AgentAPIvscmux
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
AgentAPI
Coder · Agent harness
OSS
Panel
7.33 spec wins
- Reliability
- 7.2
- Usefulness
- 6.7
- Cost
- 8.5
- Longevity
- 6.8
“Its web platform is a chat page served to your own laptop on port 3284, which makes it the most honest cloud on this board.”
cmux
Manaflow · Agent harness
OSS
Panel
6.63 spec wins
- Reliability
- 6.3
- Usefulness
- 6.5
- Cost
- 7.5
- Longevity
- 6.0
“A terminal for coordinating many agents on exactly one operating system, so the agent wars are settled by what laptop you were issued.”
Spec by spec
| Spec | AgentAPI | cmux |
|---|---|---|
| Architecture | ||
| Category | Agent harness | Agent harness |
| Runs | local | local |
| Platforms | macos, linux, windows, web | macos |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | No |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | NoEditing is done by the wrapped agent; AgentAPI only relays messages to and from it. | No |
| Git operations | No | NoThe sidebar displays branch and pull request status but cmux performs no git operations itself. |
| Browser control | No | Yes |
| Sandboxed execution | No | No |
| Multi-agent orchestration | No | YesNative panes for Claude Code Teams and oh-my-opencode orchestration; cmux runs and watches the agents rather than running an agent loop of its own. |
| Headless / CI mode | Yes | No |
| Models | ||
| Backbone | via wrapped agents (Claude Code, Goose, Aider, Gemini CLI, Amp, Codex) | via managed agents (Claude Code, Codex, OpenCode, Gemini CLI, Amp, Aider) |
| Bring your own model | Yes | No |
| Local models | No | No |
| Cost | ||
| Pricing model | free | free |
| Starts at | $0/mo | $0/mo |
| Free tier | Yes | Yes |
| Bring your own key | Yes | No |
| Openness | ||
| Open source | Yes | Yes |
| License | MIT | GPL-3.0-or-later |
| GitHub stars | 1,500 | 27,557 |
Which one would each critic pick
| Critic | AgentAPI | cmux | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.5 | 7.3 | AgentAPI — Pick it when a script or a web page needs to talk to an agent you already trust in a terminal; pick the Claude Agent SDK if you only ever wrap one. |
| El Crítico | 6.5 | 6.5 | no preference |
| El Profesor | 7.0 | 6.8 | AgentAPI — The interface is specified rather than described: an openapi.json ships in the repository with a served documentation UI, and no benchmark is claimed. |
| La Inversora | 7.3 | 6.0 | AgentAPI — Coder gives this away because an agent that speaks HTTP belongs in a remote development environment, and that is the product with the price on it. |
| La Jefa | 7.0 | 5.5 | AgentAPI — Zero licence cost and the rare tool here that fits automation without argument, but the row carries no SSO, no SCIM and no audit log. |
| El Hacker | 8.5 | 7.5 | AgentAPI — MIT, one downloaded binary, `agentapi server -- claude`, and their answer on MCP is a README section showing you how to build that server yourself. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.