AI coding agent spend is scattered across every developer's machine: each agent keeps its own logs, in its own format, under its own plan. Tokenbase reads those logs where they already live and rolls them up into spend and usage by team, with Claude Code, Codex, Copilot, and Cursor normalized to one basis so the numbers actually compare. Everything is measured from the agents' own logs, not modeled from estimates. You can even use it to help you get hired!
Every TypeScript agent SDK I tried treated Azure OpenAI as a second-class citizen. Stratus flips that. It's built Azure-first and includes everything you'd expect: tools, subagents, handoffs, sessions, streaming, structured output with Zod, guardrails, hooks, tracing, and MCP client support. Plus Code Mode, which lets the model write code to orchestrate tools in a loop instead of one call per turn. If you're on Azure and tired of adapter tax, this is for you.
Feedstock is a web crawler and scraper built for TypeScript developers who want speed without giving up control. It runs on Bun, supports Playwright, CDP, and Lightpanda backends, and handles deep crawling, markdown generation, structured extraction (CSS, XPath, regex), anti-bot detection, proxy rotation, and SQLite caching out of the box. If you've used crawl4ai in Python and wished it existed natively in TypeScript, this is that. (
