Codex CLIvsmini-SWE-agent
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Codex CLI
OpenAI · Terminal agent
#1OSSMCP
Panel
7.13 spec wins
- Reliability
- 7.3
- Usefulness
- 7.0
- Cost
- 6.8
- Longevity
- 7.2
“Apache-2.0, so you can read every line except the one that lets you pick a model that is not OpenAI's.”
mini-SWE-agent
SWE-agent (Princeton and Stanford) · Terminal agent
#8OSS
Panel
6.90 spec wins
- Reliability
- 6.3
- Usefulness
- 5.5
- Cost
- 8.8
- Longevity
- 7.0
“One hundred lines of Python, which is fewer than most competitors spend on their pricing page.”
Spec by spec
| Spec | Codex CLI | mini-SWE-agent |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local | local, sandbox |
| Platforms | macos, linux, windows | macos, linux |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | Yes | No |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | Yes | Yes |
| Browser control | NoThe shared Codex codebase carries a browser-use configuration with Chrome DevTools Protocol access, but OpenAI's documentation states browser is not available in the Codex CLI or the IDE extension; it runs in ChatGPT on the web and in the desktop app. The CLI's --search flag adds live web search only. | No |
| Sandboxed execution | Yes | Yes |
| Multi-agent orchestration | Yes | No |
| Headless / CI mode | Yes | Yes |
| Models | ||
| Backbone | OpenAI GPT-5.x, GPT-5.x-Codex | any via litellm |
| Bring your own model | Yes | Yes |
| Local models | Yes | Yes |
| Cost | ||
| Pricing model | mixed | byok |
| Starts at | $8/mo | n/a |
| Free tier | Yes | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | Apache-2.0 | MIT |
| GitHub stars | 128,711 | 8,410 |
Which one would each critic pick
| Critic | Codex CLI | mini-SWE-agent | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 8.0 | 6.8 | Codex CLI — If you already pay for ChatGPT, this is the terminal agent you have and it is a good one; open source, MCP, headless, and pointed at OpenAI until you configure it otherwise. |
| El Crítico | 7.0 | 6.5 | Codex CLI — A sandbox mode you choose once is the only barrier between the agent and your shell, the free tier is a taste, and the defaults point at one vendor. |
| El Profesor | 6.3 | 8.0 | mini-SWE-agent — The reference harness for the SWE-bench bash-only leaderboard: one bash action per turn via subprocess.run, a linear history, no tool-calling API, and Gemini 3 Pro reported above 74% on Verified. |
| La Inversora | 8.3 | 6.8 | Codex CLI — A lab's terminal agent bundled into a $20 subscription with 121,000 stars on the repo; the distribution is ChatGPT, and that is the whole thesis. |
| La Jefa | 7.3 | 5.0 | Codex CLI — Business at $20 a seat with SAML SSO and no default training, Enterprise for SCIM and audit logs; if the org is on ChatGPT already, this is a line item, not a project. |
| El Hacker | 5.8 | 8.5 | mini-SWE-agent — MIT, any model through litellm, OpenRouter or Portkey including my local server, a YAML config, and source short enough to read before breakfast; the missing MCP client is the only gap. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.