Directus vs Speakeasy
Side-by-side trajectory, velocity, and editorial themes.
Directus is on a steady weekly cadence with AI tooling deepening on every release.
Directus is shipping weekly point releases on the 11.17.x line, each carrying a mix of small UI features, AI-related additions, and dependency hygiene. The recent stretch added a /ai/object structured-generation endpoint, an asset cache-revalidation header (ASSETS_CACHE_REVALIDATE), background data imports with timeout and concurrency controls, a Tabs group interface that absorbs a previously-extension feature, and comparison-modal improvements (timezone-aware datetime, modified-only view). UI work in 11.17.0 also shrunk the app to 90% and converted px to rem — flagged as a potential breaking change for extensions with hardcoded pixel values.
Two parallel arcs: (1) AI Assistant continues to grow — image/PDF upload, multi-provider model refresh (Anthropic, Google, OpenAI), an Anthropic tool-search adapter for context efficiency, and now a structured-object endpoint for inline experiences; (2) the app shell is being modernized — rem-based sizing, native replacements for previously third-party UI primitives (reka, native Tabs), and migration of @directus/visual-editing into the monorepo. Bug-fix volume is high but consistent — typical of a project absorbing a wide community contribution stream.
Expect continued weekly 11.17.x cuts focused on the AI surface (more inline AI-aware components, more structured-output use cases) and the in-progress monorepo consolidation. The 90%-UI shrink will likely require an extensions-side migration cycle before a major version cut.
Speakeasy's Gram is shipping daily — multi-MCP chat, Codex hooks, and long-running assistants in one week.
Speakeasy's Gram platform is moving at multiple-releases-per-day cadence across two trains. The Platform train has shipped issuer-gated OAuth from the playground, release-stage badges, OpenRouter credit monitoring with auto-reconciliation, a v2 assistant runtime foundation, hook telemetry attribution in Datadog, Codex (OpenAI) hooks support, OTEL forwarding to customer destinations, Slack Block Kit with interactive replies, and a full migration to WorkOS-native auth. The Elements train added multi-MCP server chat configuration with namespaced tool merging, and a resilience fix so a failing MCP server doesn't wipe out tools from healthy ones in the same chat. Long-running assistants gained token-aware context compaction, self-wake triggers, and long-term memory via vector embeddings.
Gram is being built as an MCP-native assistant platform — every release reads like infrastructure for assistants that compose many MCP servers, run for a long time, recover from failures, and integrate with enterprise auth and telemetry. The architectural choices (multi-MCP merging with namespacing, per-assistant Fly apps, OTEL forwarding, WorkOS) say the target buyer is a platform team building real production agents, not a tinkerer. Self-healing chat history, credit-exhaustion 402 responses, and per-server failure isolation are the kinds of features that only matter at scale — Speakeasy is building for that scale already.
Expect Gram to formalize its v2 assistant runtime in the next sprint, add usage-based pricing tied to OpenRouter credits and Fly machine-hours, and ship deeper MCP server lifecycle tooling (version pinning, canary deploys for new tool versions). A managed MCP server catalog is a plausible adjacency given how much of the platform already presumes multi-MCP composition.
See more alternatives to Directus →
See more alternatives to Speakeasy →