convez.ai
MCP ServerProdutividadeIntermediário
nathanramoscfa

RoadModel

nathanramoscfa/roadmodel

Recomenda qual modelo IA usar para cada tarefa com base em benchmarks

Ver no GitHub
BomPluginScore · de 0 a 100

MCP server que recomenda o modelo de IA, plataforma e configurações ideais para qualquer tarefa, baseado em benchmarks públicos e ratings por categoria. Funciona como CLI, servidor MCP e oferece um kit de planejamento para integrar recomendações de modelo em seus próprios projetos.

Instalação

$npx convez-ai nathanramoscfa/roadmodel

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
1
Acompanhando
0
Saúde
100%
Último commit
há 1 dia
Versão
v0.2.116
Issues abertas
37
Contribuidores
3

Casos de uso

  • Escolher entre Claude, GPT, Cursor ou outros modelos para uma tarefa específica
  • Otimizar custos selecionando o modelo mais eficiente para o trabalho
  • Integrar recomendações automáticas de modelos em fluxos de desenvolvimento

Veredito

Ferramenta prática e bem fundamentada para quem gerencia múltiplas subscrições de IA e precisa de decisões determinísticas sobre qual modelo usar. O suporte a MCP e o kit de planejamento exportável agregam flexibilidade real ao fluxo de desenvolvimento.

README

A tradução para o português deste README ainda está na fila.

roadmodel

A BYO-key command-line tool that recommends which AI model on which platform with which settings for a given prompt. Point it at a task description, and it returns a six-field block — MODEL / PLATFORM / MAX MODE / THINKING / CONVERSATION / RATIONALE — grounded in a bundled benchmark and pricing catalog (Cursor pricing, Artificial Analysis, LiveCodeBench, τ²-bench, SWE-bench, MMMU, LMArena) and filtered against your own subscriptions and API keys. Built for developers who use several AI subscriptions (Claude Code, Cursor, Codex / ChatGPT, raw provider APIs) and want a deterministic answer to "what should I use for this?" instead of guessing.

PyPI version Python versions License: Apache 2.0 CI Phase verify

Install

pip install roadmodel

Python 3.11 or newer.

MCP server

Install the MCP runtime with pip install "roadmodel[mcp]" to enable the roadmodel-mcp stdio server entrypoint; plain pip install roadmodel keeps the SDK optional and does not install mcp. The server exposes three tools — recommend_model, generate_phase_roadmap, and read_catalog — to any MCP-compatible client (Cursor, Claude Code, Claude Desktop, VS Code + Continue). Per-client registration walk-throughs live in docs/mcp-setup.md; tool signatures and return schemas are documented in docs/mcp-tools.md.

Planning kit ($0 marginal recommendations)

To author project/phase roadmaps with per-step model recommendations in another project, export the planning kit into it and let the AI already open in your editor (e.g. Claude Code on a flat plan) run the selector in its own context — no per-call API spend, just the editor session you already pay for.

Cross-platform (recommended). With roadmodel installed, one command writes the kit on Windows, macOS, or Linux — no shell or network needed:

cd /path/to/other-project
roadmodel export-kit            # writes ./planning with selector + cost-scale
                                # + templates + HOW-TO-USE + your user-context

It uses the catalog bundled in the installed wheel, so refresh with pip install -U roadmodel and re-run roadmodel export-kit at the start of each phase. Flags: --dest <subdir>, --force (overwrite an existing kit user-context.md), --user-context <path>.

Shell alternative (no install). A bash script fetches the kit fresh from this repo's main branch instead of from an installed wheel:

scripts/export-planning-kit.sh /path/to/other-project

Flags: --dest <subdir>, --ref <git-ref>, --local (copy from a local checkout instead of GitHub), --user-context <path>. On Windows PowerShell, call curl.exe (not the curl alias) if you fetch files by hand; the export-kit command above avoids that entirely.

Either way the in-editor AI runs the algorithm itself rather than calling the recommender service. Use the MCP server above instead when you want deterministic, structured recommendations in a script or CI.

Quickstart

Three steps from a fresh install to a parsed recommendation block.

1. Export an API key for any one of the three providers. Anthropic shown here; OpenAI and Google work the same way — see docs/byo-key-setup.md for the full guide.

export ANTHROPIC_API_KEY=sk-ant-...

2. Run roadmodel recommend once to bootstrap your user-context file. On the first invocation, the CLI writes a copy of the bundled template to ~/.config/roadmodel/user-context.md (or $XDG_CONFIG_HOME/roadmodel/user-context.md when XDG_CONFIG_HOME is set), prints a one-line stderr notice telling you what it did, and exits without calling the provider. Open the file and replace the $XXX and Yes/No placeholders with your actual subscription amounts and API-key state. The full field-by-field walk-through lives in docs/user-context-setup.md.

roadmodel recommend "Refactor auth middleware across 12 files"
# stderr: Created /home/you/.config/roadmodel/user-context.md from
#         bundled template. Edit it with your real subscription
#         state, then re-run.

