Search

Animated data-flow diagrams your AI agent can write. CLI.

Install curated AI agent skills for Claude Code, Codex, Cursor, OpenCode, and Kimi: zero dependencies, one command.

🔍 Blast radius & caller analysis for legacy Java. Heuristic-ranked impact audit — npm-installable agent skill for OpenCode, Codex, Claude Code, Copilot, Gemini & DeepCode.

Bootstrap oh-my-design skills + agents into your project. After install, talk to your AI coding agent in natural language — no other CLI commands.

Smart Agent for Claude Code — learn skills from your coding conversations

Bash + markdown-skills framework for structured multi-agent development with Claude Code

Pi extension for isolated skill pressure testing with baseline and skill-present subagents.

Skill-first local CI runner -- run your CI jobs locally and fix failures with AI

Capability-based IFC, streaming-native cascaded guardrails, and an eval-to-guardrail compiler for LLM agents.

A lightweight Python framework for building single and multi-agent LLM applications.

Human steers. Agent builds. The AI agent starter kit.

🐟 AZERCLAW — Open-source, BYOK AI agent for your terminal. Your AI, Your Keys, Your Way.

Common Agent Runtime — a deterministic execution layer for AI agents

Go AI embeddable AI agent elements for the browser. Six chat layouts (floating / inline / modal / drawer / page / standalone) plus an iframe wrapper. Shadow-DOM-isolated, streaming SSE.

Ollama agent router and local LLM router for OpenAI-compatible model routing, GPU-aware queues, async jobs, and CLI configuration.

Cross-framework AI agent observability and reliability shim

LangGraph.js checkpoint saver for Cloudflare D1

Drop-in AI agent controlled via Telegram, sandboxed to its folder

Ephemeral coding-agent runner: orchestrates Pi CLI via Docker for automated code modifications with validation

Placeholder package. The real release is coming soon.