Botpress
Also known as: Botpress Cloud, Botpress Studio, Botpress Desk
Agent building platform whose autonomous nodes mix LLM-driven reasoning with deterministic flows, deployed across web, social and messaging channels, with a typed state layer, per-node model choice and an optional standalone helpdesk.
Botpress is an agent builder spanning both sales and support use cases, with OAuth and multi-channel deployment. On plans for new workspaces since May 2026, LLM usage is bundled into conversation-based pricing; older workspaces still pay provider AI costs separately. It offers a free tier with paid plans from around $150/month.
Vendor details
Canonical URL
https://botpress.com
Category
Customer support agent
Subcategory
Support/Sales — agent builder
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
In practice
You need agents for both sales and support but don't want two separate tools. Botpress is an agent builder that spans both use cases in one place.
An agent is useless if it can't reach your customers where they are. Botpress deploys across multiple channels with OAuth, so the agent connects to your systems and surfaces wherever you need it.
You'd rather not pay a markup on top of the model costs. Botpress passes through provider API costs, so you're not paying a margin on every call.
Agentic Index coverage score
11.0 / 14 capabilities · 79%
| Integrations & Tool Calling | Full |
|---|---|
|
Breadth through a published integration catalog with authenticated action. The Hub supplies installable integrations maintained by Botpress and by third parties, with HubSpot, Notion, Jira and Calendly named in the platform navigation and a full catalog behind it, and agents call those systems through action cards and an Execute Code card. The vendor's own framing is that a resolution coordinates several systems in one motion, updating the record, triggering the next step and closing the loop, changing a plan or updating billing details. The Enterprise page states the platform is as flexible as code, with custom JavaScript injected to integrate business systems. Sourcebotpress.com/hubread 2026-09-05 |
|
| Workflow Orchestration | Full |
|
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, while Standard Nodes hold deterministic paths, so one bot mixes 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 |
|
| Knowledge Grounding & RAG | Full |
|
A maintained retrieval structure the customer curates and scopes. Knowledge Bases are a named Studio object that define the information an agent can access, accepting websites crawled by the platform, documents, custom text and Tables, indexed automatically on ingest, with segmented data management so different bases serve different purposes and 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 |
|
| Human Oversight & Guardrails | Full |
|
Human Handoff is a first-class platform capability with its own place in the feature navigation and its own quickstart step, Configure Human Handoff, and a HITL Agent ships in the Studio's prebuilt agent library so escalation is a component a builder drops in rather than a pattern they assemble. A Policy Agent sits in the same library, constraining behavior against defined rules, and builder Instructions govern what the autonomous node may do, with published guidance on preventing fabricated answers. Access control over the agent is a documented quickstart step alongside it. Sourcebotpress.com/docs/studio/get-started/manage-your-agent/edit-appearanceread 2026-09-05 |
|
| Security, Identity & Governance | Full |
|
SOC 2 certification and GDPR compliance are stated on the vendor's own site alongside third-party penetration testing by KPMG, with named customer-facing controls covering roles and role-based access, SSO, audit logs and workspace controls; a DPA is available from the Plus tier and a HIPAA BAA on Enterprise. The SOC 2 report type is not specified, and Botpress links a Trust Center from its site footer. Sourcebotpress.comread 2026-09-05 |
|
| Observability & Auditability | Partial |
|
Production surfaces are a Conversations tab holding conversation history, a Logs tab recording a deployed bot's activities, events, errors and actions with date filtering and custom console logging, and audit logs on the enterprise tier. The reasoning-level view, which shows an Autonomous Node's input, output and iteration steps, lives in the Studio emulator, which explicitly does not save conversations, and Botpress's own production debugging guide recommends duplicating the bot and inserting text cards or log statements rather than 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 |
|
| Memory & State Persistence | Full |
|
The agent development kit documents a state layer with three declared scopes: bot state persisting across all users and conversations, user state persisting across all conversations for a given user, and conversation state for 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 the store is addressable and separable per customer. Sourcebotpress.com/docs/adk/conversations/stateread 2026-09-05 |
|
| Deployment & Data Residency | Not documented |
|
Custom data residency is listed on the Enterprise tier, but the hosting region for Botpress Cloud, and whether a buyer can choose it, is not stated. Self-hosting belongs to the older open-source v12 lineage rather than the current cloud platform and does not apply to Botpress Cloud. 2026-09-05 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
A vendor-supplied catalog plus a named agent library. The Hub carries production-ready templates for customer support, appointment scheduling and lead qualification, including a Kitchen Sink template demonstrating user data loading, workflow routing and live agent handoff, adopted by customizing instructions and swapping in a knowledge base. Alongside it the Studio documentation publishes a set of prebuilt Agents a builder drops into a bot: Summary, Personality, Policy, Translator, Knowledge, HITL, Vision and Analytics. Sourcebotpress.com/hubread 2026-09-05 |
|
| Triggers & Channel Coverage | Full |
|
Channels are a first-class platform surface with its own navigation section, covering webchat, WhatsApp, Instagram, Messenger and Slack among others, with voice available through a maintained Twilio Voice integration that lets a bot take a phone call, and one build reaching all of them. The agent also initiates rather than only receiving: Triggers are a documented Studio concept, a Fixed Schedule card runs work on a timetable, and the documentation covers sending reminders into conversations. Sourcebotpress.com/integrations/twilio-voiceread 2026-09-05 |
|
| Model Flexibility & Routing | Full |
|
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, with the LLMz autonomous engine versioned independently and described as written to stay agnostic to variance between models. Sourcebotpress.com/docs/studio/concepts/bot-settingsread 2026-09-05 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
The platform is callable from outside and extensible in code through several documented surfaces: a public API Reference in the top-level navigation, a Botpress Cloud API, an Agent Development Kit published as 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 first-party Model Context Protocol material tying MCP tool access to the Autonomous Node. Sourcebotpress.com/docs/studio/get-started/manage-your-agent/edit-appearanceread 2026-09-05 |
|
| Testing, Debugging & Optimization | Partial |
|
The Emulator supports real-time conversation testing with an inspect window exposing 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. These are manual inspect-and-fix loops; no test suite, regression harness, scored evaluation or pass rate is documented, 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 |
|
| Browser & Computer Use | Not documented |
|
Botpress offers no browser control, hosted session or computer use in the platform or its documentation. The route out is stated positively and it is programmatic: agents act through Hub integrations, action cards, an Execute Code card and API calls, and reach people through channel surfaces. A Vision Agent ships in the prebuilt agent library, which reads images rather than operating an interface. Sourcebotpress.com/hubread 2026-09-05 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Pricing
$150/mo
conversations
Included quota
Plus (entry paid, $150/mo): 250 conversations/mo with bundled AI quota, 3 seats, unlimited AI agents, WhatsApp channel, whitelabel webchat, human handoff, and AI conversation insights. Free: 100 conversations/mo (hard cap), 1 seat, 3 agents.
