ArgusBotvsWizard
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
ArgusBot
waltstephen · Agent harness
OSS
Panel
5.73 spec wins
- Reliability
- 5.2
- Usefulness
- 5.7
- Cost
- 7.0
- Longevity
- 5.0
“It ships a stall watchdog that restarts the agent, the most honest feature name anyone in this category has published.”
Wizard
teddytennant · Agent harness
OSS
Panel
5.71 spec wins
- Reliability
- 5.0
- Usefulness
- 5.5
- Cost
- 7.3
- Longevity
- 4.8
“It calls itself a sovereign agent, which is a great deal of constitutional language for a binary living in your home directory.”
Spec by spec
| Spec | ArgusBot | Wizard |
|---|---|---|
| Architecture | ||
| Category | Agent harness | Agent harness |
| Runs | local | local |
| Platforms | macos, linux | macos, linux |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | No |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | YesFiles are changed by the Codex or Claude Code backend ArgusBot supervises, not by ArgusBot itself. | Yes |
| Git operations | No | No |
| Browser control | No | No |
| Sandboxed execution | No | No |
| Multi-agent orchestration | YesA reviewer sub-agent and a planner sub-agent run alongside the main agent to gate completion and maintain the plan. | No |
| Headless / CI mode | YesRuns can be started and steered without a terminal through a daemon controlled from Telegram or Feishu; there is no dedicated CI integration. | No |
| Models | ||
| Backbone | Codex CLI, Claude Code CLI | xAI, OpenAI, Anthropic, Gemini, DeepSeek, Groq, OpenRouter, llama.cpp |
| Bring your own model | Yes | 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 | Yes | Yes |
| License | MIT | Apache-2.0 |
| GitHub stars | 317 | 105 |
Which one would each critic pick
| Critic | ArgusBot | Wizard | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.3 | 6.0 | ArgusBot — Pick ArgusBot when your tasks have a test that says done; pick a plain agent session when done is a judgement call you would rather make yourself. |
| El Crítico | 5.3 | 4.8 | ArgusBot — Runs launched from the daemon use the permissive execution flag by default, and the README itself flags that as a security risk on untrusted workspaces. |
| El Profesor | 5.8 | 6.3 | Wizard — Memory is stored as markdown and sessions as line-delimited records, which makes the accumulated context a document a person can read and correct. |
| La Inversora | 5.5 | 5.0 | ArgusBot — MIT, one maintainer, 316 stars and no entity: this is a workflow opinion published as software, and workflow opinions do not have cap tables. |
| La Jefa | 4.8 | 4.0 | ArgusBot — Nothing to buy for sixty seats, and no way to govern them: the control surface is a Telegram or Feishu chat with slash commands and no directory behind it. |
| El Hacker | 6.8 | 8.0 | Wizard — Apache-2.0, and choosing Local on first run has it size a Qwen 3 build to my hardware and start llama.cpp itself, with no key and no account anywhere. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.