IOSM CLIvsoli
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
IOSM CLI
rokoss21 · Terminal agent
#241OSSMCP
Panel
5.23 spec wins
- Reliability
- 4.8
- Usefulness
- 5.2
- Cost
- 7.2
- Longevity
- 3.7
“Recent releases lead with configurable keybindings, which is one way to announce that the hard part is finished.”
oli
amrit110 · Terminal agent
#184OSS
Panel
5.42 spec wins
- Reliability
- 4.7
- Usefulness
- 4.8
- Cost
- 7.8
- Longevity
- 4.2
“The name stands for Open Local Intelligent assistant, an acronym that clearly had to work for it.”
Spec by spec
| Spec | IOSM CLI | oli |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local | local |
| Platforms | macos, linux, windows | macos, linux |
| 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 | No | No |
| Multi-agent orchestration | Yes | No |
| Headless / CI mode | No | No |
| Models | ||
| Backbone | multiple providers | Anthropic Claude, OpenAI, Google Gemini, Ollama |
| Bring your own model | Yes | Yes |
| Local models | No | YesOllama models with function calling, such as Qwen 2.5 Coder, are supported for full tool use. |
| 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 | Apache-2.0 |
| GitHub stars | 144 | 244 |
Which one would each critic pick
| Critic | IOSM CLI | oli | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 5.8 | 5.3 | IOSM CLI — Pick this if you want to grant permission a turn at a time rather than once at the start; pick Claude Code if you would rather approve less and read more diffs. |
| El Crítico | 5.0 | 5.0 | no preference |
| El Profesor | 5.0 | 6.3 | oli — The agent loop, tool execution and provider calls live in a compiled backend addressed over JSON-RPC, so the interface is a client rather than the program. |
| La Inversora | 4.5 | 4.8 | oli — 245 stars, a permissive licence, one author and no entity: this is a personal engineering exercise published openly, and it is priced accordingly at nothing. |
| La Jefa | 5.0 | 4.0 | IOSM CLI — No licence cost across sixty engineers, and the layered policy engine is the only artefact here I could put in front of a security reviewer without apologising. |
| El Hacker | 6.0 | 7.0 | oli — Apache-2.0, and local models with function calling are supported for full tool use rather than chat only, with Qwen 2.5 Coder named as one that actually works. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.