GitLab DuovsKelos
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
GitLab Duo
GitLab · Agent harness
MCP
Panel
6.82 spec wins
- Reliability
- 6.7
- Usefulness
- 6.5
- Cost
- 5.8
- Longevity
- 8.0
“It has shipped a Security Analyst agent, so the robot now files the vulnerability the other robot wrote.”
Kelos
Kelos · Agent harness
OSSMCP
Panel
6.84 spec wins
- Reliability
- 7.0
- Usefulness
- 7.0
- Cost
- 7.0
- Longevity
- 6.2
“Agents can be spawned from a cron entry, so your codebase now changes on a schedule whether or not anybody asked.”
Spec by spec
| Spec | GitLab Duo | Kelos |
|---|---|---|
| Architecture | ||
| Category | Agent harness | Agent harness |
| Runs | local, cloud | cloud, sandbox |
| Platforms | macos, linux, windows, web | macos, linux, web |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | Yes | Yes |
| MCP server | Yes | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | Yes | Yes |
| Browser control | No | No |
| Sandboxed execution | No | YesEvery agent runs in an isolated Kubernetes Pod or Job rather than on a developer laptop. |
| Multi-agent orchestration | Yes | Yes |
| Headless / CI mode | YesFlows started from the GitLab UI execute in GitLab CI/CD runners. | Yes |
| Models | ||
| Backbone | Anthropic Claude | via managed agents (Claude Code, Codex, Gemini, OpenCode, Cursor, custom agent images) |
| Bring your own model | YesOnly through the GitLab Duo Self-Hosted deployment on Self-Managed instances. | Yes |
| Local models | YesGitLab Self-Managed instances can run Duo against self-hosted models through a self-installed AI Gateway; GitLab.com uses GitLab-selected models. | No |
| Cost | ||
| Pricing model | seat | byok |
| Starts at | n/a | $0/mo |
| Free tier | No | Yes |
| Bring your own key | No | Yes |
| Openness | ||
| Open source | No | Yes |
| License | proprietary | Apache-2.0 |
| GitHub stars | n/a | 335 |
Which one would each critic pick
| Critic | GitLab Duo | Kelos | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.0 | 6.8 | GitLab Duo — Pick this if your issues, reviews and pipelines already live in GitLab; pick GitHub Copilot if they live somewhere else, because the value here is adjacency. |
| El Crítico | 6.5 | 6.0 | GitLab Duo — An agent with shell access and commit rights runs inside the system that holds the source, the pipelines and the deploy credentials, with no container boundary of its own. |
| El Profesor | 7.0 | 7.3 | Kelos — Task status records the branches, commits, pull requests and token usage a run produced, which turns the outcome of an agent into a queryable field rather than a screenshot. |
| La Inversora | 8.0 | 6.3 | GitLab Duo — Bundling the entry tier into Premium and Ultimate is an attach-rate play, not a product launch: the AI is defending the subscription, not selling itself. |
| La Jefa | 7.3 | 6.8 | GitLab Duo — The add-on seats are quoted rather than listed, and Agent Platform usage draws down purchased Credits, so sixty developers is one number I cannot compute in advance. |
| El Hacker | 4.8 | 7.8 | Kelos — Apache-2.0, an AgentConfig that carries my instructions, skills, plugins and MCP servers into every run, and a custom agent image when the supported ones are not what I want. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.