Agentic Index
Botpress vs Voiceflow (2026)
Botpress and Voiceflow are the perennial conversational agent builder rivals, both freemium with meaningful paid structures: Botpress runs a free tier then plans from 150 dollars a month, developer friendly with deep customization, while Voiceflow uses three part pricing, a base subscription plus 50 dollar editor seats plus usage credits, Pro from 60 dollars an editor monthly and Business around 150, with credits that do not roll over and voice workloads burning them fast. That verdict is the Agentic Index coverage score, graded from each vendor's own published materials.
Developer teams building custom agents lean Botpress; design led teams collaborating on conversation flows, especially voice, lean Voiceflow while budgeting credits carefully.
This comparison is published by Agentic Index, an independent agentic AI vendor research platform. Botpress and Voiceflow are each graded against the same 14 capability Agentic Index taxonomy, from the vendor's own public materials under the Agentic Index verification standard, alongside 955 researched vendors. No vendor pays for placement and no vendor has reviewed this page. How this evidence is graded
Choose Botpress if
- Developer extensibility and custom code paths are your requirement.
- A flat monthly platform fee is simpler than seat plus credit math.
- Complex custom agents beyond templated flows are the job.
Choose Voiceflow if
- Designers and product managers collaborate on flows in your process.
- Voice agent design tooling is a specific strength you need.
- Editor based pricing maps to your small design team.
| Feature | B Botpress |
V Voiceflow |
|---|---|---|
| Action & orchestration | ||
|
Integrations & Tool Calling Ability to connect agents to real systems through native integrations, OAuth-authenticated actions, custom tools, APIs, webhooks, or MCP-compatible tools. |
||
|
BotpressIntegrations & Tool Calling The Hub supplies installable integrations maintained by Botpress and by third parties, including HubSpot, Notion, Jira and Calendly, with a full catalog behind them, and agents call those systems through action cards and an Execute Code card. A single resolution can coordinate several systems at once, updating the record, triggering the next step and closing the loop, for example by changing a plan or updating billing details. On Enterprise, custom JavaScript can be injected to integrate business systems, which Botpress says makes the platform as flexible as code. Sourcebotpress.com/hubread 2026-09-05 |
||
|
VoiceflowIntegrations & Tool Calling Agents act in any third-party system through a build step, not a fixed connector list. Voiceflow says agents integrate with third-party services and APIs using Voiceflow Functions and API blocks, and that teams build custom logic, actions and integrations with the full power of code, APIs and JSON. Because the route is a general API block plus custom code, the reach is set by what the customer can call, and a separate integrations directory sits alongside. App Credentials are stored encrypted, and API keys never appear in agent logs. Sourcevoiceflow.com/features/platform-overviewread 2026-09-05 |
||
|
Workflow Orchestration Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps. |
||
|
BotpressWorkflow Orchestration The Autonomous Node runs on LLMz, a versioned autonomous engine that decides which cards to execute and in what order, iterating until it reaches a final decision. Standard Nodes hold deterministic paths, so one bot can mix reasoning-driven and rule-based execution across multiple workflows. Agents can be composed with a Vision Agent for image input and hand off to other agents or to a person mid-flow. Sourcebotpress.com/docs/studio/introductionread 2026-09-05 |
||
|
VoiceflowWorkflow Orchestration Two orchestration modes sit side by side. Workflow Builder handles multi-step tasks as scripted flows the agent calls, which execute in order every time, and Voiceflow calls this the route for ultimate control. Playbooks carry natural-language instructions for complex tasks the agent executes, the reasoning-led alternative. Beneath both sits a set of canvas steps covering agent, prompt, capture, condition, set and end, so branching, variable assignment and termination are all built in, and reusable Components carry a sequence such as authentication across agents. Sourcevoiceflow.com/features/workflowsread 2026-09-05 |
||
|
Triggers & Channel Coverage How agents wake up and where they work: schedules, webhooks, message events, CRM events, inbox events, chat, email, voice, and collaboration tools. |
||
|
BotpressTriggers & Channel Coverage Channels include webchat, WhatsApp, Instagram, Messenger and Slack among others, with voice through a maintained Twilio Voice integration that lets a bot take a phone call, and one build reaches all of them. The agent can also start work itself. Studio has Triggers, a Fixed Schedule card runs work on a timetable, and bots can send reminders into conversations. Sourcebotpress.com/integrations/twilio-voiceread 2026-09-05 |
||
|
