The living ecosystem where AI agents learn from real-world work through iterative workflow loops, reusable experience, and collective training signal exchange.
-
Updated
Jun 20, 2026
The living ecosystem where AI agents learn from real-world work through iterative workflow loops, reusable experience, and collective training signal exchange.
Your agents are guessing at APIs. Give them the actual Agent-Native spec. 1500+ API's Ready To-Use skills, Compile any API spec into a lean, agent-native format. 10× smaller. OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman.
Best DX + AX for Building the Best UX — An ultra-lightweight (~2.5KB) pure vanilla JavaScript framework with signal-based reactivity and built-in AI agent support.
SpecMem: 🧠 Unified Agent Experience and Cognitive Memory for Every Coding Agent
Wish-style SSH applications built with OpenTUI and deployed in a Cloudflare Container.
LAP skills marketplace for Claude Code - 1,500+ auto-generated API skills
Open source tooling and scoring framework to measure how well services work for AI agents.
Put your company's private web online, on your Cloudflare account.
Mount MCP servers as a filesystem. Plan 9 for the agent era.
Open Reflection Protocol — Turn agent failures into regression tests, reusable lessons, and measurable improvements. Built on OpenTelemetry.
Stop teaching your coding agent the same lesson twice.
AX Score - The Lighthouse for AI Agent Experience. Measure how agent-friendly your website or API is.
grep for your Claude Code conversations — regex + semantic search, agent-friendly output
LAP benchmark results — 500 runs, 50 specs, 5 formats. Agents run 35% cheaper with LAP.
Run your agents full-auto in loops. When one actually needs a human, it pings your phone and waits 📟
Mount MCP servers as filesystems to access reads via standard file commands and perform writes through a CLI tool.
Score any OpenAPI spec /100 for DevEx + Agent Experience. x-capability pattern, Spectral governance, MCP generator.
Assets related to ensuring OpenAPIs are AI-Ready. This is part of a workshop delivered at the APIOps Conference in Helsinki, and a Jentic Webinar.. It demonstrates Jentic's API AI-Readiness Framework and CLI for scoring and improving OpenAPI Descriptions such that agents can safely discover and utilize.
Fast, agent-friendly Vercel CLI replacement. Bun-powered, JSON-first.
A living list of tools, frameworks, and projects for building agent-friendly systems
Add a description, image, and links to the agent-experience topic page so that developers can more easily learn about it.
To associate your repository with the agent-experience topic, visit your repo's landing page and select "manage topics."