ccteamvsMyrlin Workbook
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
ccteam
firstintent · Agent harness
OSS
Panel
6.41 spec wins
- Reliability
- 6.0
- Usefulness
- 6.5
- Cost
- 7.7
- Longevity
- 5.3
“It supports scheduled turns, so the agent can now wake at three in the morning and be wrong on a timer.”
Myrlin Workbook
therealarthur · Agent harness
OSS
Panel
6.41 spec wins
- Reliability
- 5.7
- Usefulness
- 6.3
- Cost
- 8.3
- Longevity
- 5.2
“There is a demo mode, so you can watch somebody else's coding sessions before admitting you want to watch your own.”
Spec by spec
| Spec | ccteam | Myrlin Workbook |
|---|---|---|
| Architecture | ||
| Category | Agent harness | Agent harness |
| Runs | local | local |
| Platforms | macos, linux | macos, linux, windows, web |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | No |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | YesCode is changed by the vendor CLI ccteam spawns; ccteam supplies the routing, guardrails and delivery. | YesMyrlin calls no model itself; edits come from the Claude Code or Codex session it spawns in a terminal pane. |
| Git operations | No | YesBranch, dirty state and ahead/behind per project, worktree create and delete, and promoting an issue to a worktree plus a session. |
| Browser control | No | No |
| Sandboxed execution | No | No |
| Multi-agent orchestration | Yes | YesSeveral sessions across both CLIs run at once in their own worktrees; they are not coordinated with each other. |
| Headless / CI mode | No | No |
| Models | ||
| Backbone | Claude Code, Codex, Grok, Kimi, DeepSeek Harness, Pi | Claude Code, Codex |
| 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 | AGPL-3.0 |
| GitHub stars | 620 | 387 |
Which one would each critic pick
| Critic | ccteam | Myrlin Workbook | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.8 | 6.8 | no preference |
| El Crítico | 5.5 | 6.0 | Myrlin Workbook — It reads Claude Code sessions from a vendor's dotfiles and Codex threads from a desktop app's SQLite store, and neither is a published interface. |
| El Profesor | 6.8 | 6.5 | ccteam — Every delegation is recorded as a traceable parent-to-child edge on a live topology, which makes the provenance of a change a queryable structure rather than an inference. |
| La Inversora | 5.8 | 5.8 | no preference |
| La Jefa | 6.3 | 6.0 | ccteam — It keeps a running cost ledger, which is the first time this category has offered me a number before the invoice; Windows only through WSL is the price. |
| El Hacker | 7.3 | 7.3 | no preference |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.