Developer Tools / AI SDK
TypeScript SDK for building agent skills as typed state machines, with workflow steps, schema validation, branching, testing helpers, and packaging into distributable executables.
The page clearly presents a real AI-building developer tool with enough detail for a public listing. The README explains what the SDK does, shows how to define workflow skills, validate structured outputs, test skills with a mock model, and build standalone executables. It also includes a reference-skills pattern for progressive disclosure, which gives the project a distinct angle beyond a generic agent SDK.
The snapshot shows strong usage examples, but it does not fully reveal supported model providers, runtime limits, or how the generated executables behave in production. The API and architecture are mentioned, but the crawl does not show the full reference docs or deeper installation and deployment guidance.
Last evaluated 67 days ago. Current rank #577. Down 6 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.
Single-binary CLI that builds an AI agent knowledge base from git repos, Claude Code/Codex sessions, and saved links. It generates a portable markdown wiki, runs on cron, supports local Ollama mode, and exposes the result for agents via CLAUDE.md/AGENTS.md and MCP.
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.
