dirivsOpenClaw.NET
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
diri
cristicretu · Agent harness
OSS
Panel
6.92 spec wins
- Reliability
- 6.8
- Usefulness
- 6.5
- Cost
- 8.3
- Longevity
- 5.8
“It runs plain shells beside the agents, so a human and four robots can now miss the same deadline in parallel.”
OpenClaw.NET
clawdotnet · Agent harness
OSSMCP
Panel
7.06 spec wins
- Reliability
- 6.5
- Usefulness
- 6.8
- Cost
- 8.3
- Longevity
- 6.2
“It states clearly that it is not affiliated with the project whose name it borrowed, which is a great deal of effort spent on a name.”
Spec by spec
| Spec | diri | OpenClaw.NET |
|---|---|---|
| Architecture | ||
| Category | Agent harness | Agent harness |
| Runs | local | local |
| Platforms | macos, linux | macos, linux, windows |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | Yes |
| MCP server | No | Yes |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | YesEdits come from the agent running in the session; diri supplies the worktree, the status and the persistence. | Yes |
| Git operations | Yes | No |
| Browser control | No | YesOutbound web fetches and browser navigations run through a URL-safety policy that blocks loopback and private hosts by default. |
| Sandboxed execution | No | No |
| Multi-agent orchestration | Yes | No |
| Headless / CI mode | No | YesSetup and the harness regression suite run non-interactively via "openclaw setup --non-interactive" and "openclaw harness test". |
| Models | ||
| Backbone | Claude Code, Codex, Cursor, Gemini | OpenAI, Claude, Gemini, Azure OpenAI, DeepSeek, Ollama, OpenAI-compatible |
| Bring your own model | Yes | Yes |
| Local models | No | YesOllama is a first-class native provider, and an embedded mode runs an OpenClaw-managed local model such as Gemma 4 GGUF through a supervised sidecar. |
| 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 | MIT |
| GitHub stars | 351 | 517 |
Which one would each critic pick
| Critic | diri | OpenClaw.NET | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.3 | 7.3 | no preference |
| El Crítico | 6.8 | 6.5 | diri — Sessions run on remote hosts as well as locally, and nothing documented describes what a remote run does when the link drops mid-task. |
| El Profesor | 7.3 | 7.0 | diri — Session state lives in a daemon rather than in the user interface: closing the app does not end a run, and restarting the daemon restores the conversations. |
| La Inversora | 6.0 | 6.3 | OpenClaw.NET — 492 stars for an independent reimplementation of another project in another language: the positioning is derivative, and the ecosystem it serves is underserved. |
| La Jefa | 7.0 | 6.5 | diri — A signed and notarized universal build delivered through a self-updating Homebrew cask is the first distribution story on this shelf I could hand to sixty people unchanged. |
| El Hacker | 7.0 | 8.3 | OpenClaw.NET — MIT, MCP in both directions, Ollama as a native provider and an embedded mode that supervises a local GGUF model in a sidecar it manages itself. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.