Molten Hub Code
Molten-Bot/moltenhub-code
Agent IA para executar tarefas de código em repos GitHub e gerar PRs
Ver no GitHubAgent de IA para desenvolvimento rápido que executa tarefas de codificação contra repositórios GitHub e gera pull requests automaticamente. Integrado com Claude e Codex, oferece interface web com suporte a ditado por voz e análise de código.
Instalação
npx convez-ai Molten-Bot/moltenhub-code1 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
Casos de uso
- Automatizar mudanças de código em repositórios via agentes IA
- Gerar pull requests a partir de prompts em linguagem natural
- Revisar código automaticamente quando solicitado como reviewer
- Manter guardrails e diretrizes de projeto com Railsmith
Veredito

Ferramenta robusta para automatizar fluxos de desenvolvimento com agents de IA atuando diretamente em repositórios GitHub. Exige configuração técnica substancial (Go 1.26+, Docker, tokens de auth) e é mais adequada para times de engenharia estabelecidos que buscam acelerar mudanças de código em escala.
README
A tradução para o português deste README ainda está na fila.
Molten Hub Code
The highest velocity way to make code changes. Run AI coding agents against GitHub repositories, prompt to PR. Product details live at molten.bot/code.
Quick Start
Docker
docker run -p 7777:7777 moltenai/moltenhub-code
Docker Compose with Prompt Dictation
cp .env.example .env
docker compose up
For a local image build instead of the published Docker Hub image:
docker compose -f docker-compose.yml -f docker-compose.local.yml up --build
The Compose stack runs moltenhub-code with a linuxserver/faster-whisper
sidecar. The web UI probes faster-whisper:10300; when it is reachable, the
Prompt Studio shows a microphone button that appends dictated text to the
prompt field. The Compose sidecar disables Docker log capture because
wyoming-faster-whisper logs transcript text at INFO level.
The bundled sidecar defaults to the base-int8 model and English language
hints for more reliable short-form dictation; set both WHISPER_LANG=auto and
MOLTEN_HUB_SPEECH_LANGUAGE=auto to use Whisper language detection.
Local Build
Requires Go 1.26.2 or newer plus git, gh, and the selected agent CLI.
go build -o bin/harness ./cmd/harness
./bin/harness hub
Local harness hub listens on 127.0.0.1:7777 by default.
With GitHub auth configured, local hub mode also watches GitHub review-request
notifications by default. When the authenticated GitHub user is still requested
as a PR reviewer, the harness queues the bundled code-review task and posts a
summary comment back to the original PR. Auto-merge is off by default; opt in
with review_watch.auto_merge: true in the runtime config.
Go Module
MoltenHub Code is distributed as a Go module from this Git repository. Use a
Git tag such as v1.0.0 for stable installs.
go get github.com/Molten-Bot/moltenhub-code@v1.0.0
go install github.com/Molten-Bot/moltenhub-code/cmd/harness@v1.0.0
Bundled Tools
The Docker image includes railsmith, an npm CLI for creating and maintaining
repository AGENTS.md guardrails. Container startup also seeds a Codex skill
from the package's AGENT_GUIDE.md into the persisted Codex home so agents can
activate Railsmith guidance during coding sessions.
railsmith guide
railsmith doctor --root .
railsmith diff --root . --mode detailed
railsmith check --root .
The image also includes git-changes-by-day, a Go CLI for exporting git
history to CSV. Agents can use it when a task needs per-commit change data.
git-changes-by-day -repo /path/to/repo -text-out /tmp/commit-text.csv
The CSV includes UTC datetime/date columns, commit metadata, changed file counts, and line change counts.
Environment Variables
Useful environment variables:
GITHUB_TOKENorGH_TOKEN: GitHub auth for clone, push, PRs, and checks.MOLTEN_HUB_TOKEN: remote Hub agent token.MOLTEN_HUB_REGION:naoreu; defaults tona.MOLTEN_HUB_URL: explicit hosted Hub API URL,https://na.hub.molten.bot/v1orhttps://eu.hub.molten.bot/v1.MOLTEN_HUB_SESSION_KEY: runtime config session key; defaults tomain.HARNESS_AGENT_HARNESS: default agent harness.HARNESS_AGENT_COMMAND: default agent executable.OPENAI_API_KEY: Codex login bootstrap.MOLTEN_HUB_DEFAULT_REPOSITORY: optional repository prefill for Prompt Studio; omitted leaves the repository field empty.MOLTEN_HUB_SPEECH_HOST: optional speech sidecar host; defaults tofaster-whisper.MOLTEN_HUB_SPEECH_PORT: optional speech sidecar Wyoming port; defaults to10300.MOLTEN_HUB_SPEECH_LANGUAGE: optional speech language hint; defaults toen. Set toautoto use Whisper language detection.MOLTEN_HUB_SPEECH_DISABLED: set totrueto hide prompt dictation.
Response Modes
Supported responseMode values:
defaultoffcaveman-litecaveman-fullcaveman-ultracaveman-wenyan-litecaveman-wenyan-fullcaveman-wenyan-ultra
Omitted or default maps to caveman-full. The harness prepends the bundled
Caveman skill to the agent prompt unless
responseMode is off.
Development
go test ./...