Developer Tools / Agent Development
A curated learning roadmap for building production AI agents, covering OpenAI, Anthropic, MCP, harnesses, evals, memory, and safety. The README organizes the material into phases with exercises and a prioritized reading table.
The page clearly presents a useful AI-builder resource: a structured roadmap with 114 official resources, phased learning sections, and concrete build exercises for agent foundations, MCP, memory, harnesses, coding agents, and evals. The repository evidence is enough to understand its purpose and who it is for.
The crawl shows the roadmap structure well, but not the full contents of the reading table, so it is hard to tell how exhaustive or current the resource list is. There is also no visible license, release activity, or maintenance signal beyond the repo snapshot.
Last evaluated 92 days ago. Current rank #1820. Holding steady in the rankings.
CodeGraph is a local code knowledge graph for AI coding agents like Claude Code, Cursor, Codex, OpenCode, and Hermes Agent. It aims to cut token use, tool calls, and runtime by letting agents query pre-indexed code structure instead of scanning files repeatedly.
Mercemur is a store automation platform with three interfaces: a REST API, an MCP server for AI agents, and a CLI for editing storefronts as files. The docs show authentication, scopes, rate limits, error handling, pagination, idempotency, and a large API surface for catalogue, orders, customers, pricing, and money.
A zero-dependency C++23 CLI and MCP server that gives coding agents a ranked map of a repository, including call context, blast radius, and tests to run.
Traccia is an AI agent observability and governance platform with OpenTelemetry-native tracing, runtime policy enforcement, prompt registry, evals, cost attribution, and compliance evidence export.
