-
Notifications
You must be signed in to change notification settings - Fork 0
Roadmap
Jerome Louvel edited this page Mar 24, 2026
·
35 revisions
The goal of this version is to deliver a MVP to enable common AI integration use cases and grow our community.
- Declarative applied capability exposing Agent Skills
- Declarative MCP exposing Resources and Prompts (Tools only so far)
- Support for lookups as part of API call steps
- Authenticate API and MCP Server consumers and manage permissions
- Reusable source HTTP adapter declaration across capabilities
- Declarative applied capabilities with reused source capabilities
- Publish FAQ in the wiki
- Publish Naftiko JSON Structure
- Publish Naftiko Skill based on Naftiko CLI
- Publish Naftiko Ruleset based on Spectral
- Publish Maven Artifacts to Maven Central
- Publish Javadocs to Javadoc.io
- Publish Docker Image to Docker Hub
- Provide GitHub Action template based on Super Linter
The goal of this version is to deliver a MVP to enable common AI integration use cases and grow our community.
- Add support for authentication in the MCP server adapter
- Facilitate integration with MCP and AI gateways
- Facilitate skills publication in skills marketplaces
- Support Webhook server adapter for workflow automation
- Factorize capability core with "aggregates" of functions initially, entities and events later
- Add conditional steps, for-each steps, parallel-join
- Allow reuse of "binds" blocks across capabilities
- Enable API token refresh flows
- Facilitate integration with API gateways
- Support A2A server adapter with tool discovery and execution
- OpenAPI-to-Naftiko import tooling — generate a starter capability YAML from an existing OpenAPI file
- Publish starter capability templates (golden path skeletons with all required fields pre-filled)
- Provide Control port
- Usable via REST API, usable via Naftiko CLI, packaged as capability
- Usable via webapp as Docker Desktop Extension
The goal of this version is to deliver a stable MVP, including a stable Naftiko Specification.
- Rightsize AI context
- Evolve MCP server adapter to support server-side code mode like CloudFlare
- Enhance API reusability
- Add support for resiliency patterns (retry, circuit breaker, rate limiter, time limiter, bulkhead, cache, fallback)
- Publish reference bridge capabilities (RSS/Atom XML feeds, XML/SOAP, CSV, etc.)
- Provide enhanced security
- Facilitate authorization management
- Incorporate community feedback
- Increase test coverage and overall quality
The goal of this version is to release our first version ready for production.
- Incorporate community feedback
- Solidify the existing beta version scope
- Increase test coverage and overall quality
- Publish JSON Schema to JSON Schema Store
The goal of this version is to broaden the platform surface area based on production learnings.
- Add support for gRPC and tRPC as server adapters
- Add full resiliency patterns (rate limiter, time limiter, bulkhead, cache)
- Facilitate integration with Keycloak, OpenFGA
- Provide Control webapp (per Capability)
- Publish Docker Desktop Extension to Docker Hub
- Fabric discovery of published capabilities for consumers