EkovsLegion
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Eko
Fellou AI · Agent framework
OSSMCP
Panel
6.55 spec wins
- Reliability
- 6.0
- Usefulness
- 6.3
- Cost
- 7.3
- Longevity
- 6.2
“It can pause, resume and interrupt itself on demand, which is more self-control than most of its users manage.”
Legion
Software Mansion · Agent framework
OSS
Panel
6.52 spec wins
- Reliability
- 6.0
- Usefulness
- 6.2
- Cost
- 8.0
- Longevity
- 5.8
“It writes Lua to get work done in Elixir, which is two functional languages agreeing that a third one should take the blame.”
Spec by spec
| Spec | Eko | Legion |
|---|---|---|
| Architecture | ||
| Category | Agent framework | Agent framework |
| Runs | local | local |
| Platforms | macos, linux, windows, web | macos, linux |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | Yes | No |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | No | No |
| Multi-file edits | No | Yes |
| Git operations | No | No |
| Browser control | Yes | No |
| Sandboxed execution | No | YesLegion runs generated Lua or Elixir in its own sandbox; the README does not describe a container runtime. |
| Multi-agent orchestration | Yes | No |
| Headless / CI mode | No | No |
| Models | ||
| Backbone | Anthropic, OpenAI, Google, any OpenAI-compatible endpoint | multiple providers |
| Bring your own model | Yes | Yes |
| Local models | YesNot a documented local runtime, but any OpenAI-compatible server can be reached by setting a custom baseURL on the provider config. | 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 | 4,963 | 220 |
Which one would each critic pick
| Critic | Eko | Legion | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.8 | 6.8 | no preference |
| El Crítico | 6.0 | 6.0 | no preference |
| El Profesor | 6.3 | 7.8 | Legion — One evaluation can filter, branch and loop, so a sequence that costs a tool-calling agent a model round trip per step collapses into a single call. The claim is structural and checkable. |
| La Inversora | 5.8 | 6.3 | Legion — 166 stars and a consultancy's name on it. Software Mansion builds open libraries to sell engineering time, which funds this exactly as long as the pitch still works. |
| La Jefa | 6.0 | 5.5 | Eko — Free as a dependency across sixty engineers, TypeScript only, and nothing here runs unattended in a pipeline, so it lives inside an application we build and support. |
| El Hacker | 8.0 | 6.8 | Eko — MIT, one package install, native tool-server loading, and a custom base URL on the provider config so my own endpoint is just another model. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.