TEN Framework
TEN Framework is a real-time conversational AI framework from Agora with a visual designer, a SIP extension for phone calls, turn detection and avatar extensions, run with Docker Compose. Its licence is Apache-2.0 plus conditions that forbid hosting it on end-user devices and any deployment that competes with Agora, so this site labels it source available rather than open source. Its documented quick start depends on an Agora account.
What does TEN Framework do?
TEN "is an open-source framework for real-time multimodal conversational AI", in its own words. It ships two assistant shapes, a chained one (speech to text, language model, text to speech) and a speech-to-speech one, plus a visual designer called TMAN Designer where you pick the extensions and set keys. Extensions cover voice activity detection, turn detection ("enables full-duplex dialogue communication"), avatars from HeyGen, Tavus and Trulience, memory, and a SIP extension "that enables phone calls powered by TEN", with a Twilio example. It runs on the ESP32-S3 Korvo board as well as servers.
Key facts
- Licence: an "Open Source License" that is Apache-2.0 "with the following additional conditions", copyright Agora; the README's own badge reads "Apache 2.0 with certain conditions".
- Condition one, verbatim: you may not host it "on any End User devices" or deploy it "in a way that competes with Agora's offerings and/or that allows others to compete with Agora's offerings".
- Only the packages directory is plain Apache-2.0, per the README's licence section.
- Two assistant shapes: a chained one (speech to text, language model, text to speech) and a speech-to-speech one.
- The visual designer, TMAN Designer, runs on port 49483; extensions cover voice activity detection, turn detection, avatars from HeyGen, Tavus and Trulience, memory, and SIP with a Twilio example.
- The quick start requires an Agora app ID and certificate, an OpenAI key, a Deepgram key and an ElevenLabs key.
- Runs with Docker Compose and Node.js 18 LTS, or in GitHub Codespaces; minimum stated hardware is 2 CPU cores and 4 GB of RAM.
- Also runs on the Espressif ESP32-S3 Korvo V3 board. Latest tagged release when read: 0.11.71.
What does it replace, and where does it fall short?
TEN replaces Vapi, Retell AI and ElevenLabs Agents for a team that can accept its licence conditions and its dependency on Agora's real-time service for the documented quick start.
The licence is the reason this page labels it source available. The LICENSE file grants Apache-2.0 "with the following additional conditions": you may not host it "on any End User devices", and you may not deploy it "in a way that competes with Agora's offerings and/or that allows others to compete with Agora's offerings". Derivative works stay under the same terms. Only the packages directory is plain Apache-2.0. A field-of-use restriction like that is not something an OSI-approved licence permits, and the README's own badge reads "Apache 2.0 with certain conditions".
Where it falls short beyond the licence: the quick start requires an Agora app ID and certificate, an OpenAI key, a Deepgram key and an ElevenLabs key. The README does not describe running without Agora's service.
How does TEN Framework run?
Docker and Docker Compose with Node.js 18 LTS: docker compose up -d, then task install and task run inside the container. The designer runs on port 49483. Self-hosting is described as building the example Dockerfile, or splitting a Go backend on port 8080 from a Next.js front end. GitHub Codespaces is offered as a Docker-free path. Minimum stated hardware is 2 CPU cores and 4 GB of RAM. No hosted TEN is sold in the README.
Who is TEN Framework for?
A team already on Agora that wants a visual designer and a SIP path. A team that needs an OSI licence or wants to run without Agora should use Pipecat or LiveKit Agents.
What limits does the README state?
The 2-core, 4 GB minimum; a first build of the default example takes 5 to 8 minutes by the README's estimate; running the transcriber without Docker is marked beta.
Questions people ask
Is TEN Framework open source?
Not by the definition this site uses. The licence starts from Apache-2.0 and adds conditions: no hosting on end-user devices, and no deployment that competes with Agora's offerings or lets others compete. A field-of-use restriction like that is not something an OSI approved licence permits, so TEN is labelled source available.
Can I use TEN Framework commercially?
The licence allows deploying it to create applications for your own benefit and your direct end users, with an optional "Powered by TEN FRAMEWORK" notice. What it forbids is competing with Agora or enabling third parties to build or deploy applications, and hosting on end-user devices. Read the LICENSE before building a product on it.
Does TEN need Agora's service?
The documented quick start does: it requires an Agora app ID and certificate for real-time transport, and the README does not describe running without that service. The backend itself can be self-hosted in a container, and a Next.js front end deployed elsewhere.
How does TEN compare with Vapi and Pipecat?
TEN brings a visual designer and a SIP path, which the other frameworks lack, at the cost of a restricted licence and an Agora dependency. Pipecat and LiveKit Agents carry plain OSI licences. The alternatives to Vapi page places TEN as the pick if Agora already fits.
What hardware does TEN need?
The README states a minimum of 2 CPU cores and 4 GB of RAM, and estimates 5 to 8 minutes to build the default example. It runs through Docker Compose with Node.js 18, or in GitHub Codespaces with no Docker. A board example targets the ESP32-S3 Korvo V3.
Sources
- TEN Framework README: github.com/TEN-framework/ten-framework, read 2026-09-16.
- TEN Framework LICENSE, "Open Source License" with additional conditions, copyright Agora: LICENSE, read 2026-09-16.
Compared with the others
On the open-source alternatives to Vapi page, TEN Framework is the pick for a visual designer, if agora fits. A visual designer, a SIP extension with a Twilio example, turn detection, and avatar extensions, run with Docker Compose.
Also on that page: Pipecat for the widest provider and carrier list, LiveKit Agents for the whole stack on your own servers, Bolna for a phone agent from a json file.
On the open-source alternatives to Retell AI page, TEN Framework is the pick for a visual designer, if agora fits. A visual designer, a SIP extension with a Twilio example, turn detection, and avatar extensions, run with Docker Compose.
Also on that page: Pipecat for the widest provider and carrier list, LiveKit Agents for the whole stack on your own servers, Bolna for a phone agent from a json file.
On the open-source alternatives to ElevenLabs Agents page, TEN Framework is the pick for a visual designer, if agora fits. A visual designer, a SIP extension with a Twilio example, turn detection, and avatar extensions, run with Docker Compose.
Also on that page: Pipecat for the widest provider and carrier list, LiveKit Agents for the whole stack on your own servers.
More voice agent frameworks
A Python framework under BSD-2-Clause, maintained by Daily, for real-time voice and multimodal agents, with the widest provider list on this site and telephony serialisers for Twilio, Telnyx, Plivo, Vonage, Exotel and Genesys.
An Apache-2.0 framework for real-time voice agents that connects any speech, language and voice provider, with semantic turn detection, native MCP tool support, a test framework, and an open-source media and SIP stack it can run on entirely.
Added September 16, 2026. Every claim above comes from the project's README, LICENSE or model card, read on September 16, 2026, or from the GitHub API on the date shown in the panel. Found an error? Write to reveneau@licheo.com and it is fixed in the next weekly pass. Repository: github.com/TEN-framework/ten-framework.
Want TEN Framework running on your own servers?
Reveneau sets it up on your hardware, connects it to your product, and builds the software around it.