AgorvsRaven
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Agor
Preset · Agent harness
MCP
Panel
6.33 spec wins
- Reliability
- 5.8
- Usefulness
- 6.5
- Cost
- 7.2
- Longevity
- 5.5
“Multiplayer with live cursors, so your colleagues can now watch you argue with a robot in real time.”
Raven
EverMind AI · Agent harness
OSS
Panel
6.25 spec wins
- Reliability
- 5.3
- Usefulness
- 6.3
- Cost
- 8.0
- Longevity
- 5.2
“It has a Sentinel that sends you proactive nudges, so the agent now has opinions about your afternoon.”
Spec by spec
| Spec | Agor | Raven |
|---|---|---|
| Architecture | ||
| Category | Agent harness | Agent harness |
| Runs | local, sandbox | local, sandbox |
| Platforms | macos, linux, web | macos, linux, windows |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | Yes | No |
| MCP server | Yes | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | Yes | No |
| Browser control | No | YesDeep Research performs web search and page reading via MiroThinker and returns a cited report; there is no general browser-automation tool documented. |
| Sandboxed execution | YesExecution is configurable as trusted local, a fail-closed sandbox, or delegated to an external runner; Docker is one documented install path. | YesOnboarding asks for a sandbox or execution location, documented separately under docs/sandbox/usage.md. |
| Multi-agent orchestration | Yes | YesThe agent loop spawns subagents, and tracing records parent-child subagent runs. |
| Headless / CI mode | No | Yes |
| Models | ||
| Backbone | via managed agents (Claude Code, Codex, Gemini CLI, OpenCode, GitHub Copilot, Cursor) | OpenAI, Anthropic, Gemini, OpenRouter, DeepSeek, MiniMax, Moonshot, Groq, Azure OpenAI, GitHub Copilot (OAuth), Codex (OAuth), Ollama, vLLM |
| Bring your own model | YesAgor ships no model of its own; the model comes from whichever agent CLI or SDK the session is configured to use. | Yes |
| Local models | No | Yes |
| Cost | ||
| Pricing model | byok | byok |
| Starts at | $0/mo | $0/mo |
| Free tier | Yes | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | No | Yes |
| License | BSL-1.1 | Apache-2.0 |
| GitHub stars | 1,420 | 5,061 |
Which one would each critic pick
| Critic | Agor | Raven | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.3 | 6.5 | Raven — Pick it if you want an assistant that remembers last week; pick a plain terminal agent if you would rather start every session from a clean slate. |
| El Crítico | 5.8 | 5.8 | no preference |
| El Profesor | 6.8 | 6.3 | Agor — Sessions form an explicit genealogy: forking copies context forward, spawning a subsession starts a fresh window, and the distinction is a real design decision. |
| La Inversora | 6.3 | 6.0 | Agor — Business Source License 1.1 from a company whose actual product is elsewhere, which makes this a strategic side project with a licence designed to stop competitors hosting it. |
| La Jefa | 6.3 | 5.0 | Agor — Self-hosted with role-based access scoped to branches, which is a real access-control answer, and there is no unattended execution, so it never becomes a pipeline. |
| El Hacker | 6.3 | 7.8 | Raven — Apache-2.0, Ollama and vLLM among the supported providers, and tracing switched on by default but written to my own disk instead of a vendor's. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.