Design the whole conversation as a graph — branching logic, any LLM, your own docs. Then ship it as text, real-time voice, or a lip-synced AI avatar. Same agent, one switch, no code.
↳The real editor — building a conversation graph, then switching its output to voice and to a live avatar.
A prompt can't hold a real conversation. A graph can. Drag nodes, wire the branches, publish — the flow of the dialogue is the thing you edit, not a wall of instructions.
↳A real agent — classifier → condition → six branch agents, each on its own model.
Condition nodes route the conversation on intent, on state, on a tool's answer. Every path is visible, so nothing hides inside a prompt.
Classify on a cheap fast model, reason on a strong one. The provider is a property of the node, not of the project.
Agent, Condition, Delay, Set Variable, Transcribe, HTTP Request. Reach anything over HTTP, then keep going in the graph.
Most tools make you pick the channel up front and rebuild the bot to add voice. Here the modality is a field on the agent. Change how it answers without touching the conversation you already built.
Plain chat replies.
Speaks out loud, streamed live as it thinks.
A talking face on screen.
Realtime streaming
Speak as the agent thinks
Voice input works the same way — drop a Transcribe node in front of the agent and the graph takes speech as well as it takes text.
Two things separate an agent from a chat widget: it carries context across turns, and it answers from your material instead of guessing.
Typed workflow and agent state carries context across every turn — set it, branch on it, watch it update. The values live in Postgres, so a conversation survives restarts, deploys, and weeks of silence.
Upload PDFs, paste text, attach the knowledge base to any agent. It retrieves over your material and answers with citations — no fine-tuning, no separate vector database to run.
Run the agent in the debug panel — type or talk — and watch each step as it happens. When something goes wrong in production, open the run and walk it back step by step.
Hit publish and you get POST /api/workflows/wf_… with bearer auth and a stable contract. Put it behind your own product, your own UI, your own funnel — no separate deploy, no infrastructure code.
curl -X POST https://app.assmblx.com/api/workflows/wf_a3f2 \
-H "Authorization: Bearer $ASSEMBLIX_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": { "message": "I want a refund" },
"state": { "user_id": "u_42" }
}'{
"executionId": "exec_d7c9b585",
"status": "completed",
"output": {
"parsed_message": {
"intent": "refund",
"confidence": 0.94,
"next_action": "check_policy"
},
"tool_executions": []
},
"state": { "user_id": "u_42", "turn": 3 },
"metadata": { "durationMs": 850, "totalSteps": 3 }
}Postgres-backed state · Webhooks, REST, schedules · Every run traced and replayable.
Nothing here is locked to one vendor. Bring your own keys for the model, the voice, and the avatar — and swap any of them without rebuilding the agent.
Bring your own keys · vendor-neutral
On the free tier you can run on our keys to get started. After that the cost of a call is between you and the provider.
Own your stack. Postgres-only core, no phone-home, bring your own keys. Source-available and free to self-host.
Source-available — MIT + Commons Clause. The commercial billing layer is a separate Enterprise license, off by default.
$ git clone https://github.com/nmamizerov/assemblix$ cd assemblix && docker compose up→ pulling images…✓ postgres ready on :5432✓ assemblix-api ready on :8000✓ assemblix-web ready on :3000Assemblix is live → http://localhost:3000
Short, direct answers to the things people ask most. Anything still unclear — ping us on Telegram, we reply fast.
Everything above runs on your own machine at no cost — that is the whole install, and it stays that way. If you would rather not operate it yourself, here is what the managed cloud costs. Call limits visible, no hidden seats.
For prototyping and weekend hacks.
For production solo and small teams.
For scale and collaboration.
Tell us what's missing — new nodes, providers, integrations land in days, not quarters. Direct line to the founder.
Request a featureFree tier, no credit card. Build the conversation as a graph, flip the output to voice, and hear it answer.