# MindMeld *

**Canonical:** https://apis.io/providers/mindmeld/  
**Website:** https://www.mindmeld.com  
**APIs profiled:** 0

MindMeld is an open-source conversational-AI platform for building deep-domain voice interfaces and chatbots, originally developed by the GV-backed startup MindMeld (formerly Expect Labs), acquired by Cisco in 2017 and open-sourced in 2019. Distributed as the `mindmeld` Python framework (Apache-2.0), it provides tooling for every step of a modern conversational workflow — domain and intent classification, entity recognition and resolution, and dialogue management — along with reusable application Blueprints for use cases such as food ordering, video discovery, and home-assistant experiences. MindMeld powers the Webex Assistant and other Cisco conversational products.

## Kin Score — 12.4 / 100 (emerging)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 12.4).

| Facet | Score |
|---|---|
| Discoverability | 50.0 |
| Contract Quality | 0.0 |
| Governance | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 18.4 |
| Developer Ergonomics | 25.0 |
| Commercial Clarity | 0.0 |
| Access Clarity | 0.0 |

## Agent readiness — 0.0 (human-only)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | no |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Unknown — onboarding: unknown, pricing: unknown, trial: no (confidence: low).

## Security (1)

- **Mindmeld Domain Security** — TLSv1.3

## Tags

Company, Artificial Intelligence, Conversational AI, Chatbots, Natural Language Processing, Voice Interfaces, Machine-Learning, Open-Source, Python

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/mindmeld/). Scores are computed from the provider's own public artifacts under a published rubric.