AI agents for sales teams that find prospects, run multi-channel outbound and surface buyer signals
AgentSDR
New· 4Open-source, self-hosted AI sales development workspace with email, LinkedIn and WhatsApp outreach and an AI CRM; free under the MIT licence, you pay for your own infrastructure.
- Sales
- CRM
- Lead Generation
- Email Marketing
About AgentSDR
Not yet independently verified. Operator named by the maker as Kandid; no location; the launch date rests on the maker's own Product Hunt launch of 9 October 2026; no independent report found. We will update this when it can be confirmed, and remove this note.
AgentSDR is an open-source workspace for outbound sales. It runs email sequences from Google Workspace mailboxes, sends LinkedIn invites and follow-ups through Unipile, and handles WhatsApp calls and messages. A built-in CRM uses AI to classify replies and draft responses that a person approves before sending. Its site names founders doing outbound without a sales team, agencies running one deployment with a separate organisation per client, and sales teams sharing a pipeline with per-rep accounts as its audience. It is self-hosted with Docker and Postgres, using the buyer's own AI keys through OpenRouter, and the code is public on GitHub under the MIT licence. The site says there are no seats and no per-contact fees; users pay for their own server, connected accounts and AI usage. A live demo with sample data is available without sign-up. The operator is shown only as AgentSDR, with no company or location. The maker presented it on Product Hunt on 9 October 2026. A buyer should check the outreach rules that apply to their markets, who maintains the project, and the cost of the connected services.
TrustList summary
Not yet independently verified. The launch date rests on the maker's own Product Hunt launch of 9 October 2026. Every detail comes from the maker's own site and launch page; the operator is named only as AgentSDR (GitHub organisation Kandid-ai), with no company or location, and no independent report was found. We will update this when it can be confirmed, and remove this note.
AgentSDR is an open-source workspace for outbound sales. It runs email sequences from Google Workspace mailboxes, sends LinkedIn invites and follow-ups through Unipile, and handles WhatsApp calls and messages. A built-in CRM uses AI to classify replies and draft responses that a person approves before sending. Its site names founders doing outbound without a sales team, agencies running one deployment with a separate organisation per client, and sales teams sharing a pipeline with per-rep accounts as its audience. It is self-hosted with Docker and Postgres, using the buyer's own AI keys through OpenRouter, and the code is public on GitHub under the MIT licence. The site says there are no seats and no per-contact fees; users pay for their own server, connected accounts and AI usage. A live demo with sample data is available without sign-up. The operator is shown only as AgentSDR, with no company or location. The maker presented it on Product Hunt on 9 October 2026. A buyer should check the outreach rules that apply to their markets, who maintains the project, and the cost of the connected services.
Categories & features
- Sales
- CRM
- Lead Generation
- Email Marketing
Trust Score
An earned signal from verification, reviews, awards, transparency and engagement - the vendor can't buy it.
Updated 10/9/2026
Request a demo or quote from AgentSDR
Reviews
Questions & answers
No questions yet. Be the first to ask about AgentSDR.
AgentSDR alternatives
Similar listings buyers compare against this one.
Every customer, every deal, one place
Open-source, self-hostable CRM where every AI-proposed change waits for human approval

Field Service Management Software called Service CRM
More on TrustList
Everything here links back to the same verified catalogue. Pick your next stop.
- Write a reviewHelp other buyers decide
- CompaniesAgencies, consultancies and IT service providers, ranked by verified reviews.
- ArticlesGuides, comparisons and research from the editorial desk and the community.
- AwardsAnnual recognition decided by verified reviews and an independent jury.
- LaunchesNew products and releases, voted up by the community every day.
- AI ModelsBenchmark scores and community ratings for every major model.
- RequestsBuyers describe what they need; vendors respond directly.
- PeopleReviewers, authors and makers with public profiles.
- ComparePut up to four listings side by side before you shortlist.

