Parlant
A conversational agent framework that selects relevant guidelines, tools, domain knowledge and journey steps for each turn of a customer interaction.
About Parlant
Customer-facing agents need to apply business rules and use the right tools as conversations move between topics.
Who it’s for
- Developers building customer-facing conversational agents
- Teams defining agent behavior through rules and workflows
When to consider it
Consider Parlant when you want to define conversational guidelines, multi-turn journeys and approved responses with traceable context selection.
Tradeoffs & limitations
- Apache-2.0 licensed and requires Python 3.10 or newer. The quickstart runs a local server and needs an LLM-provider API key; the default provider is Emcie, the maker's own inference service, with other providers available through extra packages.
SOTA overview · Documentation-based assessment · Sources & review method
Updates
No updates shared yet.
Discussion
Newest firstAsk a question or share how you use Parlant.
Keep it helpful. Community rules
Loading discussion…
Sources & review method
Documentation-based assessment · Oct 30, 2026 · Prepared with AI assistance; not a hands-on benchmark.
- Official product overview
- Official repository, capabilities and setup
- Apache-2.0 code licence
- Installation and runtime requirements
Checked by SOTA · AI-assisted documentation review. Selection advice is our assessment; verify current requirements for your deployment.
Import history & original evidence
Parlant official website
A conversational agent framework that selects relevant guidelines, tools, domain knowledge and journey steps for each turn of a customer interaction.
Based on official pages and announcements checked on 2026-10-30. No hands-on test, performance benchmark or popularity ranking is claimed.
Parlant official repository and licence
Parlant code is Apache-2.0 licensed; capabilities and setup were checked in the official repository.
Based on official pages and announcements checked on 2026-10-30. No hands-on test, performance benchmark or popularity ranking is claimed.
Parlant official installation documentation
Apache-2.0 licensed and requires Python 3.10 or newer. The quickstart runs a local server and needs an LLM-provider API key; the default provider is Emcie, the maker's own inference service, with other providers available through extra packages.
Based on official pages and announcements checked on 2026-10-30. No hands-on test, performance benchmark or popularity ranking is claimed.