Prometheus vs Speakeasy
Side-by-side trajectory, velocity, and editorial themes.
Prometheus enters 3.12 RC while running a coordinated security backport across the 3.5 LTS line.
Prometheus published a 3.12.0 release candidate with PromQL and Service Discovery additions, TSDB performance work, and security fixes for a remote-write denial-of-service and a STAC secret leak. In the same window, 3.11.3 and 3.5.3 shipped coordinated security fixes for snappy decoding, AzureAD client_secret handling, and an old-UI XSS, and the prior 3.11.2/3.5.2 pair fixed a metric-name XSS in the web UI. The project is clearly maintaining 3.5 as a long-term branch alongside the active 3.x line.
Cadence is dominated by responsible-disclosure security work, with feature additions concentrated in the upcoming 3.12 release. The fact that 3.5 keeps receiving coordinated backports months after 3.11 suggests Prometheus is informally treating 3.5 as a stable LTS for environments that cannot upgrade quickly.
Expect 3.12.0 to ship final within a few weeks given the RC has already landed, and a 3.5.4 backport to follow the next security disclosure rather than the next feature batch.
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 Prometheus →
See more alternatives to Speakeasy →