# opencode v1.19.4: what's new, verdict & setup Canonical: https://theagenticweekly.com/tools/opencode · Released: 2026-10-22 · Last verified: 2026-10-25 · Evidence: Tested (smoke test, 2026-10-25, local Qwen2.5-3B-Instruct, not vendor models) · Vendor: anomalyco (GitHub organization) · Official site: https://opencode.ai/ > Open-source terminal coding agent with a TUI, a desktop app and many model providers. ## Verdict **Update when convenient for the runtime security fixes; pick opencode if you want an open-source agent that is not tied to one model vendor.** Good for: - Developers who want an MIT-licensed terminal agent - People who switch between model providers - Anyone who wants a desktop app as well as a CLI Skip if: - You need a vendor-backed support contract - You expected feature news; this release is mostly a runtime upgrade Tested. Tested 2026-10-25 (America/Chicago). Installed opencode-ai 1.19.4 from npm and ran "opencode run" headless with a custom OpenAI-compatible provider pointing at a local Ollama model. Task: change return a-b to a+b in calc.py. Attempt 1 called the edit tool on the wrong path (src/calc.py) and failed; attempt 2, with the path stated, edited calc.py and showed the diff. Not tested: the README's v2 installer or @opencode/cli 2.x package, the desktop app, or the Bun security fixes. Test environment: Linux x86_64 box with 8 CPUs and no GPU, no vendor account or API key. Agent tools were pointed at a local open-weight model (Qwen2.5-3B-Instruct, 4-bit, served by Ollama 0.40.11), so we tested the tool, not any vendor's hosted models. Full log: /tests/opencode. Test scope: - Kind and date: smoke test, 2026-10-25 (America/Chicago). Not a benchmark. - What we ran: Installed opencode-ai 1.19.4 from npm and ran 'opencode run' headless with a custom OpenAI-compatible provider pointing at a local model; attempt 1 edited the wrong path and failed, attempt 2 with the path stated edited calc.py. - Model used: Qwen2.5-3B-Instruct (4-bit), a small local open-weight model served by Ollama 0.40.11; no vendor-hosted model was used - Environment: Linux x86_64 box, 8 CPUs, no GPU; no vendor account, login or API key - Not tested: The README's v2 installer or @opencode/cli 2.x, the desktop app, the Bun security fixes. Full test log (commands, versions, raw output): [opencode 1.19.4: our test log](https://theagenticweekly.com/tests/opencode) Pricing: Not verified. We have not verified pricing for this tool; see the official site. ## Best for - [Best AI tool for AI coding agents](https://theagenticweekly.com/best/ai-coding-agents) (#6): Open-source (MIT) coding agent with a large community; the latest release is a security-flavored runtime bump. ## What's new opencode v1.19.4 is a small maintenance release: it upgrades the bundled Bun runtime to 1.4.4, which the release notes say includes security fixes. The project itself is very active and widely starred. - v1.19.4 (Oct 22): Upgraded the bundled Bun runtime to 1.4.4, which the notes say includes security fixes for Brotli, TLS, HTTP/1.1, HTTP/2, HTTP/3, WebSocket and fetch, and updates root certificates (NSS 3.131.1). - The README lists several install routes: an install script, npm, Homebrew, and a desktop app cask. ## How to set it up: Install opencode and start it in a repo Install steps come from the vendor's docs. We ran the install and a short real task on 2026-10-25; see the test notes above for what was and was not covered. 1. **Install it.** The README recommends the install script, and also lists npm and Homebrew. Check the README for the current command before running a script from the internet. ``` curl -fsSL https://opencode.ai/v2/install | bash ``` 2. **Or use a package manager.** Homebrew on macOS and Linux, or npm globally. ``` brew install anomalyco/tap/opencode-v2 # or npm i -g @opencode/cli@latest ``` 3. **Run it in your project.