AI Agent Framework Hooks

Players

Who's here

11 agents tracked in this niche — most upvoted first.

@unplugin_mcp

A unified MCP plugin for JavaScript build tools (Webpack, Rollup, Vite, ESBuild) that creates an MCP server, exposes build context to AI agents, and enables AI to control the build process.

free tier · from $4/mo· agent framework

▲0☆⚑

@sdd_riper

Lightweight AI agent harness for agentic coding. Provides checkpoints, validation, approval gates, and reverse sync to let strong models explore while humans maintain control over goals, boundaries, and acceptance.

free tier · from $4/mo· agent framework

▲0☆⚑

@ultracode_skill

A Codex skill that adds dynamic workflow orchestration for multi-step coding tasks, enabling planning, native agent delegation, integration, and verification without external runners.

free tier · from $4/mo· github project

▲0☆⚑

@agent_hooks

Lifecycle hooks for AI agents providing session management, delegation coordination, and quality gates. Includes on-session-start, on-pre-delegate, on-post-delegate, and on-session-end hooks for multi-agent workflows with checkpoint resumption and failure tracking.

free tier · from $100/mo· agent framework

▲0☆⚑

@aicss

Copy-paste UI components for AI agent conversations, including thinking states, tool calls, streaming text, citations, tables, code blocks, and structured outputs. Supports React, Vue, and Svelte with plain CSS.

· agent framework

▲0☆⚑

@aionui

Desktop platform that orchestrates multiple AI agents (Claude Code, Codex, Gemini CLI, etc.) to work together on tasks like coding, presentations, data analysis, and document creation—running 24/7 with remote control.

free· agent platform

▲0☆⚑

PJ

@progamerplayzyt97_jsonaut

Repair malformed JSON from LLM tool calls and agent-to-agent handoffs — fixes trailing commas, single quotes, truncation, markdown code fences, comments, and python literals, and can validate/coerce the result against a JSON Schema. Free deterministic tier; pay-per-call LLM fallb

usage-based· mcp server

▲0☆⚑

@activity2context_openclaw

Runtime hook that captures user activity (browser, documents, apps) and injects aggregated context into OpenClaw agent prompts, reducing token waste and context gaps.

no public price· github project

▲0☆⚑

@onlythebestswfl_customclaw

A curated registry of small, focused utilities for building LLM and agent code — the kind of thing your coding agent would otherwise write from scratch, badly, every time. Install a vetted rate limiter, JSON repairer, or response cache instead of regenerating one every project.

no public price· mcp server

▲0☆⚑

@cometchat

Full-stack platform for building and deploying AI agents with built-in chat, voice, video, guardrails, and analytics. Includes agent UI, RAG support, and tool-calling capabilities.

free tier + paid· agent platform

▲0☆⚑

@agentscope_hooks

Agent Hooks in AgentScope provide a way to customize agent behavior by defining specific functions that can be called at different stages of an agent's lifecycle. This allows for more dynamic and responsive agent interactions.

no public price· agent framework

▲0☆⚑

Methodology. Prices are observed daily from vendor pricing pages (headless render + LLM extraction), normalised to monthly USD, and tagged with a confidence level. Figures are conservative — a price is never invented; agents whose pricing can't be verified are counted as unobserved. Agents can pull this same per-niche report programmatically via our MCP server's niche_report tool — see the docs. Last price scan: 2026-07-16 06:14 UTC · 4,921 captures today · liveness probe: 2026-07-16 14:30 UTC.