Developer Tools / AI Agent Frameworks
Kastor is an open-source Go toolchain for defining AI agents, tools, and prompts in HCL. It treats agents like versioned infrastructure, with build, plan, and apply workflows, code generation for frameworks like LangGraph, and drift-aware management on hosted platforms.
The page clearly describes a real AI developer tool with a concrete purpose: a declarative, Terraform-style workflow for AI agents. The README gives enough detail to understand what it does, how it’s installed, how it’s used, and what problem it solves. It also includes an example, build steps, and implementation details that make it useful for an AI-builder directory listing.
The snapshot does not show broader ecosystem evidence such as releases, adoption, screenshots, or independent usage examples. It also doesn’t make it fully clear which hosted platforms are supported beyond the general plan/apply description.
Last evaluated just now. Current rank #81. Down 3 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.
A lightweight React Markdown renderer with built-in LaTeX, syntax highlighting, streaming-safe rendering, and security-focused defaults.
Claude Code plugin that blocks dependency edits until a fresh, source-cited version check is recorded, helping prevent hallucinated or stale package versions across npm, pip, Poetry/uv, Cargo, and NuGet.
SigMap is a deterministic grounding layer for AI code work. It generates a signature-and-evidence map, helps pick relevant files, validates coverage, and judges whether an AI answer is grounded in the repo.
