP diagnostics), using results as new inputs, and repeating until task completion. The Build age...

Comparisons

Custom Comparisons

Some of the use cases of OpenCode:

  • Planning and implementing features directly from a terminal-based coding workflow.
  • Refactoring and updating multi-file codebases with agentic change execution.
  • Connecting your preferred LLM provider for coding help (or using included free models).
  • Running repository tasks from GitHub issues/PRs by triggering OpenCode in CI via comments.

Loading Community Opinions...

Pricing model:

free

Code access:

open-source

Popularity level: 53%

Industries:

Software DevelopmentBusiness Automation

Tags:

terminal uiide extensiondesktop appcode refactoringmulti-file editsgithub actionsci automationmodel providers

OpenCode Video:

Free credibility widget

Turn this profile into a trust signal

Show prospects that OpenCode has a public place where they can check product details, pricing, ratings, and reviews.

Build confidence

Give buyers a third-party profile to explore.

Reduce hesitation

Put validation beside your strongest CTA.

Earn discovery

Every badge links prospects to your listing.

Choose your style

Preview it, then copy the complete embed code.

Live previewReady to embed

Shows buyers where to validate your product, pricing, and reputation.

Plain HTML. No signup, script, or maintenance required.

All AI AgentsOpenCode Video Page
Make it work for you

Describe the job. Get an AI worker you can actually message.

We create the setup, keep it running after your laptop closes, and save its memory. Test in the browser, then add Telegram, WhatsApp, or Slack.

Runs without your laptopBrowser + messaging appsCredits, keys, or subscriptionsMemory survives restarts
Describe my agentSee Agent Teams

Plans start at $29/month. Cancel anytime.

Hosted agent

OpenClaw or Hermes

saved state
Browser
WhatsApp
Telegram
Slack
“I checked the inbox, handled the routine messages, and sent you the one question that needs a decision.”
Create an AI worker that keeps running after this tab closes.
Open Agent Teams

Did you find this page useful?

Not useful
Could be better
Neutral
Useful
Loved it!