mini-SWE-agent vs OpenAI Codex
mini-SWE-agent (Princeton University & Stanford University (SWE-agent team)) and OpenAI Codex (OpenAI) side by side on public data, as of Nov 20, 2026.
OpenAI Codex has 8.6x the weekly package downloads of mini-SWE-agent (26.6M against 3.1M). OpenAI Codex has 13.9x the GitHub stars of mini-SWE-agent (136K against 9,771). Over the last 30 days downloads moved -2% for mini-SWE-agent and +7% for OpenAI Codex.
Which should you choose?
Choose mini-SWE-agent if
- benchmark results matter to you: 91.0% on Terminal-Bench against 62.1%
Choose OpenAI Codex if
- you want it inside your editor
- you want to work from a browser
- you want to check in from your phone
- you want subagents or several agents working in parallel
- you prefer the more widely used tool, with more docs and answers around (Gid Score 84 against 51)
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 | OpenAI Codex |
|---|---|---|
| Gid Score | 51 | 84 |
| Usage data as of | Nov 19 | Nov 19 |
| Rank by Gid Score | #40 | #2 |
| Downloads, last 7 days | 3.1M | 26.6M |
| Downloads, 7-day change | down 3.5% | up 2.4% |
| Downloads, 30-day change | down 1.7% | up 7.4% |
| VS Code installs | — | 16.9M |
| Marketplace rating | — | 2.7 / 5 (975) |
| GitHub stars | 9,771 | 136K |
| Homebrew installs, 30 days | — | 529K |
| Hacker News mentions, 30 days | 5 | 1,429 |
| Latest stable release | 2.4.6 · 4mo ago | 0.168.0 · 7d ago |
| Stable releases, 90 days | 0 | — |
| Terminal-Bench (best run) | 91.0% · v4.1 | 62.1% · v4.1 |
| Price | Free (OSS) | Free + $8/mo |
| Usage limits | — | 5-hour limit, weekly limits may apply Go: GPT-6 Luna in the desktop app; limits not published all plans |
| Incidents, last 30 days | — | 1 |
| License | MIT | Apache-2.0 |
| First released | April 2024 | April 2025 |
| Interfaces | CLI | CLI, IDE extension, Desktop, Web, Mobile, SDK |
| Models | Any model via LiteLLM, OpenRouter, Portkey and similar | OpenAI GPT models (GPT-6 family per current docs) via ChatGPT sign-in or an OpenAI API key |
A dash means there is no public data for that metric as of Nov 20, 2026.
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
OpenAI Codex
OpenAI's coding agent, offered as an open-source terminal CLI, an IDE extension, a desktop app and a cloud agent that works on repositories. Users sign in with a ChatGPT account or use an OpenAI API key; with an API key, Codex works in the CLI, SDK and IDE extension without cloud features such as GitHub code review and Slack. On the Free and Go plans Codex runs in the desktop app (subject to rollout); the web, CLI and IDE extension come with Plus and higher.
Pricing: Included in ChatGPT plans: Free $0, Go $8/month, Plus $20/month, Pro from $100/month ($100, $200 or $500 tiers), Business $20/user/month billed annually ($25 monthly), Enterprise and Edu by contact. API-key use is billed at API rates (no cloud features).
Latest release 0.168.0:
- Browse model providers under Sessions → Model providers and choose the default for new chats.
- Enable features.tui_workspace to view a side conversation beside the main chat. Drag the divider to resize the panes or press leader z to zoom the focused pane.
- Attach recordings when using an audio-capable model. Codex skips confirmed rejected recordings on later turns and uses clip duration to keep more short recordings in context.
- Enable features.image_generation_animation to generate or edit animated GIFs with optional frame count and timing controls.
mini-SWE-agent vs OpenAI Codex: common questions
How do mini-SWE-agent and OpenAI Codex prices compare?
mini-SWE-agent: Free (OSS). OpenAI Codex: Free + $8/mo. Prices come from each vendor's pricing page.
Which is more popular, mini-SWE-agent or OpenAI Codex?
OpenAI Codex has a Gid Score of 84 against 51 for mini-SWE-agent. The score combines package downloads, editor installs, GitHub activity and attention, updated daily.
Do mini-SWE-agent and OpenAI Codex support MCP servers?
OpenAI Codex documents support for MCP servers; mini-SWE-agent's documentation does not.