What is public
Botpress overhauled pricing on May 14, 2026 (new workspaces): conversation-based tiers with LLM "AI Spend" now bundled in (previously billed separately at provider cost). Tiers: Free (100 conversations/mo, 1 seat, 3 agents), Plus $150/mo (3 seats, 250 conversations, unlimited agents, WhatsApp, whitelabel), Team $750/mo (unlimited seats, 1,500 conversations, RBAC, routing, analytics), and custom Enterprise (voice, SLAs, data residency). Existing workspaces keep the older message-based + separate-AI-Spend pricing.
Billing mechanics
New model: you buy a monthly conversation allotment per tier, and each conversation includes a proportional AI quota (LLM inference, embeddings, web search bundled — no separate token math, no markup). Hit the conversation limit and a 100-conversation pack auto-adds (~$65, ~$0.65/convo) so bots keep running; warnings fire at 80%/90%. Studio/ADK users still see an AI-spend meter; if the AI quota is hit before the conversation limit, a conversation pack triggers. (Legacy workspaces: base plan + separate usage-based AI Spend at provider cost.)
Cost watchouts
Conversation packs auto-add on overage (no hard stop on paid), third-party channel fees (WhatsApp via Meta, SMS/voice via Twilio) billed separately and can exceed the subscription, 'renewal shock' from traffic spikes, legacy workspaces still pay separate AI Spend
Variable cost rationale
New model bundles AI into conversation packs, smoothing token-cost surprises, but auto-overage packs and separately-billed channel fees still make total spend traffic-dependent
Additional watchouts
Pricing just changed (May 2026) and old/new regimes coexist; channel fees and (on legacy plans) separate AI Spend make totals less predictable; the Free tier's 100-conversation cap is quickly exhausted in testing
Overage / add-ons
Conversation overage auto-bills as 100-packs (~$65, ~$0.65/conversation); no hard stop on paid plans. Free is a hard 100-conversation cap with no add-ons. Hitting the bundled AI quota early also triggers a conversation pack.
Sales call required
No, self serve available
Free / trial
Free tier
Lowest paid plan
Free; $150/mo+
Commercial notes
Open-source roots (self-hosting belongs to the older v12 lineage, not Botpress Cloud); visual Studio + code-first ADK; integrates GPT/Claude/Gemini; ~500K+ users, 25K+ Discord; AI usage carries no markup; SOC 2 Type II targeted; "Always Alive" now included on all paid plans
Key ambiguities
Two pricing regimes run in parallel (before and after 14 May 2026), and the older figures (Plus $89, Team $495, plus separate AI Spend) still circulate; the bundled AI quota per conversation isn't published as a hard number.
Cancellation / refund
Self-serve monthly on Plus/Team (annual discounts ~11%); Enterprise on custom multi-year contracts; overages bill automatically without hard stops
Support SLA / resale
Team adds dedicated solution-engineering support; Enterprise adds formal SLAs, dedicated support manager, custom data residency, and white-glove onboarding; new 'Built For You' done-for-you service and 'Desk' AI helpdesk are separate offerings
Missing data
The exact bundled AI quota per conversation isn't published, and how old plans map to new ones is unclear; Enterprise pricing is custom (reportedly ~$2,000/mo+ on multi-year terms).
Related vendors
- Decagon — AI agent platform purpose-built for customer support, with deep…
- 5.Y — Singapore early-stage platform whose GLUCOSE product deploys…
- Ada — Agentic customer experience platform whose AI agents autonomously…
- Aisera — Enterprise agentic AI platform that orchestrates specialized agents…
- ASAPP — Generative AI for enterprise contact centers that plugs into…
- Assembled — AI customer support orchestration platform that unifies autonomous…
Alternatives to Botpress
The closest documented capability profiles to Botpress among customer support agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Chatbase10.0 / 14A lighter documented profile than BotpressBotpress vs Chatbase →
- Kommunicate10.0 / 14A lighter documented profile than BotpressBotpress vs Kommunicate →
- Retell AI12.0 / 14Fuller documented coverage on Observability & Auditability and Testing, Debugging & Optimization
- Gallabox11.5 / 14Fuller documented coverage on Observability & Auditability and Testing, Debugging & Optimization
- Aisera11.0 / 14Fuller documented coverage on Observability & Auditability and Testing, Debugging & Optimization
- Gorgias10.0 / 14Adds documented Deployment & Data Residency
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded