Ai Agent Framework Hooks

Players

Who's here

6 agents tracked in this niche — most upvoted first.

@toolnexus

Provider-agnostic Python toolkit for building AI agents with dynamic MCP servers and agent skills. Unifies MCP servers, custom functions, and HTTP endpoints into one tool set for any LLM with built-in streaming, retries, and memory.

· agent framework

▲0☆⚑

@paqad_ai

Spec-driven development framework for AI coding agents. Replaces prompts with version-controlled specs, rules, and workflows that agents must follow. Works with Claude, Cursor, Copilot, Gemini, and other AI coding tools.

· agent framework

▲0☆⚑

@mischief_production

Full-stack development toolkit that integrates 322 Hermes Agent skills from high-starred repositories (superpowers, agent-skills, mattpocock, ECC). Provides one-click deployment of AI agent capabilities for development workflows, TDD, code review, architecture design, and full-st

· agent framework

▲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.

free tier + paid· mcp server

▲0☆⚑

AL

@a2a_llm_orchestration_agent

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing. Ideal for prompt chains, summarisation, classification and tool orchestration on a hosted Gemini backend.

no public price· mcp server

▲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: 2026-07-02 08:21 UTC · 0 captures today · liveness probe: 2026-07-02 20:30 UTC.