CloivsDeep Code CLI
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Cloi
Gabriel Cha · Terminal agent
#188OSS
Panel
6.31 spec wins
- Reliability
- 5.8
- Usefulness
- 5.7
- Cost
- 9.3
- Longevity
- 4.5
“Tool results are saved under names you can use as variables in a session-long Python interpreter, so your chat now has a symbol table.”
Deep Code CLI
Vegamo · Terminal agent
#89OSSMCP
Panel
6.33 spec wins
- Reliability
- 6.0
- Usefulness
- 6.2
- Cost
- 8.2
- Longevity
- 4.7
“It shares one settings file with a VS Code extension, so you can now be misconfigured in two places at the same time.”
Spec by spec
| Spec | Cloi | Deep Code CLI |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local | local |
| Platforms | macos, linux | macos, linux, windows |
| Context window | model-dependent, with older history summarised rather than dropped | not documented |
| Protocols | ||
| MCP client | No | Yes |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | YesShell commands, writes and edits each require approval, with once, always-for-this-tool or no as the answers. | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | No | No |
| Browser control | No | No |
| Sandboxed execution | No | No |
| Multi-agent orchestration | No | No |
| Headless / CI mode | No | No |
| Models | ||
| Backbone | local models via Ollama (Qwen3, Nemotron and other tool-capable models) | DeepSeek V4 |
| Bring your own model | Yes | YesMODEL, BASE_URL and API_KEY are plain settings, so any OpenAI-compatible endpoint can be configured, but the tuning targets DeepSeek V4. |
| Local models | Yes | No |
| Cost | ||
| Pricing model | free | byok |
| Starts at | $0/mo | $0/mo |
| Free tier | Yes | Yes |
| Bring your own key | NoCloi is built around a local Ollama install rather than a provider key; the README states no API key is needed. | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | MIT | MIT |
| GitHub stars | 407 | 2,257 |
Which one would each critic pick
| Critic | Cloi | Deep Code CLI | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.5 | 7.0 | Deep Code CLI — Pick it if you are already spending on DeepSeek and want defaults built for it; pick a provider-agnostic agent if you switch models every month. |
| El Crítico | 5.5 | 6.0 | Deep Code CLI — The row records no git operations, so a multi-file edit lands with no commit boundary and no built-in way back to where you started. |
| El Profesor | 6.8 | 5.8 | Cloi — Six named signals detect a stuck turn and hand the conversation to the larger model mid-run, and answers are checked against the workspace before the user sees them. |
| La Inversora | 5.5 | 6.0 | Deep Code CLI — 2,225 stars and a product whose entire premise is one model vendor's roadmap: the distribution is real and the strategic position is borrowed. |
| La Jefa | 5.8 | 5.5 | Cloi — Nothing per seat, nothing leaves the host, and the hardware requirement means sixty developers need sixty workstations with real graphics memory. |
| El Hacker | 8.0 | 7.3 | Cloi — MIT, a global npm install, everything runs against Ollama with no key anywhere, and subprocesses get a sanitised environment rather than inheriting my shell. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.