VoiceflowTriggers & Channel Coverage Coverage spans text, voice and messaging, with the interface left open. Voiceflow ships a web chat widget and, through the Dialog API, deployment into any custom interface, with worked examples for Slack, Microsoft Teams, Discord, Telegram, Twilio SMS, WhatsApp and Shopify. Voiceflow treats voice as a first-class channel, not an add-on, with its own documentation covering voice settings, voice input, call recording, custom voice actions and SIP functionality, and it reports 50ms platform latency for telephony. Answering service, call center and virtual receptionist solutions cover inbound telephony. Sourcedocs.voiceflow.com/docs/faqread 2026-09-05 |
||
| Knowledge & context | ||
|
Knowledge Grounding & RAG Ability to ground agent behavior in company data through document ingestion, retrieval, external knowledge APIs, semantic search, or RAG layers. |
||
|
BotpressKnowledge Grounding & RAG Knowledge Bases are a Studio object that defines the information an agent can access. They take websites crawled by the platform, documents, custom text and Tables, index them automatically on ingest, and can be segmented so different bases serve different purposes, with per-node toggling of which bases an autonomous node may use. A Search Knowledge card performs retrieval inside the node, a Knowledge Agent ships in the prebuilt agent library, and Botpress publishes guidance on optimizing files for retrieval. Sourcebotpress.com/academy-lesson/studio-ui-knowledge-baseread 2026-09-05 |
||
|
VoiceflowKnowledge Grounding & RAG Customers curate a knowledge store the agents answer from. Knowledge Base is a named product with its own feature page. Teams import data and documents into it so agents respond using curated data, and Voiceflow describes it as training agents on the customer's own data to power responses and perform tasks using any LLM model. Voiceflow's build sequence puts the knowledge base first, before workflows and integrations, and the Content Management System curates agent content, components and logic so it scales across teams and use cases. Sourcevoiceflow.com/features/knowledge-baseread 2026-09-05 |
||
|
Memory & State Persistence Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer. |
||
|
BotpressMemory & State Persistence The agent development kit has a state layer with three scopes. Bot state persists across all users and conversations, user state persists across all conversations for a given user, and conversation state covers a single conversation, each defined as a typed schema in the agent config and read or written through the runtime. Any user or conversation can be loaded by id from anywhere in the agent to read and write its state and tags, so each customer's store can be reached and kept separate. Sourcebotpress.com/docs/adk/conversations/stateread 2026-09-05 |
||
|
VoiceflowMemory & State Persistence There is no memory, saved state or persistence layer. The Set step assigns variables within a flow, which is session state, and the Knowledge Base is a curated corpus for grounding answers, not memory the agent keeps. |
||
| Control & trust | ||
|
Human Oversight & Guardrails Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls. |
||
|
BotpressHuman Oversight & Guardrails Human Handoff is a core platform feature with its own setup step, Configure Human Handoff, and a HITL Agent in the Studio's prebuilt agent library lets a builder drop escalation into a bot. A Policy Agent in the same library constrains behavior against defined rules, builder Instructions govern what the autonomous node may do, and Botpress publishes guidance on preventing fabricated answers. Access control over the agent is another setup step. Sourcebotpress.com/docs/studio/get-started/manage-your-agent/edit-appearanceread 2026-09-05 |
||
|
VoiceflowHuman Oversight & Guardrails There is no runtime oversight of agent actions, with no handoff or escalation to a human agent, no approval step before sending and no policy threshold that pauses a sensitive action. The controls that exist sit around the run. Staging and stakeholder review before production is a release gate, SSO with advanced user permissions is an administrative control, and neither holds an agent action at run time. |
||
|
Security, Identity & Governance RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy. |
||
|
BotpressSecurity, Identity & Governance Botpress states SOC 2 certification and GDPR compliance, with third-party penetration testing by KPMG. Customer controls cover roles and role-based access, SSO, audit logs and workspace controls, and a DPA is available from the Plus tier and a HIPAA BAA on Enterprise. The SOC 2 report type is not specified, and a Trust Center is linked from the site footer. Sourcebotpress.comread 2026-09-05 |
||
|
