Agents

Autonomous and orchestrated multi-step AI workers.

259 tools

Why it matters

The agent ecosystem is the youngest category here — frameworks, orchestrators, and end-to-end autonomous workers are evolving fast, with reliability and observability still maturing.

What's in here

Includes orchestration frameworks (LangGraph, CrewAI, Claude Agent SDK), end-to-end product agents (Devin, Manus), and open-source platforms (AutoGPT, OpenAI Swarm).

How to pick

Pick LangGraph when production reliability matters. Pick CrewAI for fast multi-agent prototyping. Pick Claude Agent SDK if you're Claude-aligned. Use Devin / Manus when you want a finished agent product, not a framework.

GameMaker MCP Server

Agents

Project-aware MCP server that gives AI coding agents structured, guarded access to GameMaker Studio projects.

Free· Free and open source (MIT license). Install via npm/npx.AI-assisted GML refactoringGameMaker project static analysis

GenAI Agents (NirDiamant)

Agents · Framework-agnostic; most notebooks default to OpenAI GPT-4 class models, with Ollama and local model examples included.

50+ Jupyter tutorials for building GenAI agents, from a simple chatbot to multi-agent systems.

Free· Free and open source (Jupyter notebooks). Author sells an optional paid course at diamant-ai.com and runs a free newsletter; the repository itself has no paywall.LangGraph multi-agent workflowCustomer support agent

Genspark

Agents · Mixture-of-agents across ~9 LLMs including GPT-4.1, Claude, Gemini plus OpenAI Realtime API for voice

A no-code Super Agent that orchestrates 9 frontier LLMs and 150+ tools to research, build, and even make phone calls for you

Freemium· Basic: $10 · Pro: $25 · Enterprise: Contact salesautonomous deep-research reportsone-shot pitch deck generation

Go Micro

Agents · Model-agnostic: Claude (Anthropic), OpenAI, and 300+ models via Atlas Cloud

Agent harness and microservice framework, in one Go runtime.

Free· Open source (Apache 2.0). Commercial support available separately; hosted model access via Atlas Cloud is billed by that provider.Production AI agents that call internal microservicesAgent-to-agent systems with service discovery

Google Agent Development Kit (ADK)

Agents · Gemini (default) plus Claude, GPT-4/5, Llama, and other providers via LiteLLM

Google's open-source framework for building, evaluating, and deploying production AI agents

Free· Framework itself is free and open-source (Apache 2.0). Costs come from the underlying model provider (e.g. Gemini API / Vertex AI usage) and any hosting infrastructure (Cloud Run, GKE, Agent Engine).Multi-agent research assistantCustomer support triage agent

Google Antigravity

Agents · Gemini 3 family (Flash tiers highlighted)

Google's agent-first development platform for building software with autonomous coding agents.

Freemium· For Individuals: $0/month · Google AI Pro: ? · Google AI Ultra: ? · Organization plan via Google Cloud: ?Parallel autonomous coding agentsRepository-aware refactors

Goose

Agents · Provider-agnostic — Claude 3.5/4, GPT-4o/4.1, Gemini 1.5/2, Llama 3.x via Ollama, plus Azure OpenAI, Bedrock, OpenRouter and others

Open-source, local-first AI agent for code, workflows, and everything in between.

Free· Free and open source under Apache 2.0. You bring your own model API keys (or run local models via Ollama); provider costs are pass-through.Multi-file code refactors and PR generationLocal repo Q&A and code review

gpt-engineer

Agents · OpenAI GPT (default), Anthropic Claude, Azure OpenAI, and open-weights models like WizardCoder via configuration

Describe software in natural language, watch an AI agent write, run, and improve it.

Free· Free and open source under MIT license. Users pay only for the underlying LLM API calls (OpenAI, Anthropic, Azure OpenAI) or run local models at zero token cost.Greenfield script and prototype generationSmall single-file utility creation from a spec

GPT Pilot

Agents · Model-agnostic via OpenAI-compatible API (OpenAI GPT-4/4o, Anthropic Claude, Groq-hosted Llama, Azure OpenAI, OpenRouter)

Open-source multi-agent 'AI developer' that builds apps step by step with human checkpoints

Free· Free / open source (MIT). Users supply their own LLM API keys (OpenAI, Anthropic, Groq, Azure, or OpenRouter), so real cost depends on token usage on the chosen provider.greenfield full-stack app scaffoldingmulti-agent coding research

GPT Researcher

Agents · Model-agnostic (default GPT-4o; supports Anthropic Claude, Google Gemini, Groq, Ollama, and any LiteLLM-compatible provider)

Open-source autonomous deep-research agent with cited long-form reports

Free· Free and open-source (MIT License). Costs come only from your chosen LLM provider (OpenAI, Anthropic, Google, etc.) and retriever (Tavily, Bing, SerpAPI, DuckDuckGo is free).Autonomous deep research reportsMarket research briefs

Hydra

Agents · Multi-provider: routes across Claude, GPT, Gemini Flash, OpenRouter-hosted models, and local Qwen via Ollama / LM Studio

Local-first trust control plane that routes AI tasks to the cheapest model that clears your confidence bar.

