Category

Librarys

45 saved librarys.

GitHub LibraryFeatured

Garden Skills - production skill pack for Claude Code, Cursor, and Codex

Three carefully-scoped skills: web-design-engineer (with an anti-cliche blocklist that breaks the generic-AI-landing-page loop), gpt-image-2 (80+ templates, three runtime modes including advisor-only fallback), and kb-retriever (layered data_structure.md navigation for bounded local-KB retrieval). Tested across Claude Code, Claude.ai, Cursor, Codex, Gemini, OpenCode.

Why I saved this - The web-design skill's anti-cliche blocklist is the most opinionated take on 'stop producing the same hero + 3 cards' I've seen.

#claude-code #skills #cursor #codex #gemini-cli

gpt_image_2_skill - 162-prompt gallery and skill for GPT Image 2

Curated gallery, CLI, and agentic skill for OpenAI's GPT Image 2. 162 reusable prompts across anime, gaming, photography, UI/UX, and research-figure categories. Supports text-to-image, mask-edit, multi-reference edits, and batch ops. Installable as a Claude Code plugin, Codex skill, or standalone CLI via uv.

Why I saved this - Bigger prompt gallery than garden-skills' gpt-image-2 (162 vs 80+) but narrower in scope - this is just the image skill, not a multi-skill pack.

#claude-code #codex #skills #image-generation #python

Foundry - foundation layer for agentic intelligence

Python agent runtime and framework aimed at production agentic systems. Early but already has 800+ stars and a clear shape around runtime primitives.

#agent-framework #agent-runtime #ai-agent #python #multi-agent

SkVM - language VM for agent skills

Runtime that treats agent skills as first-class programs, providing a structured execution model for skill composition, isolation, and reuse.

#skills #agent-runtime #developer-tools #typescript

engram - context spine for AI coding agents

Aggregates six providers (graph, git, MemPalace, Context7, Obsidian) into rich context packets that fire on every agent Read. Local SQLite, no native deps, no cloud.

#claude-code #context-engineering #agent-memory #code-intelligence #self-hosted

OQP - verification protocol for AI agents

MCP-compatible spec defining four endpoints (capabilities, workflows, execute, assess-risk) so agents can prove a shipped change satisfies business requirements before it goes live.

#mcp #agent-security #evals #verification #ai-agent

GitHub LibraryFeatured

AgentBox - SDK to run coding agents in any sandbox

One SDK to run Claude Code, Codex, or OpenCode inside Docker, E2B, Modal, Daytona, or Vercel sandboxes - boots each agent's native server (JSON-RPC, HTTP/SSE) instead of using non-interactive --print mode.

#claude-code #codex #opencode #sandbox #agent-security

LABE - legal action boundary eval

Public benchmark that tests an agent at the moment it's about to take a high-impact legal action. Same harness, baseline vs verified, measures unjustified action drops and goal-completion gains.

#evals #agent-security #ai-agent #benchmark

pydantic-deepagents - Claude Code-style agents in Python

Pydantic AI library for building deep agents with tool calling, sandboxed execution, multi-agent teams, skills, and checkpoints. Same shape as Claude Code, scriptable from Python.

#python #claude-code #multi-agent #skills #agent-framework

Wax - on-device RAG memory layer in Swift

Single-file Swift memory layer with sub-millisecond RAG on Apple Silicon via CoreML and Metal. No server, no API, ships an MCP server out of the box.

#mcp #agent-memory #macos

vurb.ts - Express.js for MCP servers

TypeScript framework for building MCP servers with type-safe tools, presenters that control what the LLM sees, and built-in PII redaction. Targets Claude Code, Cursor, and other MCP clients.

#mcp #typescript #claude-code #framework

LLM-Rosetta - translate API calls between providers

Translator that maps OpenAI, Anthropic, and Gemini API requests through a shared intermediate representation, instead of writing N-by-M provider adapters by hand.