VoiceflowSecurity, Identity & Governance Voiceflow holds SOC 2 Type II, ISO/IEC 27001:2022, GDPR and HIPAA, each linked to a trust portal, alongside annual external penetration testing, continuous vulnerability scanning, automated and manual code review, and a vulnerability disclosure policy with safe harbor and a bug bounty. For customers, SSO with SAML and roles and permissions each have their own workspace administration sections, with granular access controls, audit logging and alerting, encryption at rest under customer-managed keys, and full project history with rollback. Infrastructure sits on AWS and GCP with multi-AZ databases, point-in-time recovery, TLS and mTLS in transit, and a CDN-backed WAF. That portal sits at trust.voiceflow.com. Sourcevoiceflow.com/legal/securityread 2026-09-05 |
||
|
Observability & Auditability Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior. |
||
|
BotpressObservability & Auditability In production, a Conversations tab holds conversation history, a Logs tab records a deployed bot's activities, events, errors and actions with date filtering and custom console logging, and audit logs come on the enterprise tier. The view of an Autonomous Node's input, output and iteration steps lives in the Studio emulator, which does not save conversations, and Botpress's production debugging guide recommends duplicating the bot and inserting text cards or log statements instead of reading a native trace. Iteration data reaches production only through a separate Improvement integration built for feedback. Sourcebotpress.com/docs/debugging-bot-behavior-in-productionread 2026-09-05 |
||
|
VoiceflowObservability & Auditability Transcripts and Analytics are their own sections under Monitoring Agents, audit logging and alerting are a platform property alongside full project history with rollback, and Environments and Backups give a record of what was deployed when. Voiceflow does not show whether a transcript reconstructs a run step by step, with the blocks traversed, the tool calls made and the retrieval performed. Sourcevoiceflow.com/legal/securityread 2026-09-05 |
||
|
Deployment & Data Residency Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting. |
||
|
BotpressDeployment & Data Residency Custom data residency is listed on the Enterprise tier, but the hosting region for Botpress Cloud, and whether a customer can choose it, is not stated. Self-hosting belongs to the older open-source v12 line, not the current cloud platform, and does not apply to Botpress Cloud. |
||
|
VoiceflowDeployment & Data Residency A different hosting arrangement is available by negotiation, not as a published option. Voiceflow is based in Canada and may host, transfer and process data in Canada and other countries unless it expressly agrees otherwise, so a different arrangement can be had by contract, with enterprise negotiation as the gate. No region is named or selectable, and there is no VPC, single tenant or self hosted option. Voiceflow runs multi-AZ databases, cross-region backup and infrastructure on AWS and GCP, which is redundancy, not a location a customer chooses. Voiceflow keeps a trust portal at trust.voiceflow.com. Sourcevoiceflow.com/privacyread 2026-09-05 |
||
| Solution readiness | ||
|
Prebuilt Agents, Templates & Packs Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value. |
||
|
BotpressPrebuilt Agents, Templates & Packs The Hub carries production-ready templates for customer support, appointment scheduling and lead qualification, including a Kitchen Sink template that shows user data loading, workflow routing and live agent handoff, adopted by customizing instructions and swapping in a knowledge base. The Studio also offers prebuilt Agents that a builder drops into a bot, namely Summary, Personality, Policy, Translator, Knowledge, HITL, Vision and Analytics. Sourcebotpress.com/hubread 2026-09-05 |
||
|
VoiceflowPrebuilt Agents, Templates & Packs Packaged assets exist and are reused across agents, but the customer builds them. Reusable Components hold a sequence such as an authentication or intake flow and are reused across agents and channels, the Content Management System curates agent content, components and logic so they scale across teams and use cases, and projects and functions can be exported and imported between workspaces. Every one of those assets starts with the customer. There is no catalog of prebuilt agents or templates from Voiceflow to browse and put into service, and the industry and solution pages describe use cases, not units to adopt. Sourcevoiceflow.com/features/agent-cmsread 2026-09-05 |
||
| Platform extensibility | ||
|
Model Flexibility & Routing Ability to work across multiple foundation models, route tasks to different models, or let buyers bring their own providers and keys. |
||
|
BotpressModel Flexibility & Routing Default LLMs are set per bot in Bot Settings and can be overridden on an individual Autonomous Node through advanced settings, separately for response generation and for the RAG model used against knowledge bases. The LLMz autonomous engine is versioned independently and written to stay agnostic to variance between models. Sourcebotpress.com/docs/studio/concepts/bot-settingsread 2026-09-05 |
||
|