$EDITOR ~/.config/roadmodel/user-context.md

3. Re-run. With the user-context filled in, the same command calls your chosen provider and prints a parsed six-field block:

roadmodel recommend "Refactor auth middleware across 12 files"
MODEL: claude-opus-4-7
PLATFORM: Claude Code
MAX MODE: On
THINKING: High
CONVERSATION: New
RATIONALE: Coding PRIMARY with cross-file scope and High complexity.
Opus 4.7 is S-tier on coding-agent benchmarks and the only model in
the catalog rated S for long-context recall. PLATFORM Claude Code
is funded by claude.ai Max ($0 marginal); THINKING High per the
selection-algorithm rule for High-complexity coding.

Pass --json to emit the same fields as machine-readable JSON, or --file PATH to read the prompt from disk.

BYO-key setup

roadmodel ships with no provider key built in — it calls your Anthropic / OpenAI / Google account on every recommendation and charges your account. Set any one of the three environment variables and the CLI auto-selects that provider:

ProviderEnv var
AnthropicANTHROPIC_API_KEY
OpenAIOPENAI_API_KEY
GoogleGOOGLE_API_KEY

The full guide — generating keys in each provider's console, storing them in a shell profile or ~/.config/roadmodel/config.toml, precedence rules, and verifying with a smoke call — is docs/byo-key-setup.md.

User context setup

roadmodel reads a per-user Markdown file describing your active subscriptions, API keys, platform preference order, and budget posture so the <access-selection> step can pick a platform and thinking level alongside the model. The resolved default path is ~/.config/roadmodel/user-context.md (or $XDG_CONFIG_HOME/roadmodel/user-context.md when XDG_CONFIG_HOME is set); override it for a single run with --user-context PATH or for a whole shell with ROADMODEL_USER_CONTEXT=PATH. The full walk-through — first-run bootstrap, full precedence chain, field-by-field schema, when to update — is docs/user-context-setup.md.

Subcommands

CommandWhat it does
roadmodel recommend PROMPTRecommend a six-field block for the given prompt.
roadmodel recommend --file PSame, but read the prompt text from file P.
roadmodel recommend --jsonEmit the parsed six fields as JSON instead of the labeled text block.
roadmodel recommend --providerOverride which provider answers (anthropic / openai / google).
roadmodel recommend --modelOverride the specific model ID on the chosen provider.
roadmodel recommend --user-context PATHOverride the user-context.md location for this invocation.
roadmodel catalog showPrint the bundled model-selector.txt (use --doc tier-cost-scale for the price doc).
roadmodel catalog pathPrint the on-disk path of the bundled catalog document (same --doc flag).
roadmodel context showPrint the resolved user-context.md file.
roadmodel context pathPrint the resolved user-context.md path (or the bootstrap target if missing).
roadmodel context initBootstrap user-context.md from the bundled template (--force to overwrite).
roadmodel versionPrint the installed version.

How it works

The CLI ships three documents as package data: model-selector.txt (the selection algorithm and the per-model access-methods catalog), model-tier-cost-scale.md (per-token prices and tier ratings), and user-context.example.md (the user-state template). At recommendation time, roadmodel recommend reads your filled-in user-context.md from disk, concatenates the three docs into a single system prompt, and calls the provider you configured. The provider returns a MODEL / PLATFORM / MAX MODE / THINKING / CONVERSATION / RATIONALE block following the <output-format> specification inside model-selector.txt. MODEL is chosen by <selection-algorithm> against your prompt's task category and complexity; PLATFORM and THINKING are filled by the <access-selection> step, which depends on the subscriptions and API-key state declared in your user-context.md.

Benchmarks & ratings

Each model carries a per-category capability rating on an S → D scale, and the recommender grounds its rationale in public benchmarks (SWE-bench Verified, τ²-bench, Terminal-Bench, Humanity's Last Exam, and more). See docs/benchmarks-and-ratings.md for what the scale means and a linked index of every benchmark the recommender cites — in the web app, each benchmark term in a recommendation's rationale links straight to its source.

Project status

roadmodel is in Phase 1 — the open-source CLI release. Phase 2 adds an MCP server alongside the CLI; later phases add a hosted SaaS at roadmodel.ai. The project was previously named model-selector and was renamed to roadmodel ahead of the public release; the canonical bundled-doc filename model-selector.txt is preserved so existing references in other projects keep working. Until v1.0.0, expect breaking changes to the CLI surface as Phase 2 lands.

See ROADMAP.md for the phase plan and shipping order.

Contributing

See CONTRIBUTING.md for branch naming, pull request scope, the catalog-edit process, and the Code of Conduct that applies in community spaces. Report security issues privately per SECURITY.md.

License

Licensed under the Apache License, Version 2.0. Bundled third-party attributions are listed in NOTICE.

Ver o original no GitHub

Bom para

Relacionados