#llm #developer-tools

a2a-java - Java SDK for Agent2Agent protocol

Official Java SDK implementing the Agent2Agent (A2A) protocol for inter-agent messaging and capability discovery. Provides client and server implementations for JVM agent stacks.

#multi-agent #java #protocol #ai-agent

Arcjet JS - AI security building blocks for Node

JS/TS SDK for runtime AI security: prompt-injection defense, bot blocking, rate limits, and budget protection wired into Next.js, Bun, and Node servers. Aimed at apps where agents call your tools.

#agent-security #prompt-injection #typescript #javascript

gopher-mcp - C++ SDK for MCP

Model Context Protocol implementation in C++ with async transport, JSON-RPC, and security primitives. Targets MCP servers that need native performance or embed into existing C++ stacks.

#mcp #c #developer-tools

passmark - Playwright AI regression testing

Open-source Playwright library for AI-driven browser regression testing with intelligent caching, auto-healing locators, and multi-model verification. Designed to keep flaky AI tests stable across model versions.

#evals #ai-agent #typescript #developer-tools

bunqueue - SQLite-backed job queue for Bun

High-performance Bun job queue with SQLite persistence, dead-letter queue, cron scheduling, and S3 backups. Marketed as BullMQ alternative for AI agent workloads.

#typescript #developer-tools #ai-agent

honker - Postgres NOTIFY/LISTEN for SQLite

SQLite extension that brings durable pub/sub, task queues, and event streams to SQLite by watching the WAL file for ~1ms cross-process notifications. Inserts jobs in the same transaction as business writes for an outbox pattern by default.

#sqlite #rust #queue #pubsub #developer-tools

agent-prism - React components for agent traces

React component library for visualizing distributed traces from AI agents. Drop-in widgets for timelines, span trees, and tool-call breakdowns from LangChain or custom runtimes.

#observability #typescript #ai-agent #developer-tools

terminator - Playwright for Windows computer use

Rust SDK for driving Windows applications with native UI Automation, designed as a Playwright-style API for AI agents. Lets LLMs click, type, and read state across desktop apps.

#rust #ai-agent #automation

browser-harness-js - self-healing browser harness for LLMs

TypeScript browser harness that lets an LLM complete arbitrary tasks with automatic recovery when selectors break or pages restructure. From the browser-use team.

#ai-agent #typescript #automation

reasonix - DeepSeek-native agent framework

TypeScript agent framework built around DeepSeek with cache-first loops, R1 thought harvesting, and tool-call repair. Ships with an Ink-based TUI for runtime inspection.

#ai-agent #deepseek #typescript #tui #prompt-caching

stricli - type-safe TypeScript CLI framework

Bloomberg's zero-dependency CLI framework for building complex tools in TypeScript with end-to-end type safety. No runtime parser fights, no untyped arg objects.

#cli #typescript #developer-tools

cliffy - runtime-agnostic CLI toolkit

TypeScript CLI toolkit with command framework, argument parser, prompts, tables, and ANSI utilities. Runs on Deno, Node, and Bun without porting.

#cli #typescript #deno #developer-tools

unbug - Rust runtime debug assertions

Rust crate providing macros for runtime assertions, including assertions inserted before try-operator failures. Hooks into test mode to trigger failures when assertions fire.

#rust #debugging #developer-tools

bubblezone - mouse zones for Bubble Tea

Helper library for the Bubble Tea TUI framework that maps mouse events to declarative zones. Lets you build clickable terminal UIs without manual coordinate math.

#tui #go #bubbletea

iocraft - Rust crate for crafted CLIs and TUIs

Declarative Rust library for building CLIs and TUIs with React-like components. Targets terminal IO that needs more than ratatui's lower-level primitives.

#rust #tui #cli #developer-tools

libtmux - Python wrapper for tmux

Python library that exposes tmux servers, sessions, windows, and panes as objects. Powers test harnesses and TUI orchestrators that script tmux.

