ContrabassvsOpenClaw.NET
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Contrabass
junhoyeo · Agent harness
OSSMCP
Panel
7.12 spec wins
- Reliability
- 6.8
- Usefulness
- 7.3
- Cost
- 8.2
- Longevity
- 6.0
“Every issue gets a worktree under workspaces/ named after the ticket, so your filesystem is now a faithful copy of your backlog.”
OpenClaw.NET
clawdotnet · Agent harness
OSSMCP
Panel
7.04 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 | Contrabass | 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 | Yes | Yes |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | YesFiles are changed by the agent runner Contrabass launches in each issue's worktree. | 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 | YesA --no-tui flag runs the orchestrator headless with events logged to stdout. | YesSetup and the harness regression suite run non-interactively via "openclaw setup --non-interactive" and "openclaw harness test". |
| Models | ||
| Backbone | Codex app-server, OpenCode, oh-my-opencode, OMX, OMC | 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 | 223 | 517 |
Which one would each critic pick
| Critic | Contrabass | OpenClaw.NET | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.5 | 7.3 | Contrabass — Pick it when your backlog already lives in a tracker and you want it drained; pick a session manager when you would rather choose each task yourself. |
| El Crítico | 6.8 | 6.5 | Contrabass — Stall detection and orphan recovery supervise five external agent runners, so liveness is inferred from processes this project does not control. |
| El Profesor | 7.5 | 7.0 | Contrabass — Teams mode separates plan, exec and verify into phases with branch advance verification and deterministic retry backoff, which is a pipeline rather than a loop. |
| La Inversora | 6.5 | 6.3 | Contrabass — 220 stars for a careful reimplementation of a model vendor's internal tool: excellent engineering, and a position that exists at somebody else's discretion. |
| La Jefa | 6.3 | 6.5 | OpenClaw.NET — An admin interface and a non-interactive setup command are two things I can operate; there is still no SSO, no SCIM and no audit log across sixty installations. |
| El Hacker | 8.0 | 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.