Free· Free and open-source under the MIT license; no hosted tier or paid plan. You still pay whatever the underlying providers (Anthropic, OpenAI, OpenRouter, etc.) charge for tokens Hydra dispatches to them.multi-model CLI routingcost-optimized code generation

Kritt

Agents · Codex and Claude Code (as agent harnesses)

AI-assisted code security research with parallel agents and verified findings

Freemium· Single Scan: $5,000 per scan · Enterprise: Contact usPre-launch security audit of a new serviceContinuous vulnerability scanning in CI/CD

LDBD Prediction Leaderboard

Agents · Model-agnostic (users bring their own — Claude, GPT, Gemma, or custom); leaderboard shows entries from Claude, GPT and Gemma variants

Public leaderboard where AI bots and humans forecast markets and get auto-scored against real outcomes.

Free· Free to play. Free plan includes 2 identities, 20 predictions/day, and 50 simultaneous open predictions. No paid tier advertised.Benchmarking LLM trading agentsPublic track record for a custom prediction bot

Lindy

Agents · Frontier LLMs (Anthropic Claude and OpenAI GPT families) selected per task; not user-configurable

No-code AI agents for email, meetings, and the rest of your admin work

Paid· Plus: $29.99 /mo per user · Pro: $99.99 /mo per user · Max: $199.99 /mo per user · Enterprise: Contact salesAI executive assistantInbox triage and email drafting

LLM Gateway

Agents · Routes to GPT-4o, Claude 3.5 Sonnet, Gemini 1.5, Llama 3.1, Mistral, and 200+ others

One API, 200+ models, transparent pricing, and no vendor lock-in.

Freemium· Free: $0 · Enterprise: CustomMulti-provider LLM routingAutomatic failover between model vendors

LobeHub

Agents · OpenAI GPT-4o/o1, Anthropic Claude 3.5/4, Google Gemini, DeepSeek, Mistral, Ollama, and 40+ other providers (bring-your-own-key)

Open-source AI agent platform and chat UI supporting every major LLM, plugins, and multi-agent workflows.

Freemium· Free: Free · Starter: $9.9 · Premium: $19.9 · Ultimate: $39.9Self-hosted ChatGPT alternativeMulti-provider LLM comparison

Mem0

Agents · Model-agnostic — pluggable via OpenAI, Anthropic, Gemini, Ollama, LiteLLM (no in-house LLM)

Persistent memory layer for AI agents and LLM apps

Freemium· Hobby: Free · Starter: $19 · Pro: $249 · Enterprise: CustomLong-lived customer support copilotsPersonal AI companions and journaling agents

MemPalace

Agents · Embedding backends: embedding-gemma-300m (multilingual) or all-MiniLM-L6-v2 (English). No LLM required for retrieval.

Open-source, local-first AI memory system for LLM agents

Free· Free and open-source under the MIT license. No paid tiers; self-hosted with zero API costs once installed.Persistent memory for Claude Code and Cursor sessionsPer-agent memory isolation in multi-agent systems

Netdata

Agents · In-house unsupervised ML models for per-metric anomaly detection; AI Co-Engineer and Ask Nedi built on third-party LLMs (unspecified) with MCP integration for external assistants

Real-time infrastructure observability with embedded AI anomaly detection and an AI co-engineer for root-cause analysis.

Freemium· Community: Free · Business: $4.50 /node/month · Enterprise: Contact salesReal-time infrastructure anomaly detectionAI-assisted incident root-cause analysis

Neverbell

Agents · Agent-framework agnostic (Claude Code, OpenClaw, Hermes and other compatible frameworks)

Market access skill that lets AI agents monitor and trade real markets

Freemium· Early access with $1,000 in test funds; production pricing tiers not yet disclosedAgent-executed equity and ETF tradesAutonomous crypto trading

Octomind

Agents · Multi-provider: OpenAI, Anthropic (Claude), DeepSeek, Ollama, and 20+ others; benchmarks cite GLM-5.2 and Claude Opus

Homebrew for AI agents: install specialized, budget-capped AI specialists with one command.

Freemium· Free: $0 · Pro: $10 _first month_ → $20/mo · Max: $50 _first month_ → $100/mo · Team: $500/mo _flat, whole team_Domain-specialist coding agentsAutomated PR review and fixes

Omentir

Agents · Claude Opus 4.5

AI sales agent for automated, personalised LinkedIn outreach

Freemium· Monthly: $29/month · Lifetime: ?Automated LinkedIn cold outreachICP-based lead scoring

OneWayInterview

Agents

AI-scored async video interviews for SMB hiring teams

Freemium· Starter: $13.99 · SME: $34.99 · Business: $62.99 · Unlimited: $209.99async video screeningAI candidate ranking

OpenAI Agents SDK (Python)

Agents · GPT-4o / GPT-4.1 / gpt-realtime (provider-pluggable via LiteLLM)

A lightweight Python framework for building multi-agent LLM applications with handoffs, guardrails, and built-in tracing.

Free· SDK is free and open source (MIT-licensed). Cost is pass-through to whichever model provider you point it at — OpenAI API pricing applies when using GPT models; third-party providers billed separately.Multi-agent customer support with specialist handoffsVoice agents using gpt-realtime for phone or in-app calls