convez.ai
MCP ServerMarketing & VendasIntermediário
cognis-digital

PactGen

cognis-digital/pactgen

Gere propostas comerciais brandizadas com validação automática de cálculos

Ver no GitHub
BomPluginScore · de 0 a 100

MCP server que gera propostas de vendas e SOWs (Statement of Work) formatadas em PDF/HTML a partir de arquivos YAML com escopo e tabela de preços. Valida determinísticamente a matemática de itens de linha para evitar erros de cálculo.

Instalação

$npx convez-ai cognis-digital/pactgen

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
0
Forks
0
Acompanhando
0
Saúde
100%
Último commit
há 4 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Gerar propostas comerciais automáticas a partir de templates YAML
  • Validar cálculos de preços e totais em propostas antes do envio
  • Manter propostas versionáveis em git com builds reproduzíveis

Veredito

Ferramenta sólida para automatizar geração de propostas comerciais com garantia de acurácia matemática. Ideal para equipes que precisam escalar processos de vendas mantendo controle de versão e reprodutibilidade.

README

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

PACTGEN

Generate branded sales proposals and SOWs from a YAML scope file + pricing table into PDF/HTML, with a deterministic line-item math check.

PyPI CI License: COCL 1.0 Suite

Part of the Cognis Neural Suite.

pip install cognis-pactgen
pactgen scan .            # → prioritized findings in seconds

Contents

Why pactgen?

Proposals diffable in git with reproducible builds — the same scope file always renders the same dollar total, so no more copy-paste pricing errors slipping to a client.

pactgen is single-purpose, scriptable, and self-hostable: point it at a target, get prioritized results in the format your workflow already speaks (table · JSON · SARIF), gate CI on it, and let agents drive it over MCP.

Features

  • ✅ Parse Yaml
  • ✅ Parse Proposal
  • ✅ Parse Proposal File
  • ✅ Compute Totals
  • ✅ Check Math
  • ✅ Proposal To Dict
  • ✅ Render Html
  • ✅ Runs on Linux/macOS/Windows · Docker · devcontainer
  • ✅ Ports in Python, JavaScript, Go, and Rust (ports/)

Quick start

pip install cognis-pactgen
pactgen --version
pactgen scan .                       # scan current project
pactgen scan . --format json         # machine-readable
pactgen scan . --fail-on high        # CI gate (non-zero exit)

Example

$ pactgen scan .
  [HIGH    ] PAC-001  example finding             (./src/app.py)
  [MEDIUM  ] PAC-002  another signal              (./config.yaml)

  2 findings · risk score 5 · 38ms

Architecture

flowchart LR
  A[Input: file / dir / API] --> B[Collectors]
  B --> C[Rules / Analyzers]
  C --> D[Scorer]
  D --> E{Reporters}
  E --> F[Table]
  E --> G[JSON / SARIF]
  E --> H[MCP tool -. drives .-> AI agents]

Use it from any AI stack

pactgen is interoperable with every popular way of using AI:

  • MCP server — pactgen mcp (Claude Desktop, Cursor, Cognis.Studio, uncensored-fleet)
  • OpenAI-compatible / JSON — pipe pactgen scan . --format json into any agent or LLM
  • LangChain · CrewAI · AutoGen · LlamaIndex — wrap the CLI/JSON as a tool in one line
  • CI / scripts — exit codes + SARIF for non-AI pipelines

How it compares

Cognis pactgenPandoc + Typst, echoing PandaDoc
Self-hostable, no account✅varies
Single command, zero config✅⚠️
JSON + SARIF for CI✅varies
MCP-native (AI agents)✅❌
Polyglot ports (JS/Go/Rust)✅❌
Open license✅ COCLvaries

Built in the spirit of Pandoc + Typst, echoing PandaDoc/Proposify, re-framed the Cognis way. Missing a credit? Open a PR.

Integrations

Pipes into your stack: SARIF for code-scanning, JSON for anything, an MCP server (pactgen mcp) for AI agents, and a webhook forwarder for SIEM/Slack/Jira. See docs/INTEGRATIONS.md.

Install — every way, every platform

pip install "git+https://github.com/cognis-digital/pactgen.git"    # pip (works today)
pipx install "git+https://github.com/cognis-digital/pactgen.git"   # isolated CLI
uv tool install "git+https://github.com/cognis-digital/pactgen.git" # uv
pip install cognis-pactgen                                          # PyPI (when published)
docker run --rm ghcr.io/cognis-digital/pactgen:latest --help        # Docker
brew install cognis-digital/tap/pactgen                             # Homebrew tap
curl -fsSL https://raw.githubusercontent.com/cognis-digital/pactgen/main/install.sh | sh
LinuxmacOSWindowsDockerCloud
scripts/setup-linux.shscripts/setup-macos.shscripts/setup-windows.ps1docker run ghcr.io/cognis-digital/pactgenDEPLOY.md (AWS/Azure/GCP/k8s)

Related Cognis tools

  • warmline — Score and rank inbound/outbound leads from a YAML rulebook, emitting a ranked queue as JSON/CSV for your SDRs and CI gates.
  • coldforge — Render personalized cold-outreach sequences from Markdown templates + a contacts CSV, with spam-score linting and per-send dry-run preview.
  • crmsync — Bidirectional, idempotent sync of contacts/deals between a local SQLite source-of-truth and CRM APIs (HubSpot/Pipedrive/Salesforce) via one config.
  • dripcheck — Lint email sequences and drip campaigns for deliverability: SPF/DKIM/DMARC, link health, unsubscribe presence, and CAN-SPAM/GDPR compliance.
  • dealflow — Model your sales pipeline as a YAML state machine and compute conversion rates, stage velocity, and weighted forecast straight from CRM exports.
  • introbot — Find warm-intro paths through your team's combined network graph and draft double-opt-in intro requests from a single contacts manifest.

Explore the suite → 🗂️ all 170+ tools · ⭐ awesome-cognis · 🔗 cognis-sources · 🤖 uncensored-fleet · 🧠 hermes

Contributing

PRs, new rules, and demo scenarios are welcome under the collaboration-pull model — see CONTRIBUTING.md and SECURITY.md.

⭐ If pactgen saved you time, star it — it genuinely helps others find it.

License

Source-available under the Cognis Open Collaboration License (COCL) v1.0 — free for personal, internal-evaluation, research, and educational use; commercial / production use requires a license (licensing@cognis.digital). See LICENSE.


Ver o original no GitHub

Bom para

Relacionados