opencode

opencode — Provider-agnostic open-source TUI with a client/server split and LSP awareness. opencode is the most credible fully provider-agnostic terminal harness: it resolves models through a shared registry, so anything with an endpoint is a config line rather than a fork. The client/server architecture means the agent can run on one machine and be driven from another, and sessions are shareable by link. It has subagents, per-tool permission rules and LSP integration, but no OS sandbox and no first-class pull-request path. Built by SST. Founded 2025. Open source under MIT.

We track it in 1 comparison — Coding agents — so every claim below is a cell in a table you can open and check rather than an impression. Across those rosters it sits against 16 other tools, and what follows is where it visibly separates from them.

Where it wins.

• Opens PRs — Yes, which only 6 of 16 tools here manage.
• Subagents — Yes, which only 5 of 14 tools here manage.

Each of those is ranked against the whole roster on its category page, not against a hand-picked subset, so a first place here means first of everything we list.

Where it gives ground.

• GitHub stars — 25,000, 6th of 9. Gemini CLI records 75,000.

None of these disqualify it on their own. They are the fields to check against your own requirements before you commit, because they are the ones where a competitor genuinely does better.

Provenance. 24 of 26 tracked fields carry a value for opencode, and 7 of those cite a document you can open. Last verified 2026-01-15. Every figure keeps its own provenance — measured by us, claimed by the vendor, inferred, or community-reported — and we would rather print a dash than a guess.

Its nearest neighbour in our data is Aider. opencode is ahead on Opens PRs (Yes against No) and MCP (Yes against No). Aider takes Checkpoint & undo (Yes against Partial) and GitHub stars (37,000 against 25,000). That pattern repeats across the rest of the roster — see opencode alternatives for the other rivals, each compared the same way.

Company

SST

Founded

2025

Licence

MIT (open source)

Fields we track

24 of 26

Last verified

2026-01-15

The strongest answer for teams who refuse to couple their tooling to one model vendor: provider support is a config line, and the client/server split is genuinely useful for running agents on a remote box. It is also the only MIT-licensed harness here that reaches a pull request, through its own GitHub App. What it still lacks is an OS sandbox — the permission model is per-tool allow/ask/deny rules, which is control rather than containment.

Opens PRs

●Yes1st of 16

Vendor-claimedsource

Subagents

●Yes1st of 14

Inferredverified 2026-01-15

BYOK

●Yes1st of 16

Inferredverified 2026-01-15

Headless / CI

●Yes1st of 16

Inferredverified 2026-01-15

MCP

●Yes1st of 15

Inferredverified 2026-01-15

Entry price

$0 /seat/mo1st of 16

Inferredverified 2026-01-15

Model breadth

any provider / router1st of 16

Vendor-claimedverified 2026-01-15source

Plan mode

●Yes1st of 16

Community-reported

opencode is the right call in these situations, each one drawn from a field we actually record:

• Teams switching model providers often, or comparing them head-to-head.
• Running the agent on a big remote machine and driving it from a laptop.
• Anyone who wants an MIT-licensed harness with subagents and a PR path.
• Opens PRs is your binding constraint. opencode records Yes, which only 6 of the 16 tools in the Coding agents roster do. We define that field as a first-class path to a pull request: a built-in command, a vendor-published GitHub App with its own identity, or a hosted runner.
• Subagents is your binding constraint. opencode records Yes, which only 5 of the 14 tools in the Coding agents roster do. We define that field as can the agent spawn child agents with their own context window and toolset, and collect their results? The main lever for keeping long tasks inside a context budget.

Reach for something else when any of the following is a requirement rather than a nice-to-have:

• GitHub stars. opencode records 25,000, 6th of 9 in the Coding agents roster. Gemini CLI records 75,000 on the same field. If that is a hard requirement rather than a preference, start elsewhere.

We publish this block because a comparison that only lists what a tool is good at is marketing. Every figure above sits on the same page as its source, and the field definitions are on the category tables if you want to check how we measured them.

What we don't know. 2 of the 26 fields we track for opencode are still blank: Terminal-Bench and Bench model. Those render as dashes rather than as zeroes or assumptions, because an empty cell and a bad cell are not the same thing and only one of them is honest. If you know any of these figures and can point at a document, tell us.