# Dyno Therapeutics

**Canonical:** https://apis.io/providers/dyno-therapeutics/  
**Website:** https://dynotx.com  
**APIs profiled:** 0

Dyno Therapeutics is an AI-driven biotechnology company in Watertown, Massachusetts that combines machine learning with high-throughput in vivo experimentation to engineer adeno-associated virus (AAV) vectors for gene therapy. Its CapsidMap platform designs novel AAV capsids optimized for tissue targeting, immune evasion, manufacturability, and payload packaging, advanced through partnerships with pharmaceutical companies. Dyno also open-sources protein-design tooling for the research community, including the dyno-phi CLI for its Phi protein-design platform and the Psi-1 de novo binder-design model.

## Kin Score — 12.7 / 100 (emerging)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 12.7).

| Facet | Score |
|---|---|
| Discoverability | 50.0 |
| Contract Quality | 0.0 |
| Governance | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 2.6 |
| Developer Ergonomics | 16.7 |
| Commercial Clarity | 21.1 |
| Access Clarity | 21.1 |

Regulatory layer — **Health**: 17.5 (matched via tags).

## 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)

- **Dyno Therapeutics Domain Security** — TLSv1.3 · HSTS · DMARC

## Tags

Company, Life Sciences, Biotechnology, Gene Therapy, AAV, Machine-Learning, Protein Design, Drug Discovery

---

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