MultivsSRD CodeFree
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Multi
Patika Labs · IDE extension
#30
Panel
6.34 spec wins
- Reliability
- 5.5
- Usefulness
- 7.2
- Cost
- 7.5
- Longevity
- 5.0
“It installs into VS Code, JetBrains, Cursor, Windsurf, Kiro and Antigravity, which is one agent covering six answers to the same question.”
SRD CodeFree
China Telecom Research Institute · IDE extension
#106MCP
Panel
6.12 spec wins
- Reliability
- 6.3
- Usefulness
- 6.2
- Cost
- 5.2
- Longevity
- 6.7
“It ships prepackaged digital employees called /frontend-dev and /backend-dev, which is the org chart arriving as slash commands.”
Spec by spec
| Spec | Multi | SRD CodeFree |
|---|---|---|
| Architecture | ||
| Category | IDE extension | IDE extension |
| Runs | local | local |
| Platforms | macos, linux, windows | macos, linux, windows |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | Yes |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | YesApproval modes explicitly govern permission for file editing and shell command execution, with a whitelist for automatic execution. |
| Multi-file edits | Yes | Yes |
| Git operations | No | YesThe CodeReview skill works over pull and merge requests, a single commit or a commit range; the listing does not describe the agent committing on your behalf. |
| Browser control | No | No |
| Sandboxed execution | No | No |
| Multi-agent orchestration | YesMulti runs tasks in the background so several workstreams proceed at once and describes itself as a team of agents, but it documents no supervisor that coordinates them. | Yes |
| Headless / CI mode | No | No |
| Models | ||
| Backbone | Claude Code, Gemini CLI, GitHub Copilot, Anthropic, OpenAI, Google Gemini, OpenRouter, Ollama | GLM-5.1, Qwen3.5, SrdCoder V5, SrdNES V4 |
| Bring your own model | Yes | No |
| Local models | YesOllama is one of the supported providers, so local models are reachable through a profile. | No |
| Cost | ||
| Pricing model | byok | mixed |
| Starts at | $0/mo | n/a |
| Free tier | Yes | No |
| Bring your own key | Yes | No |
| Openness | ||
| Open source | No | No |
| License | proprietary | proprietary |
| GitHub stars | n/a | n/a |
Which one would each critic pick
| Critic | Multi | SRD CodeFree | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.3 | 6.5 | Multi — Pick Multi if you want a capable agent in the editor you already opened and refuse to sign up for anything; pick Zoo Code if you would rather the source were readable. |
| El Crítico | 6.3 | 6.0 | Multi — Auto-approval is granted per category, so approving shell execution once approves every command in the class rather than the command in front of you. |
| El Profesor | 6.5 | 7.0 | SRD CodeFree — CodeAudit runs taint-tracking security analysis and code search is backed by a language server, so two of the inputs are deterministic analyses rather than the model's impression. |
| La Inversora | 6.0 | 6.8 | SRD CodeFree — The owner is a state telecom research institute and this ships with its DevOps platform, so the assistant is a retention feature for the platform rather than a product with a margin. |
| La Jefa | 5.0 | 5.8 | SRD CodeFree — It installs free from both marketplaces and then needs an SRDCloud account whose terms are not published outside China, so my sixty seats have no contract I could read. |
| El Hacker | 6.8 | 4.5 | Multi — Closed source, and it takes 27 providers and over a hundred models, including Copilot, Claude Code and Gemini CLI subscriptions that need no separate key, plus Ollama. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.