# Open source AI SDR tools stop the send in six places

> Open source AI SDR tools are not one kind of software. Each of these six projects stops the send in a different place, and that place decides whether a company can run it. Kortix is the open-source CompanyOS, and it runs the same sales job with the send held at a human approval gate.

URL: https://aisalesagentsguide.com/open-source-ai-sdr-tools

Six repositories, one question

`kortix.yaml`

```yaml
policy:
  default_mode: risk
policies:
    - match: "helpdesk.delete_*"
      action: block
```

Source: https://kortix.com/docs/developers

The agent's persona, skills and permissions are files in the repo, versioned and changed through a reviewed change request.

[Try Kortix](https://kortix.com)

## Each project hands the send to a different place

These six projects are not versions of one product. SalesGPT is a Python library you embed in your own service, so the code that calls it decides whether an email leaves ([SalesGPT](https://github.com/filip-michalsky/SalesGPT)). Knotie-AI is a Python app that answers leads itself, and its README documents no approval gate ([Knotie-AI](https://github.com/avijeett007/Knotie-AI)). Relaticle is a CRM that agents read and update and that sends no outreach ([Relaticle](https://github.com/Relaticle/relaticle)).

DeskcommCRM answers on WhatsApp and stops at a sending window, a pacing rule and a cap ([DeskcommCRM](https://github.com/melgarafael/DeskcommCRM)). OpenSales writes the campaign and parks every draft in an approval queue until you click send ([OpenSales](https://github.com/siddartha19/OpenSales)). OpenCloser places the call from a desktop app ([OpenCloser](https://github.com/issacops/opencloser)).

Read them together and the feature lists blur: research, drafting, a sequence, a CRM. What survives the comparison is the stopping place. That is where a buyer has to put a person, a rule or a log, and it is the only part of the stack that reaches a customer.

## Where each project stops the send

| | SalesGPT | Knotie-AI | Relaticle | DeskcommCRM | OpenSales | OpenCloser |
| --- | --- | --- | --- | --- | --- | --- |
| What it does | Sales agent across voice, email and messaging, with a product-knowledge tool | Inbound and outbound sales agent in Python that talks to leads | Self-hosted CRM that agents read and update over MCP or REST | WhatsApp CRM whose agents answer, qualify and move the lead | Multi-agent outbound system that plans, finds and writes cold email | Desktop app for AI cold calling and lead generation |
| Where the send stops | In code you write; the library sends when your service calls it | Nowhere documented: the agent answers, and the README shows no approval gate | No send: it is the record the agent reads and writes | A WhatsApp message under a sending window, pacing and a cap | An approval queue: you review the drafts and click send | The call it places from your desktop |
| License | MIT | GPL-2.0 | AGPL-3.0 | MIT | MIT, declared in the README; no LICENSE file in the repo | MIT |
| How you run it | Embed the library in a service you host | Run the Python app; last commit January 2025 | Self-host the CRM; connect an agent over MCP | Self-host the CRM and its WhatsApp connection | Run it locally with your own SendGrid key | Install the Tauri desktop app |

Each cell comes from the repository named in its column, as of November 2026: [SalesGPT](https://github.com/filip-michalsky/SalesGPT), [Knotie-AI](https://github.com/avijeett007/Knotie-AI), [Relaticle](https://github.com/Relaticle/relaticle), [DeskcommCRM](https://github.com/melgarafael/DeskcommCRM), [OpenSales](https://github.com/siddartha19/OpenSales), [OpenCloser](https://github.com/issacops/opencloser).

## What none of the six gives you

Each project owns one slice. SalesGPT owns the conversation, Relaticle the record, DeskcommCRM the WhatsApp inbox, OpenSales the queue, OpenCloser the dialer. Knotie-AI owns the exchange with the lead and stops there. A company that adopts one still has to build the place where the agent gets its job, the tools it may call, the approvals it must pass, and the record of what it did. None of the six is that place, and installing a second one does not close the gap.

## The file that names the agent and rules its tools

`kortix.yaml`

```yaml
# yaml-language-server: $schema=https://kortix.com/schema/kortix.schema.json
default_agent: support
# Registries: what the project has. A registry entry gives nothing to any agent.
skills:
  refund-policy: skills/refund-policy
agents:
  support:
    prompt_file: agents/support.md
    permission:
      bash:
        "*": allow
        "git push *": ask
```

Source: https://kortix.com/docs/developers

Kortix's own example, cut to the registry and one agent. A sales project renames the agent, points it at its own prompt, and writes the rules for its tools.

## Where Kortix keeps the send

Kortix is the open-source CompanyOS, and the platform a company runs this job on. Hand a sales agent the research, the pre-call brief, the CRM write-back and the follow-up draft. Nothing goes out on its own: every follow-up stops at a human approval gate as a draft for a person to review and send. Every action is recorded.

The gate is a rule in the file that declares the agent. Each tool call is ruled allow, ask or block, down to the arguments it was given, so the address a message goes to can decide whether it waits. The persona, the skills and the permissions live in the same repository, and a change to any of them arrives as a diff a reviewer reads ([what the repo holds](/open-source-ai-sales-agent)). If the stack runs on your own infrastructure instead, [the self-hosted setup](/self-hosted-ai-sales-agent) covers what the install needs before the first session.

## Questions buyers ask about open-source sales agents

Short answers on what exists, and on what each one costs.

### Are there any open-source AI agents?

Yes. All six projects are open source, and each names its licence in its own repository. Kortix is the open-source CompanyOS: the agent's persona, skills and permissions are files in a repo you own.

### Are there any AI sales agents?

Yes. AiSDR sells a managed AI SDR that runs email and LinkedIn sequences from one inbox, with a two-way HubSpot sync. Those six projects run on infrastructure you control, and Kortix runs a sales agent you own and holds every follow-up at a human approval gate.

### Does Open AI have an AI agent?

Yes. OpenAI publishes an Agents API that runs a managed Codex harness and an Agents SDK that runs inside your own application ([OpenAI's agent docs](https://developers.openai.com/api/docs/guides/agents)). It is a hosted runtime for building agents, with no sales application of its own.

### How much do AI sales agents cost?

Most AI SDR platforms cost $200 to $5,000 a month, by AiSDR's own comparison, and AiSDR itself bills $1.50 per person contacted ([AiSDR](https://aisdr.com/blog/what-is-an-ai-sdr/)). The commercial tools and their pricing shapes are set out in [the AI SDR tools comparison](/ai-sdr-tools-compared).

## Put one send behind a rule you can read.

Start with new-lead follow-up and one tool rule, then read the draft before it goes.

[Try Kortix](https://kortix.com)