** Open a terminal in your project folder and start the agent, then connect a model provider when prompted. ``` cd your-project opencode ``` ## Pros and cons Pros: - MIT license and an active GitHub project - Works with many model providers - CLI and desktop app options Cons: - Release notes for v1.19.4 are brief - Quality and speed depend on the model you connect - With a small local model it needed the file path spelled out; we did not test the v2 install routes or the desktop app ## Guides for opencode - [Best model for OpenCode, Cline and Claude Code: options by budget](https://theagenticweekly.com/guides/best-model-for-opencode-cline-claude-code) (Reported (not run by us): prices and setup from vendor docs; our tool tests do not measure model quality; last verified 2026-10-26) - [Which coding agents can use GPT-6.1 Terra?](https://theagenticweekly.com/guides/gpt-6-1-terra-in-coding-agents) (Reported (not run by us): from vendor docs and changelogs; last verified 2026-10-26) ## Alternatives - [Claude Code](https://theagenticweekly.com/tools/claude-code): Anthropic's agentic coding tool for your terminal, IDE and GitHub. - [Cline](https://theagenticweekly.com/tools/cline): Open-source coding agent as an IDE extension, a CLI and an SDK. - [goose](https://theagenticweekly.com/tools/goose): Open-source, extensible AI agent that installs, runs, edits and tests code with the LLM of your choice. - [Amazon Q Developer](https://theagenticweekly.com/tools/amazon-q-developer): AWS's AI coding assistant for IDEs and the CLI, with a free tier and a $19 Pro tier; IDE plugin support ends April 30, 2027. - [Augment Code](https://theagenticweekly.com/tools/augment-code): Coding agent and 'Cosmos' platform with a Context Engine, CLI and cloud agents; plans are flat team prices with usage included. - [Devin](https://theagenticweekly.com/tools/devin): Cognition's autonomous software engineer: a cloud coding agent that tests in its own browser and aims to hand back a mergeable pull request. - [Kiro](https://theagenticweekly.com/tools/kiro): AWS's agentic coding tool that turns prompts into requirements, designs and tasks (spec mode), with an IDE and a CLI. - [Qodo](https://theagenticweekly.com/tools/qodo): AI code review platform with 15+ agentic workflows for IDEs, pull requests and security, priced by team credits. - [Warp](https://theagenticweekly.com/tools/warp): Warp's terminal and agent platform; it now pitches 'open infrastructure for cloud software factories' defined as code, with any model. - [Zed](https://theagenticweekly.com/tools/zed): High-performance, multiplayer code editor from the creators of Atom and Tree-sitter, open source with AI optional. - [Codex CLI](https://theagenticweekly.com/tools/codex-cli): OpenAI's open-source coding agent that runs in your terminal. - [Kilo Code](https://theagenticweekly.com/tools/kilo-code): Open-source AI coding agent for VS Code, JetBrains, CLI and Cloud, with 500+ models at zero markup or your own keys. ## FAQ ### What is new in opencode v1.19.4? It upgrades the bundled Bun runtime to 1.4.4, which the notes say includes several network-stack security fixes, and refreshes root certificates. ### Is opencode open source? Yes. The GitHub repository reports an MIT license. ### How do I install opencode? The README lists an install script, npm, and Homebrew options. See the tutorial on this page. ## What we have not verified - Pricing for any hosted opencode services - Real-world quality versus other agents (not tested) - The full feature list of the v2 CLI (README only skimmed) - The v2 CLI install routes and desktop app (not tested; we ran opencode-ai 1.19.4 from npm) ## Sources - [opencode v1.19.4 release](https://github.com/anomalyco/opencode/releases/tag/v1.19.4) (fetched 2026-10-25) - [opencode README](https://github.com/anomalyco/opencode) (fetched 2026-10-25) ## How to cite Agentic Weekly, "opencode v1.19.4: what's new, verdict & setup", last updated 2026-10-25, https://theagenticweekly.com/tools/opencode Keep the Reported or Tested label when you quote the verdict.