kiessclaw 1.6.0

Autonomous AI SEO + Sales Agent System built on OpenClaw

⚡ KiessClaw

Autonomous AI SDR + SEO agent OS. Import leads, score them, enroll them, stop when they reply. Zero manual steps.

pip install kiessclaw
kiessclaw import csv leads.csv --icp-min 60 --auto-enroll

That imports your leads, scores them with ICP rules, and enrolls the qualified ones in a multi-step outreach sequence. Replies stop the sequence. Automatically.

---

What is KIESSCLAW?

KIESSCLAW is an all-in-one CLI for generating agent/pipeline/workflow scaffolds and prompt packs.
It ships with opinionated use cases and strict templates so teams can go from idea to runnable project structure in minutes.

Built by Erwin Kiess-Alfonso as part of the KLYTICS open-source ecosystem.

---

Why this exists

• Apollo is expensive and closed. This is free and forkable.
• Most outreach tools are GUIs. This is a CLI designed for scripts, pipes, and CI/CD.
• AI personalization should be configurable, not locked to one vendor.

Non-goals

• Not a replacement for your CRM.
• Not a no-code tool.
• Not production-ready for regulated industries without review.

---

The Agent Team

Agent	Codename	Role	Model
KiessProspector	KPRO	Lead import, enrichment, ICP scoring	gpt-4o
KiessSequencer	KSEQ	Sequence orchestration, scheduling, safety	gpt-4o-mini
KiessPen	KPEN	Personalization, first lines, templates	gpt-4o
KiessInbox	KINB	Reply classification, qualification, DNC	gpt-4o
KiessMetrics	KMET	Analytics, deliverability, reporting	gpt-4o-mini
KiessCrawler	KRAWL	Technical SEO crawl, score, and issues	gpt-4o
KiessAnalyst	KANA	Keyword + SERP + competitor gap analysis	gpt-4o
KiessWriter	KWRI	SEO briefs + metadata generation	gpt-4o-mini
KiessScout	KSCO	Backlink prospecting + link gap targeting	gpt-4o-mini
KiessReporter	KREP	Weekly SEO reporting	gpt-4o-mini

All agents share one workspace brain — a markdown-based memory system where context persists, logs are written, and data is stored.

---

Features

• Use Case Registry — 6 built-in workflows (outreach_sdr, seo_audit_to_leads, github_oss_launch, etc.)
• Prompt Factory — Render deterministic system, task, guardrails, and checklist prompts
• Prompt Linting — Detect unresolved placeholders, vague instructions, and missing success criteria
• Code Scaffolding — Generate agent/skill/workflow/test/docs skeletons safely
• No-Overwrite Safety — Files are never replaced unless --force is explicitly passed
• Doctor Command — Config/workspace/dependency diagnostics with quick fixes
• Existing SDR + SEO Engine — Operational agents and API still available for runtime workflows

---

Quick Start

Prerequisites

• Python 3.10+
• An OpenAI API key (or Anthropic/Ollama)

Install

pip install kiessclaw
pip install kiessclaw[all]   # includes anthropic + slack

# Or install from source
git clone https://github.com/monykiss/kiessclaw.git
cd kiessclaw
pip install -e .

# Copy and configure environment
cp .env.example .env
nano .env  # Add your API keys

# Initialize workspace
python scripts/init_workspace.py

# Check status
python -m kiessclaw status

Docker

docker-compose up
# API live at http://localhost:8000
# Docs at http://localhost:8000/docs

Quick Start (Generator Wedge)

# 1) List built-in use cases
kiessclaw usecase list

# 2) Generate a full SDR prompt pack
kiessclaw prompt pack outreach_sdr --json-input examples/outreach_sdr.json --out prompts.json --deterministic

# 3) Scaffold a runnable use case folder
kiessclaw scaffold usecase outreach_sdr --json-input examples/outreach_sdr.json --outdir ./generated --force

# 4) Run workflow simulation
kiessclaw workflow run outreach_sdr --json-input examples/outreach_sdr.json --dry-run

# 5) Check providers
kiessclaw providers list
kiessclaw providers health

# 6) Test Slack integration (optional)
kiessclaw integrations slack test

# 7) Add a scheduled workflow run (optional)
kiessclaw schedule add --usecase outreach_sdr --cron "0 9 * * 1-5" --json-input examples/outreach_sdr.json --dry-run

# 8) Run health diagnostics
kiessclaw doctor

Slack Notifications

Set SLACK_WEBHOOK_URL in .env, then:

kiessclaw integrations slack test

Scheduled Runs

kiessclaw schedule add \
  --usecase outreach_sdr \
  --cron "0 9 * * 1-5" \
  --json-input examples/outreach_sdr.json \
  --dry-run

kiessclaw schedule list
kiessclaw schedule run <job_id>
kiessclaw schedule remove <job_id>