#python #tmux #library #developer-tools

concierge - SDK for building MCP servers

Python SDK for authoring MCP servers with batteries for tool registration, auth, and apps-sdk style flows. Aims to be the universal scaffold for new MCPs.

#mcp #python #ai-agent #developer-tools

llm-functions - LLM tools from plain shell scripts

Build LLM tools and agents by writing plain Bash, JavaScript, or Python functions; the framework wires up function-calling, schemas, and execution automatically.

#agent-framework #shell #function-calling #developer-tools

secure-exec - npm-compatible Node sandboxing

Lightweight library for sandboxing Node.js code execution from agents without containers or VMs, using runtime isolation. Built for code interpreter use cases.

#agent-security #javascript #ai-agent

open-harness - composable SDK for AI agents

TypeScript SDK for building agents with a code-first composition model: tools, skills, and MCP servers wire together as plain modules. Ships an agent loop you control.

#typescript #ai-agent #mcp #agent-harness #sdk

helixent - tiny ReAct agent loop for Bun

Small TypeScript library for ReAct-style agent loops on the Bun stack. Tools, skills, and a coding-focused harness in a minimal package.

#typescript #agent-harness #ai-agent #bun #react-pattern

cli-to-js - turn any CLI into a JS API

Wraps any command-line tool as a typed JavaScript API agents can call directly. Saves writing a custom MCP for every CLI you want to expose.

#typescript #cli #ai-agent #developer-tools #node

Keeper - embeddable secret store for Go

Embeddable Go secret store using Argon2id and XChaCha20-Poly1305 by default, with four security levels, audit chains, and crash-safe rotation. Vault when Vault is overkill.

#go #security #secrets #library #developer-tools

AIMock - mock everything your AI app talks to

One package, one port, zero deps to fake LLM APIs, MCP servers, A2A, AG-UI, vector DBs, and search backends in tests.

#testing #mcp #llm #mock-server #ai-testing

M-flow - relevance-first agent memory

Memory layer for agents that surfaces relevant context instead of just similar embeddings. Episodic plus long-term memory backed by a knowledge graph.

#agent-memory #knowledge-graph #rag #llm #long-term-memory

AgentScript - schema-driven agent orchestration language

Open language from Salesforce for declaring agent orchestration: tools, handoffs, guardrails, and stop conditions. Runtime-agnostic config.

#agent-orchestration #dsl #schema #multi-agent #typescript

claude-code-java - embeddable Claude Code engine

AI-agent engine for Java apps. CLI plus REST API that wraps the Claude Code execution model so you can drop it into any JVM service.

#claude-code #java #jvm #rest-api #ai-agent

ESP-Claw - AI agent framework for IoT

Espressif's chat-coding agent framework for ESP32 devices. Brings tool-calling LLM agents to embedded targets with C-level memory budgets.

#iot #esp32 #embedded #ai-agent #c

AgentKit - multi-agent networks in TypeScript

Inngest's framework for multi-agent networks with deterministic routing and MCP-native tooling. Picks up where the LangGraph/CrewAI camps trail off.

#multi-agent #typescript #mcp #orchestration #framework

any-llm - one interface for every LLM provider

Mozilla AI's unified Python client for OpenAI, Anthropic, Google, Mistral, and friends. Swap providers without rewriting a single call site.

#llm #openai #anthropic #python #abstraction

ADK-JS - Google's agent dev kit for TypeScript

Code-first toolkit for building, evaluating, and deploying agents on Google's stack. Tool wiring, traces, and eval harness in one package.

#agent-framework #google #typescript #evals #agentic-ai

Golf - production MCP server framework

Build, deploy, and scale MCP servers with auth, observability, debugging, telemetry, and a runtime baked in. Skips the per-server boilerplate.

#mcp #framework #auth #observability #python

dingo - Result types and pattern matching for Go

Meta-language that compiles to standard Go but adds Result types, the `?` error operator, and pattern matching. Keeps full ecosystem compatibility.

#go #compiler #language #pattern-matching #developer-tools