IBM BobvsKun
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
IBM Bob
IBM · AI-native IDE
#93MCP
Panel
5.72 spec wins
- Reliability
- 5.5
- Usefulness
- 5.7
- Cost
- 4.7
- Longevity
- 6.8
“It is metered in Bobcoins, so your refactor now has an exchange rate.”
Kun
KunAgent · AI-native IDE
#84MCP
Panel
5.86 spec wins
- Reliability
- 5.7
- Usefulness
- 6.2
- Cost
- 6.5
- Longevity
- 4.8
“It writes your code and also your slide deck, which is the most accurate description of an engineering week ever shipped as a feature list.”
Spec by spec
| Spec | IBM Bob | Kun |
|---|---|---|
| Architecture | ||
| Category | AI-native IDE | AI-native IDE |
| Runs | local | local |
| Platforms | macos, linux, windows | macos, linux, windows |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | Yes | Yes |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | No | Yes |
| Browser control | No | YesBrowser output is attached to tasks and screenshots are captured through browser automation. |
| Sandboxed execution | No | No |
| Multi-agent orchestration | YesBob spawns subagents that run in parallel, each in its own mode, with per-spawn approval. | No |
| Headless / CI mode | YesBob Shell is documented for task scripting and CI/CD pipeline integration. | No |
| Models | ||
| Backbone | multi-model routing | OpenAI, Claude, Gemini, Ollama, DeepSeek, Kimi, GLM, Qwen, MiniMax |
| Bring your own model | No | Yes |
| Local models | No | YesOllama ships as a named provider preset, and base URLs are editable so any OpenAI-compatible or Anthropic-compatible endpoint can be added. |
| Cost | ||
| Pricing model | subscription | byok |
| Starts at | $20/mo | n/a |
| Free tier | No | Yes |
| Bring your own key | No | Yes |
| Openness | ||
| Open source | No | No |
| License | proprietary | PolyForm-Noncommercial-1.0.0 |
| GitHub stars | n/a | 6,324 |
Which one would each critic pick
| Critic | IBM Bob | Kun | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 5.8 | 6.3 | Kun — Pick it if your week is half repository and half documents; pick Zed if the only thing you want an agent near is code. |
| El Crítico | 5.5 | 5.8 | Kun — Scheduled tasks, loops and background jobs run without you watching, and the row records no isolation for any of them. |
| El Profesor | 5.5 | 6.5 | Kun — The graphical client and the terminal client both attach to one local runtime, so threads, plans and approvals are shared state rather than two synchronised copies. |
| La Inversora | 7.0 | 5.0 | IBM Bob — This replaced watsonx Code Assistant, and the premium packages from $20 a month are the real business: the agent is the wrapper, modernisation is the product. |
| La Jefa | 6.5 | 4.8 | IBM Bob — Sixty developers is $1,200 a month on the entry plan and $12,000 on the top one, and the difference between them is an allowance nobody can forecast. |
| El Hacker | 3.8 | 6.5 | Kun — PolyForm Noncommercial, so I can read it and never ship a competing fork, but Ollama is a named preset and every base URL is editable. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.