VoiceflowModel Flexibility & Routing The customer chooses the model. Voiceflow names Use any model as a platform property, so any AI vendor, including OpenAI and Anthropic, can power agent responses, logic and actions, and the Knowledge Base trains agents on the customer's data to power responses and perform tasks using any LLM model. Model choice sits with the customer at build time, and Voiceflow frames the whole platform as building agents with any models and integrations. Sourcevoiceflow.com/features/platform-overviewread 2026-09-05 |
||
|
APIs, SDKs & MCP Extensibility Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems. |
||
|
BotpressAPIs, SDKs & MCP Extensibility Developers get a public API Reference, a Botpress Cloud API, an Agent Development Kit with its own documentation set alongside Studio, Integrations, Desk and Webchat, Hooks for custom code, an Execute Code card inside the autonomous node, and Import and Export for moving bots programmatically. Botpress also publishes Model Context Protocol material that ties MCP tool access to the Autonomous Node. Sourcebotpress.com/docs/studio/get-started/manage-your-agent/edit-appearanceread 2026-09-05 |
||
|
VoiceflowAPIs, SDKs & MCP Extensibility The platform can be called from outside. Voiceflow offers a Dialog API for launching agents into any custom interface, an API reference alongside the documentation and changelog, and a Voiceflow CLI with its own install and authentication guides under Developer Tools. Agent API keys are issued per agent from the agent settings, so a third party can authenticate against a specific agent, not only through the console. Worked examples built on those APIs cover Slack, Microsoft Teams, Discord, Telegram, Twilio SMS, WhatsApp, Shopify and Unity, and Voiceflow treats a developer platform for custom features, integrations and interfaces as a product pillar. Sourcedocs.voiceflow.com/docs/faqread 2026-09-05 |
||
|
Testing, Debugging & Optimization Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment. |
||
|
BotpressTesting, Debugging & Optimization The Emulator supports real-time conversation testing, with an inspect window showing an Autonomous Node's input, output and iteration steps, alongside an Event Debugger, version history and an Improvement integration that collects feedback on production iterations. Testing is a manual loop of inspecting and fixing. There is no test suite, regression harness, scored evaluation or pass rate, and the emulator neither saves conversations nor counts toward usage, so there is nothing to compare runs against. Sourcebotpress.com/academy-lesson/studio-ui-emulatorread 2026-09-05 |
||
|
VoiceflowTesting, Debugging & Optimization Production pipelines let teams test agent builds in staging and share them with stakeholders for feedback before production, a Test Tool has its own interface section, prototypes can be shared for review, and Environments and Backups separate work in progress from what is live. Those steps form a quality gate that ends in a person's judgment. There is also an Evaluations section under Monitoring Agents, and Voiceflow does not show whether it produces a score, pass rate or judge verdict against a set of scenarios. Sourcevoiceflow.com/features/platform-overviewread 2026-09-05 |
||
| Specialist automation | ||
|
Browser & Computer Use Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone. |
||
|
BotpressBrowser & Computer Use Botpress offers no browser control, hosted session or computer use. Agents act programmatically through Hub integrations, action cards, an Execute Code card and API calls, and reach people through channels. The Vision Agent in the prebuilt agent library reads images and does not operate an interface. Sourcebotpress.com/hubread 2026-09-05 |
||
|
VoiceflowBrowser & Computer Use There is no browser control, hosted session, virtual desktop or computer use. Agents work through programmatic routes, reaching third-party systems through Voiceflow Functions and API blocks and reaching end users through the web chat widget, the Dialog API and telephony, and Voiceflow frames itself as a developer platform for custom integrations and interfaces. A native web search tool retrieves information and does not operate a screen. Sourcevoiceflow.com/features/platform-overviewread 2026-09-05 |
||
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing | B Botpress |
V Voiceflow |
|---|---|---|
|
Entry price Lowest public entry point |
From $150 a month on Plus, billed annually. A free tier is available. | Not public · free plan |
|
Pricing confidence How public the numbers are |
Public, exact | Contact only |
|
Billing Primary billing axis |
Per conversation. Each tier includes a monthly conversation allotment, every conversation includes $0.10 of AI usage, and extra conversations bill in packs of 100. | plan fee + add ons (seats, phone numbers, concurrent calls) + credits |
|
Variable cost Workload / overage exposure |
Low variable cost | High variable cost |
|
Free tier / trial Try before you buy |
Free tier
|
Free tierTrial
|
|
Buying motion Self-serve vs sales call |
Self-serve | Mixed |
Other matchups in agent builders
Not the pairing you were after? These compare a different set of agent builders on the same 14 capabilities.