Developer Tools / AI Agent Infrastructure
Open-source execution runtime for production agents. It records tool and LLM calls as durable steps, supports resume after interruption, and lets teams allow, deny, or approve steps with human oversight.
The page clearly presents a real AI infrastructure project aimed at production agents, with enough visible README content to understand the product, its workflow, and how to try it. It includes quick start commands, docs topics, Python and TypeScript examples, an HTTP API, CLI, policy controls, and deployment notes, which makes it suitable for a public listing.
The snapshot does not show the full README content, so it is still unclear how mature the project is, what integrations or model providers it supports, and whether there are screenshots, demos, or release details beyond the basic setup and docs outline.
Last evaluated 31 days ago. Current rank #453. Down 4 spots 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.
Lumae is a free native macOS screen recorder and screenshot tool for polished demos, with automatic zooms, cursor smoothing, motion blur, captions, voiceover, and annotated screenshots. It also exposes editing commands over MCP so agents like Claude Code or Claude Desktop can edit projects directly.
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.
