OpenCode

Built in tools let the agent read, edit and search files and execute shell commands, extended by MCP servers, custom tools, plugins, configurable code formatters, and LSP servers automatically loaded to give the model language intelligence; native GitHub and GitLab integrations are documented, and IDE and desktop surfaces sit alongside the terminal.

Sourceopencode.ai/docs/tools, docs/mcp-servers, docs/lsp, docs/github and docs/gitlabread 2026-08-30

A two phase Plan then Build workflow lets the agent propose an implementation approach for review before making any changes, multiple agents can run in parallel on the same project, custom agents are configurable with their own tools and models, and custom commands and Agent Skills package repeatable multi step work.

Sourceopencode.ai/docs/agents, docs/commands and docs/skillsread 2026-08-30

Context is assembled per run: built in tools read, grep, glob and list files on demand, @ fuzzy file references and dropped images attach material to a prompt, and LSP servers loaded at run time give the model language level diagnostics and symbols. No maintained retrieval structure over the customer's code or documents is documented, and the docs navigation has no index or knowledge page; AGENTS.md from /init and rules are instructions the product applies.

Sourceopencode.ai/docs/tools, /docs/lsp and /docs/rules; opencode.ai/docs/lspread 2026-09-29

Plan mode disables the agent's ability to make changes so it proposes an approach for review before building, toggled with a single key and switched back to Build mode once the plan is agreed; permissions and policies govern what the agent may do, /undo and /redo revert or replay changes and can be run repeatedly, and non interactive CLI mode auto approves only when explicitly invoked for scripting.

Sourceopencode.ai/docs/permissions, docs/policies and docsread 2026-08-30

Enterprise deployment documents SSO integration through a central organization config, an internal AI gateway with all other providers disableable, permission rules and organization policies, and private npm registry support; the architecture stores no code or context data, with all processing local or direct to the customer's chosen provider, and the only exception, the optional share feature, is disableable by config. No SOC 2, ISO or other attestation is published.

Sourceopencode.ai/docs/enterprise, docs/permissions and docs/policiesread 2026-08-30

Sessions are stored locally and can be shared as a link exposing the full conversation for reference or debugging, the TUI shows tool calls as they run, and the agent is MIT licensed so its behavior is fully inspectable. No audit log, run history or organization level record of agent actions is documented.

Sourceopencode.ai/docs/share and github.com/anomalyco/opencoderead 2026-08-30

Sessions persist locally and can be resumed and shared by link, and /undo and /redo traverse change history within a session, so a run carries on where it stopped. No memory layer that the agent writes and reads across sessions is documented, and the docs navigation has no memory page; AGENTS.md carries project conventions as instructions, not agent retained memory.

Sourceopencode.ai/docs/share, /docs/rules and the docs navigationread 2026-09-29

The agent is MIT licensed open source running entirely on the developer's own machine, installable via script, npm, Homebrew, Arch, Chocolatey, Scoop, Mise or Docker, with no code or context data stored by the vendor and all processing local or direct to the customer's chosen provider; enterprise deployment routes everything through an internal AI gateway with other providers disabled, and the only hosted component, share pages, can be disabled by config with self hosting on the roadmap.

Sourceopencode.ai/docs/enterprise and docsread 2026-08-30

Agent Skills package reusable agent capabilities, custom agents and custom commands are configurable and shareable, plugins extend the runtime, and a documented ecosystem page collects community extensions; there is no vendor published catalog of prebuilt agents installable in one click.

Sourceopencode.ai/docs/skills, docs/agents, docs/commands and docs/ecosystemread 2026-08-30

The GitHub integration starts runs without anyone invoking them: pull_request runs OpenCode when a pull request is opened, synchronized or reopened, issues runs it when an issue is created or edited, and schedule runs it on a cron schedule with a stored prompt, with a published schedule example; comment mentions (/opencode or /oc) and workflow_dispatch cover invoked runs. Beyond GitHub, invocation spans the TUI, a scriptable non interactive CLI returning text or JSON, the desktop app, the IDE extension, a headless HTTP server, ACP clients and a GitLab integration.

Sourceopencode.ai/docs/github (Supported Events, Schedule Example) and /docs/gitlabread 2026-09-29

Model agnostic by design: any LLM provider can be configured with the customer's own API key across more than 75 providers via Models.dev including local models, with a provider directory, per agent model configuration, an optional curated OpenCode Zen list, Claude Pro and Max account login, and enterprise routing through an internal AI gateway.

Sourceopencode.ai/docs/providers and docs/modelsread 2026-08-30

A published JS/TS SDK, a headless HTTP server with an OpenAPI spec, a plugin system, custom tools, MCP server support, ACP support and a documented ecosystem page; the whole agent is MIT licensed on GitHub under anomalyco/opencode, and GitHub Copilot ships a formal integration authenticating with OpenCode.

Sourceopencode.ai/docs/sdk, docs/server, docs/plugins and docs/mcp-serversread 2026-08-30

LSP servers surface diagnostics so the agent can see and correct errors in its own edits, the agent can run tests and commands through built in shell tooling, and /undo and /redo support iterating on a failed attempt; no evaluation harness, replay or regression testing of agent behavior is documented.

Sourceopencode.ai/docs/lsp and docs/toolsread 2026-08-30

The agent works through file operations, shell commands, LSP servers and MCP tools in the terminal; no browser control or operation of software lacking a programmatic interface is documented anywhere in the docs.

Sourceopencode.ai/docs/toolsread 2026-08-30