Agent DeckvsDevTeam CLI
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Agent Deck
asheshgoplani · Agent harness
OSSMCP
Panel
6.84 spec wins
- Reliability
- 6.5
- Usefulness
- 6.8
- Cost
- 8.3
- Longevity
- 5.7
“It will run Cursor for you from a terminal, which is one way to settle the argument about editors.”
DevTeam CLI
agent-era · Agent harness
OSS
Panel
6.80 spec wins
- Reliability
- 6.2
- Usefulness
- 6.8
- Cost
- 8.5
- Longevity
- 5.7
“Every feature displays its diff line count, so productivity can now be measured in the least meaningful unit available.”
Spec by spec
| Spec | Agent Deck | DevTeam CLI |
|---|---|---|
| Architecture | ||
| Category | Agent harness | Agent harness |
| Runs | local | local |
| Platforms | macos, linux | 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 | YesEdits are made by the coding agent in each session; Agent Deck supplies the worktree and the review surface. | YesFiles are changed by the Claude Code, Codex or Gemini agent DevTeam launches in each worktree. |
| Git operations | Yes | YesDevTeam creates a git worktree per feature and tracks push state and GitHub PR checks; the agents are expected to open the pull requests. |
| Browser control | Yes | No |
| Sandboxed execution | Yes | No |
| Multi-agent orchestration | Yes | Yes |
| Headless / CI mode | No | No |
| Models | ||
| Backbone | Claude Code, Codex, Gemini, OpenCode, Cursor | Claude Code, Codex, Gemini CLI |
| Bring your own model | Yes | Yes |
| Local models | No | No |
| Cost | ||
| Pricing model | byok | byok |
| Starts at | $0/mo | $0/mo |
| Free tier | Yes | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | MIT | MIT |
| GitHub stars | 994 | 265 |
Which one would each critic pick
| Critic | Agent Deck | DevTeam CLI | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.5 | 7.5 | no preference |
| El Crítico | 6.5 | 6.8 | DevTeam CLI — It tracks push state and pull-request checks but expects the agent to open the pull request, so the last step belongs to nobody in particular. |
| El Profesor | 7.0 | 7.0 | no preference |
| La Inversora | 6.8 | 6.3 | Agent Deck — 839 stars, one GitHub handle and nothing to charge for: session managers are connective tissue between products other people fund. |
| La Jefa | 5.8 | 6.0 | DevTeam CLI — It reads our pull-request checks, which means it touches the one system I do govern, with no SSO, no audit log and no service account of its own. |
| El Hacker | 7.5 | 7.3 | Agent Deck — MIT, and MCP sits at the manager level rather than inside each CLI, so the servers I already run are configured once instead of five times. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.