Continue CLIvsLate
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Continue CLI
Continue · Terminal agent
#24OSSMCP
Panel
6.44 spec wins
- Reliability
- 6.2
- Usefulness
- 6.3
- Cost
- 8.0
- Longevity
- 5.2
“It installs by piping a URL straight into your shell, then politely asks permission before it touches a single file.”
Late
mlhher · Terminal agent
#49OSS
Panel
6.41 spec wins
- Reliability
- 5.7
- Usefulness
- 6.3
- Cost
- 8.3
- Longevity
- 5.2
“It is primarily developed inside itself, which is either dogfooding or a hostage situation.”
Spec by spec
| Spec | Continue CLI | Late |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local | local |
| Platforms | macos, linux, windows | macos, linux, windows |
| 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 | No |
| Browser control | No | No |
| Sandboxed execution | NoThe docs describe running the CLI inside a Docker container, not sandboxing the agent in one. | No |
| Multi-agent orchestration | No | YesSubagents are enforced rather than optional: the orchestrator plans and spawns one ephemeral subagent per atomic edit. |
| Headless / CI mode | Yes | No |
| Models | ||
| Backbone | any provider configured in config.yaml, Anthropic | local models, DeepSeek, any frontier model |
| Bring your own model | Yes | Yes |
| Local models | YesThe CLI reads the same ~/.continue/config.yaml provider schema as the IDE extensions, including a custom apiBase, so any local server can be configured; the CLI pages defer to that reference rather than naming Ollama or LM Studio. | YesThe stated goal is running real work on consumer hardware with tiny local models. |
| 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 | Apache-2.0 | NOASSERTION |
| GitHub stars | 36,084 | 440 |
Which one would each critic pick
| Critic | Continue CLI | Late | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.8 | 6.8 | no preference |
| El Crítico | 6.3 | 6.0 | Continue CLI — Tool safety here is a command-line flag: one auto switch turns the gate off, and the row records no container isolation behind it. |
| El Profesor | 6.5 | 7.0 | Late — The failure hypothesis is named rather than assumed: analysis output, compiler errors and file contents accumulate in one window until planning quality falls. |
| La Inversora | 5.3 | 5.8 | Late — One author, no company, 415 stars and no mechanism for turning attention into time: the survival question here is a single person's calendar. |
| La Jefa | 6.0 | 5.3 | Continue CLI — Zero licence for sixty and a single-shot flag that fits our pipelines, but sign-in goes to a vendor account by default and nothing on the row mentions SSO or audit. |
| El Hacker | 7.8 | 7.5 | Continue CLI — Apache-2.0 with the whole thing in a public monorepo, and a provider block that takes a custom apiBase, which is how my own server gets in. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.