Developer Tools / Code Assistant
A blog post describing an evaluation harness for comparing agentic coding tools and prompts across realistic SWE tasks, with token-cost results and model-specific behavior notes.
The page is clearly about AI agent tooling and evaluation, not just a general blog post. It includes a concrete experiment setup, named tools, model/task details, results, and observations about how coding agents behave, which makes it useful for a public listing.
It is still marked WIP, and the snapshot cuts off before the end of the writeup. There’s no downloadable harness, code repo, or clear call to action for someone who wants to reuse the evaluation setup.
Last evaluated 89 days ago. Current rank #1946. Down 1 spot 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.
