📖 The AI Tool Bible

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.

Open WebUI

Agents · Backend-agnostic: any Ollama, llama.cpp, vLLM, or OpenAI-compatible API (OpenAI GPT, Anthropic Claude, Llama 3.x, Qwen, Mistral, Gemma, etc.)

Self-hosted, extensible AI chat platform that runs on your infrastructure

Freemium· Free (self-hosted, MIT-style community license via pip/Docker) / Enterprise: custom pricing for SSO, RBAC, audit logs, air-gapped deployment, data-residency guaranteesSelf-hosted ChatGPT alternative for a teamPrivate RAG chatbot over internal documents

Opera Neon

An agentic browser from Opera built to act on the web, not just render it.

Paid· Basic: $10 · Pro: $20 · Enterprise: Contact salesMulti-tab web research briefsVendor and product comparison across sources

Perplexity Comet

Agents · Routes to Perplexity Sonar plus frontier models (OpenAI GPT, Anthropic Claude, Google Gemini) depending on task and subscription tier

An agentic AI browser from Perplexity that reads, reasons over, and acts on the pages you're viewing.

Freemium· Basic: $10 · Pro: $20 · Enterprise: Contact salesMulti-tab research synthesis with citationsAgentic email triage and drafting in Gmail

Relevance AI

Agents · Multi-model: Claude (Opus/Sonnet/Haiku), OpenAI GPT, Google Gemini, plus open-weight options (Kimi K2, GLM)

Build and deploy an AI workforce of specialized agents across your business tools

Enterprise· Free trial available via the app. Paid tiers are quote-based (Enterprise): custom actions, unlimited agents/tools/users, dedicated account manager. Reported customer benchmarks cite an average cost of ~$0.09 per task at scale; no fixed public tier pricing.Outbound prospect research and personalisationMeeting prep and CRM hygiene

Scalattice

Agents · Open-weight models including Qwen 2.5 Coder, Llama 3.3 70B, DeepSeek R1, Gemma

Pay less for AI, earn from your GPU.

Paid· Per-token pay-as-you-go on prepaid credits. Example rates per 1M tokens: Qwen-2.5-Coder-7B $0.029 in / $0.077 out; Llama-3.3-70B $0.098 in / $0.306 out. No platform fee for GPU providers to connect.Cheap open-model inference behind an OpenAI-compatible SDKAgent loops on Llama 3.3 70B or DeepSeek R1

Scrapling

Adaptive Python web-scraping framework with a built-in MCP server for AI coding agents.

Free· Free and open source under BSD-3-Clause. Self-hosted Python library with no paid tier or hosted service; users pay only for their own infrastructure, browsers, and any proxies or LLM tokens they choose to plug in.MCP-driven web scraping from Claude DesktopAgent-powered research and browsing

Sharper

AI office assistant that turns your documents and connected apps into a cited, agentic knowledge base

Freemium· Free tier available via 'Start for free'; paid plans referenced on the pricing page but tier prices load dynamically and were not visible at review time.Cross-source internal knowledge searchCited research briefs

Sierra

Agents · Undisclosed multi-model (frontier LLMs orchestrated behind Sierra's Agent OS)

Conversational AI agents for enterprise customer experience.

Enterprise· Basic: $10 · Pro: $20 · Enterprise: Contact salesEnterprise customer support agentVoice IVR replacement

Sim

Agents · Multi-model: OpenAI, Anthropic, Google, DeepSeek, xAI, Cerebras, Groq, Sakana AI

Open-source AI agent workspace — build visually, conversationally, or with code

Freemium· Free: $0 · Pro: $25 · Max: $100 · Enterprise: CustomSales outreach agentsIT ticket triage and resolution

Stagehand

Agents · Model-agnostic (OpenAI GPT-4o, Anthropic Claude, Google Gemini via Vercel AI SDK)

The SDK for browser agents

Freemium· SDK is free/open-source (MIT). Runs locally against any LLM API key. Optional Browserbase cloud runtime: Free $0/mo, Developer $20/mo, Startup $99/mo, Scale custom.AI web scrapingAutonomous browser agents

Stele

Shared project memory for AI coding agents across Claude Code, Cursor, Codex, and Copilot

Freemium· Free: $0/ forever · Pro: $12/ month · Team: $20/ user / moshared memory across AI coding agentscross-tool project context handoff

Suna

Agents · Bring-your-own-model (OpenAI GPT, Anthropic Claude, and other providers via API keys or existing subscriptions)

Open-source AI command center for deploying a workforce of autonomous agents across your company

Freemium· Free: $0 · Team: $40/ seat / mo · Enterprise: CustomAutonomous research and market intelligenceWeb scraping and data enrichment agents

Superserve

Open-source sandbox infrastructure for long-running AI agents

Freemium· Free tier (no credit card required); usage-based: $0.0504/vCPU-hour compute, $0.0162/GiB-hour memory, $0.000108/GiB-hour storageLong-running coding agent workspacesSafe execution of AI-generated code

The Email Game

Agents · Bring-your-own (any LLM the participant chooses)

An arena for autonomous email agents.

Free· Free to enter. Prize pool of $1,700 total ($1,000 first place, $500 second, $200 third). Referral bonus of $15 per referred competitor up to $45.Multi-agent LLM benchmarkingAgent negotiation research

Vigla

Agents · Model-agnostic (delegates to the underlying agent's LLM: Claude, GPT, etc.)

Open-source mission control for AI coding agents

Free· Free and open source under Apache-2.0. No paid tiers; users build from source.Supervising multiple AI coding agents in parallelPre-merge audit of agent-generated diffs

Weather MCP Server

MCP server that gives Claude live weather, climate, terrain, and hazard data for any location on Earth.

Freemium· Free tier: 50 daily calls, standard polygon size. Paid plans: higher quotas and larger polygon analysis areas (contact / registration required for higher tiers).Site-specific fire risk assessmentFlood susceptibility screening

X402vps

Pay-per-hour Docker containers for autonomous AI agents, billed in USDC via the x402 protocol

Paid· Usage-based hourly: ATOM $0.01/hr (0.1 vCPU, 256MB RAM, 2GB disk, no internet); CELL $0.02/hr (0.25 vCPU, 512MB, 5GB, 100MB/hr bandwidth); NODE $0.04/hr (0.5 vCPU, 1GB, 10GB, 500MB/hr); CORE $0.08/hr (1 vCPU, 2GB, 20GB, 2GB/hr). Bandwidth overage $0.01/GB. Exec calls are free. Paid in USDC on Base.Ephemeral web scraping sandboxesLLM code-interpreter backends

YAFL

Agent-first, end-to-end-encrypted file transfer over one MCP call or CLI command.

Free· Free to use; the schema.org offer on the homepage lists price 0 USD. No paid tiers advertised at time of review.Agent-to-agent file handoff via MCPScreenshot from phone into Claude Code on a VPS

ZeroClaw

Agents · Bring-your-own: Claude, OpenAI, or local models via Ollama / llama.cpp

Private, local-first AI assistant that connects to Telegram, Discord and WhatsApp

Free· Free and open source. You supply your own hardware and (optionally) your own LLM API keys.Personal Telegram AI assistantDiscord community bot