mini-SWE-agent vs OpenCode
mini-SWE-agent (Princeton University & Stanford University (SWE-agent team)) and OpenCode (Anomaly (SST team)) side by side on public data, as of Nov 20, 2026.
OpenCode has 1.3x the weekly package downloads of mini-SWE-agent (3.9M against 3.1M). OpenCode has 23.3x the GitHub stars of mini-SWE-agent (228K against 9,771). Over the last 30 days downloads moved -2% for mini-SWE-agent and +29% for OpenCode. OpenCode shipped 38 stable releases in the past 90 days.
Which should you choose?
Choose OpenCode if
- you want to switch between model providers (11 documented against 4)
- you want it inside your editor
- you want to work from a browser
- you want subagents or several agents working in parallel
- you prefer the more widely used tool, with more docs and answers around (Gid Score 80 against 51)
- you want frequent updates (38 stable releases in 90 days against 0)
Built from documented features, official prices, status pages and usage data on this page; it does not judge output quality.
Side-by-side numbers
| Metric | mini-SWE-agent | OpenCode |
|---|---|---|
| Gid Score | 51 | 80 |
| Usage data as of | Nov 19 | Nov 19 Wikipedia from Nov 15 |
| Rank by Gid Score | #40 | #3 |
| Downloads, last 7 days | 3.1M | 3.9M |
| Downloads, 7-day change | down 3.5% | up 15.4% |
| Downloads, 30-day change | down 1.7% | up 28.7% |
| VS Code installs | — | 1.3M |
| Marketplace rating | — | 3.6 / 5 (30) |
| GitHub stars | 9,771 | 228K |
| Homebrew installs, 30 days | — | 47.7K |
| Hacker News mentions, 30 days | 5 | 472 |
| Latest stable release | 2.4.6 · 4mo ago | 2.3.2 · 2d ago |
| Stable releases, 90 days | 0 | 38 |
| Terminal-Bench (best run) | 91.0% · v4.1 | 51.7% · v2.0 |
| Price | Free (OSS) | Free + $10/mo |
| License | MIT | MIT |
| First released | April 2024 | May 2025 |
| Interfaces | CLI | CLI, Desktop, IDE extension, Web, SDK |
| Models | Any model via LiteLLM, OpenRouter, Portkey and similar | 75+ providers via Models.dev incl. local models; OpenCode Zen/Go curated models; GitHub Copilot and ChatGPT Plus/Pro logins |
A dash means there is no public data for that metric as of Nov 20, 2026. The Terminal-Bench results come from different versions (v4.1 and v2.0), so they are not directly comparable.
Trends
mini-SWE-agent
Open-source software-engineering agents from Princeton and Stanford researchers: SWE-agent (2024) and its roughly 100-line successor mini-SWE-agent, which uses only bash and works with any model through LiteLLM and similar routers. The SWE-agent README says development effort has moved to mini-SWE-agent.
Pricing: Free MIT-licensed research software; users pay their model provider through their own API keys.
Latest release 2.4.6:
- fix(agents): count billed calls that fail to parse against cost_limit
OpenCode
Open-source coding agent from Anomaly (the team behind SST) that runs as a terminal UI, desktop app or IDE extension and connects to 75+ model providers, including local models and existing ChatGPT or GitHub Copilot logins. OpenCode 2 is now available; per the docs, OpenCode 1 and 2 both use the opencode command and cannot be installed side by side under the default command.
Pricing: OpenCode is free and open source, with free models under a daily request limit. Paid plans: OpenCode Go ($10/month) and Go Plus ($40/month) with monthly usage limits per curated model; you can add credit and turn on extra usage.
Latest release 2.3.2:
- GPT-6.2 Prompt Caching: GPT-6.2 models don't cache a system prompt sent in the Responses instructions field, so every step re-billed it as uncached input.
- Fixed GPT-6.2 models re-billing the system prompt as uncached input on every step. On GitHub Copilot gpt-6.2-sol, uncached input per step dropped from about 14,000 tokens to 3.
- webfetch structured output no longer repeats the url and format it was called with.
mini-SWE-agent vs OpenCode: common questions
How do mini-SWE-agent and OpenCode prices compare?
mini-SWE-agent: Free (OSS). OpenCode: Free + $10/mo. Prices come from each vendor's pricing page.
Which is more popular, mini-SWE-agent or OpenCode?
OpenCode has a Gid Score of 80 against 51 for mini-SWE-agent. The score combines package downloads, editor installs, GitHub activity and attention, updated daily.
Do mini-SWE-agent and OpenCode support MCP servers?
OpenCode documents support for MCP servers; mini-SWE-agent's documentation does not.