Docker Blog
-
Jan 22, 2026
Using MCP Servers: From Quick Tools to Multi-Agent Systems
Run MCP servers without runtime pain. Use Docker’s MCP Toolkit, Catalog, Gateway, and cagent to scale from single tools to multi-agent systems.
Mike ColemanRead now
-
Jan 22, 2026
Your Dependencies Don’t Care About Your FIPS Configuration
FIPS images alone won’t ensure compliance. Learn how prebuilt native deps can bypass your crypto boundary—and how to build, test, and ship FIPS-compatible apps.
Laurent GoderreRead now
-
Jan 16, 2026
Making (Very) Small LLMs Smarter
Run tiny LLMs locally and still get helpful code. Use vector search to feed the right snippets with Docker Model Runner, LangChainJS, and Nova.
Philippe CharrièreRead now
-
Guest Contributor Jan 15, 2026
Permission-Aware RAG: End-to-End Testing with the SpiceDB Testcontainer
Learn how to validate permissions in RAG pipelines end to end using Testcontainers and SpiceDB – covering setup, test data, and policy checks developers can trust.
Sohan MaheshwarRead now
-
Jan 15, 2026
OpenCode with Docker Model Runner for Private AI Coding
Configure OpenCode to use Docker Model Runner for a private, cost-aware coding assistant. Run models locally via an OpenAI-compatible API with full control.
Ignasi Lopez LunaRead now
-
Jan 14, 2026
Safer Docker Hub Pulls via a Sonatype-Protected Proxy
Why a “protected repo”? Modern teams depend on public container images, yet most environments lack a single, auditable control point for what gets pulled and when. This often leads to three operational challenges: Inconsistent or improvised base images that drift across teams and pipelines. Exposure to new CVEs when tags remain unchanged but upstream content…
Anna ChernyshovaandAndrés PérezRead now
-
Jan 9, 2026
Security Is a Developer Experience Problem, Rooted in Our Foundations
If we want better security outcomes without slowing teams down, we should start where software actually starts. That requires secure foundations, like hardened images, that are safe by default. With better foundations, security becomes quieter, development becomes smoother, and the entire system works the way it should.
Tushar JainRead now
-
Jan 6, 2026
Deterministic AI Testing with Session Recording in cagent
AI agents introduce a challenge that traditional software doesn’t have: non-determinism. The same prompt can produce different outputs across runs, making reliable testing difficult. Add API costs and latency to the mix, and developer productivity takes a hit. Session recording in cagent addresses this directly. Record an AI interaction once, replay it indefinitely—with identical results,…
Stan HamaraRead now