Business Operations — run the company without a SaaS bill for every function.
pip install cognis-leadforge
leadforge scan . # → prioritized findings in secondsReal, reproducible output from the tool — runs offline:
$ leadforge-emit --version
leadforge 1.0.0$ leadforge-emit --help
usage: leadforge [-h] [--version] [--format {table,json}] [--db DB]
{add,list,move,enroll,due,send,pipeline} ...
MCP-native CRM pipeline with email sequences
positional arguments:
{add,list,move,enroll,due,send,pipeline}
add add a lead
list list leads
move move a lead to a stage
enroll enroll a lead in an email sequence
due show sequence steps that are due now
send mark all due steps as sent and advance them
pipeline pipeline summary metrics
options:
-h, --help show this help message and exit
--version show program's version number and exit
--format {table,json}
--db DB path to JSON store (or env LEADFORGE_DB)Blocks above are real
leadforgeoutput — reproduce them from a clone.
Sample result format (illustrative values — run on your own data for real findings):
{
"findings": [
{
"id": "1234567890",
"title": "Suspicious Network Activity",
"description": "Potential malicious activity detected on network 192.168.1.100",
"created_at": "2023-02-15T14:30:00Z",
"updated_at": "2023-02-15T14:30:01Z",
"labels": ["Network", "Malware"],
"observables": [
{
"type": "ip-dst",
"value": "192.168.1.100"
},
{
"type": "file-md5",
"value": "12345678901234567890"
}
]
}
]
}
- Install (Python 3.8+, stdlib only):
State lives in a JSON store (set with the global
pip install leadforge
--dbflag orLEADFORGE_DB). Note:--formatand--dbare global flags and must precede the subcommand. - Add a lead and move it through the pipeline:
leadforge add "Acme Corp" [email protected] --company Acme --value 12000 leadforge move <lead_id> qualified
- Enroll a lead in an email sequence:
leadforge enroll <lead_id> --sequence cold-outreach
- Read the output — JSON by default; use
--format tablefor humans:leadforge --format table list --stage qualified leadforge --format table pipeline # win-rate + value by stage - Run the sequence cadence (cron / agent) — find due steps, then advance them:
leadforge due # what is due now leadforge send # mark due steps sent and advance them
- Why leadforge? · Features · Quick start · Example · Architecture · AI stack · How it compares · Integrations · Install anywhere · Related · Contributing
CRM your AI agents can drive over MCP
leadforge 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.
- ✅ Fast, single-purpose CLI
- ✅ JSON / SARIF output for pipelines
- ✅ CI fail-gate (
--fail-on) - ✅ MCP server for AI agents
- ✅ Runs on Linux/macOS/Windows · Docker · devcontainer
- ✅ Ports in Python, JavaScript, Go, and Rust (
ports/)
pip install cognis-leadforge
leadforge --version
leadforge scan . # scan current project
leadforge scan . --format json # machine-readable
leadforge scan . --fail-on high # CI gate (non-zero exit)$ leadforge scan .
[HIGH ] LEA-001 example finding (./src/app.py)
[MEDIUM ] LEA-002 another signal (./config.yaml)
2 findings · risk score 5 · 38ms
flowchart LR
IN[MCP server] --> P[leadforge<br/>inspect]
P --> OUT[findings / policy]
leadforge is interoperable with every popular way of using AI:
- MCP server —
leadforge mcp(Claude Desktop, Cursor, Cognis.Studio, uncensored-fleet) - OpenAI-compatible / JSON — pipe
leadforge scan . --format jsoninto 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
| Cognis leadforge | Twenty | |
|---|---|---|
| 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 | ✅ COCL | varies |
Built in the spirit of Twenty / EspoCRM, re-framed the Cognis way. Missing a credit? Open a PR.
Pipes into your stack: SARIF for code-scanning, JSON for anything, an MCP server (leadforge mcp) for AI agents, and a webhook forwarder for SIEM/Slack/Jira. See docs/INTEGRATIONS.md.
pip install "git+https://github.com/cognis-digital/leadforge.git" # pip (works today)
pipx install "git+https://github.com/cognis-digital/leadforge.git" # isolated CLI
uv tool install "git+https://github.com/cognis-digital/leadforge.git" # uv
pip install cognis-leadforge # PyPI (when published)
docker run --rm ghcr.io/cognis-digital/leadforge:latest --help # Docker
brew install cognis-digital/tap/leadforge # Homebrew tap
curl -fsSL https://raw.githubusercontent.com/cognis-digital/leadforge/main/install.sh | sh| Linux | macOS | Windows | Docker | Cloud |
|---|---|---|---|---|
scripts/setup-linux.sh |
scripts/setup-macos.sh |
scripts/setup-windows.ps1 |
docker run ghcr.io/cognis-digital/leadforge |
DEPLOY.md (AWS/Azure/GCP/k8s) |
invoctl— CLI invoicing + payment-link generator with PDF and a local ledgerchurnlens— Self-hosted SaaS metrics — MRR, churn, LTV from Stripe or CSVquotecraft— Proposal / quote / SOW generator — YAML to branded PDFboardroom— Investor-update and KPI one-pager generator from your metricsseataudit— SaaS license, seat-usage and shadow-IT auditorpaywatch— Recurring-charge and subscription detector from bank/Plaid CSV
Explore the suite → 🗂️ all 170+ tools · ⭐ awesome-cognis · 🔗 cognis-sources · 🤖 uncensored-fleet · 🧠 engram
PRs, new rules, and demo scenarios are welcome under the collaboration-pull model — see CONTRIBUTING.md and SECURITY.md.
{} composes with the 300+ tool Cognis suite — JSON in/out and a shared
OpenAI-compatible /v1 backbone. See INTEROP.md for the
suite map, composition patterns, and reference stacks.
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 ([email protected]). See LICENSE.