---

Project Structure

kiessclaw/
├── kiessclaw/
│   ├── core/           # Agent runtime, memory engine, LLM router
│   ├── agents/         # Individual agent implementations
│   ├── skills/         # Modular skill modules
│   ├── models/         # Data models (Contact, Sequence, etc.)
│   ├── usecases/       # Use case schemas and registry
│   ├── prompting/      # Prompt factory + linting
│   ├── codegen/        # Safe scaffold generator + templates
│   ├── seo/            # SEO agents + crawl skills
│   ├── pipeline.py     # Autonomous SEO -> SDR routing
│   ├── interfaces/     # CLI and Slack interfaces
│   └── utils/          # Helpers and utilities
├── config/
│   ├── config.yaml     # Global settings & model assignments
│   └── agents/         # Per-agent directive files (AgentMD)
├── workspace/
│   ├── data/           # JSON data storage
│   ├── memory/         # Persistent agent memory
│   ├── reports/        # Generated reports
│   └── logs/           # Activity logs
├── docs/               # Documentation
├── ROADMAP.md          # Release roadmap milestones
└── scripts/            # Setup and utility scripts

---

CLI Commands

Command	Description
kiessclaw status	Show agent status and data summary
kiessclaw usecase list	List built-in generator use cases
kiessclaw usecase show <id>	Show one use case schema
kiessclaw prompt render <id> --template ... --json-input ...	Render one prompt template
kiessclaw prompt pack <id> --json-input ... --out ...	Render all prompt templates into one pack
kiessclaw scaffold usecase <id> --json-input ... --outdir ...	Generate use case scaffold files
kiessclaw scaffold agent <Name> --outdir ...	Generate standalone agent scaffold + test
kiessclaw scaffold workflow <Name> --outdir ...	Generate standalone workflow scaffold + test
kiessclaw scaffold skill <Name> --outdir ...	Generate standalone skill scaffold + test
kiessclaw scaffold tests <Kind> --outdir ...	Generate standalone test stub
kiessclaw workflow run <id> --json-input ... --dry-run	Execute a use case workflow end-to-end
kiessclaw integrations slack test	Send a Slack test notification if configured
kiessclaw schedule add --usecase ... --cron ... --json-input ...	Persist a scheduled workflow job
kiessclaw schedule list	List scheduled jobs
kiessclaw schedule run <job_id>	Execute one scheduled job immediately
kiessclaw schedule remove <job_id>	Remove one scheduled job
kiessclaw providers list	Show registered providers and active provider by kind
kiessclaw providers health	Run active provider health checks
kiessclaw doctor	Check config/workspace/dependencies and show quick fixes
kiessclaw import --file X	Import contacts from CSV
kiessclaw contact add ...	Add one contact directly from CLI
kiessclaw sequence create --name X	Create a new sequence
kiessclaw sequence add-step --id X ...	Add sequence step content
kiessclaw enroll <contact> <sequence>	Enroll a contact into a sequence
kiessclaw run --dry-run	Simulate send + inbox cycle with no state mutation
kiessclaw run	Execute one operational cycle
kiessclaw inbox process	Process unclassified replies
kiessclaw reply --contact-id X --text "..."	Simulate inbound reply
kiessclaw analytics	Show pipeline + deliverability summary
kiessclaw pipeline	Show prospect pipeline
kiessclaw report	Generate weekly report
kiessclaw analyze	AI-powered performance analysis
kiessclaw audit --url URL --auto-enroll	Run SEO audit and optionally route low-score domains
kiessclaw serve --port 8000	Start FastAPI service layer
kiessclaw chat	Interactive agent chat

---

Configuration

Edit config/config.yaml:

llm:
  provider: openai          # openai | anthropic | ollama
  default_model: gpt-4o
  api_key: ${OPENAI_API_KEY}

agents:
  KPRO:
    model: gpt-4o
    settings:
      min_icp_score: 60
  KSEQ:
    model: gpt-4o-mini
    settings:
      max_daily_sends: 200
      sending_window_start: "08:00"
      sending_window_end: "18:00"

email:
  provider: smtp
  smtp:
    host: ${SMTP_HOST}
    port: 587
    username: ${SMTP_USERNAME}
    password: ${SMTP_PASSWORD}

safety:
  max_sends_per_day: 500
  bounce_rate_threshold: 0.05

---

Built-in Skills

Skill	Description
prospect	CSV import, email validation, ICP scoring
sequence	Sequence CRUD, enrollment, scheduling
email	SMTP sending, tracking, deliverability
personalization	Template rendering, first-line generation
inbox	Reply classification, DNC management
analytics	Funnel metrics, reports, analysis
crawl	Technical crawl, metadata, broken links, robots/sitemap checks

---

Documentation

• Quick Start Guide
• Use Cases
• Architecture Overview
• Product Specification
• Roadmap
• Release Roadmap
• Changelog

API Endpoints

• GET /health
• GET /version
• GET /usecases
• GET /usecases/{id}
• POST /providers/health
• POST /prompt/render
• POST /scaffold/usecase
• POST /workflow/run
• GET /schedule
• POST /schedule
• DELETE /schedule/{job_id}
• POST /schedule/{job_id}/run
• POST /audit
• POST /contacts
• GET /contacts
• POST /sequences/{id}/enroll
• GET /pipeline
• POST /reply
• GET /inbox
• GET /analytics
• GET /sequences
• POST /sequences
• POST /waitlist
• GET /waitlist/count

---

Contributing

Contributions are welcome! KIESSCLAW is designed to grow through community extensions.

See CONTRIBUTING.md for guidelines.

---

License

MIT License — see LICENSE for details.

---

Author

Erwin Kiess-Alfonso Founder & CEO, KLYTICS · Data & AI Performance Consultancy San Juan, Puerto Rico

---

KIESSCLAW is part of the KLYTICS open-source ecosystem.