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.
-
Build TypeScript spreadsheet import and export workflows with hucre
Use hucre when a coding agent needs to add zero-dependency XLSX, CSV, ODS, JSON, NDJSON, or XML spreadsheet parsing and writing to TypeScript or edge-runtime projects.
-
Use production-agent tutorial playbooks from Agents Towards Production
Use Agents Towards Production when an agent needs code-first tutorial playbooks for production agent features such as state, memory, retrieval, evaluation, deployment, observability, and guardrails.
-
Build agent-maintainable reactive UI with ArrowJS
Use ArrowJS when a coding agent needs to add or maintain small reactive web interfaces using DOM-native JavaScript, template literals, SSR/hydration packages, and optional WASM sandboxing.
-
Wire transcript-derived coding-agent memory with deja-vu
Use deja-vu when Codex, Claude Code, Cursor, OpenClaw, Copilot, and other local coding agents need shared recall from session history already written on disk.
-
Inspect and export Excel workbooks from the terminal with xleak
Use xleak when an agent needs to inspect, search, verify formulas, and export Excel, ODS, CSV, or TSV files from a terminal without opening a desktop spreadsheet app.
-
Run graph and vector memory backends for agents with NornicDB
Use NornicDB when an agent workflow needs a local or self-hosted graph, vector, and temporal database for GraphRAG, memory decay, historical reads, and Neo4j/Qdrant-compatible retrieval.
-
Build and optimize agent eval workflows with Kiln
Use Kiln to create eval datasets, rate outputs, optimize prompts and models, and ship the same AI task or agent definition from a local workbench into production code.
-
Run sandboxed multi-language code execution with Judge0
Use Judge0 when an agent workflow needs a self-hostable HTTP API for compiling and running untrusted or model-generated code across many languages with structured results.
-
Run private RAG and MCP skill workspaces with Yuxi
Deploy Yuxi when an agent team needs a private, multi-tenant knowledge workspace that combines document RAG, knowledge graphs, MCP tools, skills, sandboxes, and permissions.
-
Run repo-local story, handover, and review workflows with Storybloq
Use Storybloq when Claude Code or Codex needs durable repo-local stories, plans, handovers, lessons, and review evidence instead of rediscovering project state each session.