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.
-
Run deterministic browser steps with settled screenshots and event logs for agents
Use Agent Browser Protocol when an agent needs browser actions to resolve into stable step results, complete with screenshots and surfaced events, instead of racing an always-live browser session.
-
Manage multi-agent coding sessions from one terminal mission control with Agent Deck
Use Agent Deck when an operator needs one keyboard-first terminal to monitor, switch, fork, sandbox, and organize many coding-agent sessions instead of juggling tabs, panes, and worktrees by hand.
-
Statically scan agent repos for prompt injection and unsafe MCP configs with Agent Audit
Audit agent code, prompts, and MCP configuration for prompt-injection surfaces, taint issues, and unsafe tool exposure before shipping.
-
Define file-native Git workflows for agents with GitAgent
Store prompts, task chains, and reusable agent workflows as versioned project files so teams can review and reuse agent behavior through Git.
-
Turn mixed local folders into a queryable knowledge graph with Graphify
Ingest code, docs, PDFs, images, and video from local folders into a searchable knowledge graph so agents can follow entities and relationships instead of only raw text.
-
Run multi-agent code review rounds with structured reviewer discourse before human approval
Use Open Code Review when an agent needs several reviewer personas to inspect a diff, debate findings, and synthesize review output before a human approves, posts, or acts on the review.
-
Test API authorization flows with Hadrian
Lets an agent exercise REST, GraphQL, and gRPC authorization paths with YAML-defined role tests so BOLA, BFLA, broken authentication, and related API flaws are caught before release.
-
Publish installable pull-request package previews before release with pkg.pr.new
Use pkg.pr.new when an agent needs an installable preview build from a pull request so reviewers can test a package before the maintainer cuts a real npm release.
-
Catch benchmark regressions in pull requests before slowdowns ship with CodSpeed
Use CodSpeed when an agent needs benchmark runs compared in CI and surfaced on pull requests before performance regressions merge.
-
Reduce agent token burn on repo-scale coding commands with the rtk CLI proxy
Use rtk when an agent keeps wasting context on noisy shell output from large repos and you need smaller command responses before the model sees them.