Blog
News, launch notes, guides, and comparisons for builders exploring reusable AI agent skills, trust signals, and ecosystem shifts.
Latest posts
Follow product updates, editorial pieces, and practical explainers that help users navigate the marketplace and adjacent agent ecosystems.
-
Resolve syntax-aware Git merge conflicts before escalating to manual surgery with Mergiraf
Use Mergiraf to let an agent attempt tree-aware conflict resolution during merge, rebase, revert, or cherry-pick before falling back to manual edits.
-
Tail multi-pod Kubernetes logs by label during incidents with Stern
Aggregate and follow logs from matching Kubernetes pods during incident triage without hopping pod by pod.
-
Watch Kubernetes resources explain rollout stalls and surface live status transitions with kubespy
Follow a Kubernetes workload live so an agent can explain why it is pending, failing, or not becoming ready.
-
Autofix common Nix anti-patterns before style drift spreads with Statix
Lint Nix expressions and automatically rewrite common anti-patterns before review or refactor work.
-
Estimate Terraform and OpenTofu cost deltas before infrastructure changes merge with Infracost
Show projected cloud cost increases or savings from Terraform and OpenTofu plans before a PR merges.
-
Scan Kubernetes clusters and manifests for security posture drift with Kubescape
Run Kubernetes security and compliance scans against manifests or live clusters before rollout or audit.
-
Scan Python code for risky security patterns with Bandit before review or release
Catch insecure Python calls, weak crypto usage, shell injection risks, and similar patterns before merge or release.
-
Score RAG answer quality and retrieval quality before rollout with Ragas
Measure whether a RAG change actually improved answers and retrieval, instead of guessing from a few spot checks.
-
Run repeatable model and agent eval suites and inspect scoring traces with Inspect AI
Run benchmark-style eval suites against models or agents, then inspect scored traces instead of relying on ad hoc chats and gut feel.
-
Probe ML and LLM systems for regressions and vulnerabilities with Giskard
Run automated red-team and failure scans against an LLM or RAG app before users find the breakage.