AI tools

Run your AIs

189 scored tools, ranked by overall score. Last checked on 29 October 2026. Refine with the Finder →

Autonomous assistants 2 Run locally 54 Orchestrate 32 Route & save 11 Feed (memory, context) 48 Frame (methods, guardrails) 32 Monitor 23

The three to remember

Most powerful

Ollama

AppSecurity: nothing to flag

9.7

The de facto standard for running models locally and connecting them to other tools.

· Utility 9.5/10, best of the selection
· Free, no limits
· No known security caveat

Free1 clickSite ↗

Simplest

Frontend Design (Anthropic)

SkillRisingSecurity: nothing to flag

9.6

The most installed skill on the official marketplace: one click, immediate effect on UI quality.

· Utility 9/10
· Free, no limits
· No known security caveat

Free1 clickSite ↗

The alternative

Context7

MCPSecurity: nothing to flag

9.4

The most installed MCP, and for good reason: it eliminates hallucinated APIs.

· Utility 9/10
· Free tier to get started
· No known security caveat

Freemium1 clickSite ↗

TypeApp Tool MCP Built-in mode Skill PluginPriceFree Freemium Paid

Tool	Type	What it does	Price	Install	Score	Sec.
Context7MCP server that injects up-to-date, version-specific library documentation into the agent's context.	MCP	MCP server that injects up-to-date, version-specific library documentation into the agent's context.	Freemium	1 click	9.4	Security: nothing to flag
LangfuseRisingOpen source LLM observability: traces, costs, evaluations, prompt management.	App	Open source LLM observability: traces, costs, evaluations, prompt management.	Freemium	5 min	9.3	Security: nothing to flag
Hermes Agent (Nous Research)RisingSelf-hosted agent that learns from its tasks, creates its own skills, maintains persistent memory, and responds on Telegram, Discord, Slack, WhatsApp, or Signal.	App	Self-hosted agent that learns from its tasks, creates its own skills, maintains persistent memory, and responds on Telegram, Discord, Slack, WhatsApp, or Signal.	Freemium	5 min	9.1	Security: nothing to flag
MeetilyMeeting assistant that records, transcribes (Whisper or Parakeet) and summarises your meetings on your machine, with no bot and no cloud.	App	Meeting assistant that records, transcribes (Whisper or Parakeet) and summarises your meetings on your machine, with no bot and no cloud.	Freemium	1 click	9.0	Security: nothing to flag
PromptfooRisingPrompt, agent, and RAG testing and red-teaming, CI-integrable.	App	Prompt, agent, and RAG testing and red-teaming, CI-integrable.	Freemium	5 min	9.0	Security: nothing to flag
Arize PhoenixRisingLLM application tracing and evaluation, built on OpenTelemetry.	App	LLM application tracing and evaluation, built on OpenTelemetry.	Freemium	5 min	8.9	Security: nothing to flag
CrewAIRisingPython framework for orchestrating teams of agents by roles.	App	Python framework for orchestrating teams of agents by roles.	Freemium	5 min	8.8	Security: nothing to flag
LangGraphFramework for building stateful agents with an explicit control graph.	App	Framework for building stateful agents with an explicit control graph.	Freemium	Technical	8.8	Security: nothing to flag
HeliconeRisingObservability proxy: costs, latency and logs of all your LLM requests by changing one URL.	App	Observability proxy: costs, latency and logs of all your LLM requests by changing one URL.	Freemium	5 min	8.7	Security: nothing to flag
PortkeyRisingAI gateway with routing, guardrails, and observability, open source since March 2026.	App	AI gateway with routing, guardrails, and observability, open source since March 2026.	Freemium	5 min	8.6	Security: nothing to flag
Brave Search MCPRisingIndependent web search for the agent via the Brave API.	MCP	Independent web search for the agent via the Brave API.	Freemium	5 min	8.5	Security: nothing to flag
BifrostRisingAI gateway in Go, very low latency, also serving as an MCP gateway.	App	AI gateway in Go, very low latency, also serving as an MCP gateway.	Freemium	Technical	8.4	Security: nothing to flag
Guardrails AIRisingLLM input and output validators (PII, toxicity, format) with a validator hub.	App	LLM input and output validators (PII, toxicity, format) with a validator hub.	Freemium	Technical	8.4	Security: nothing to flag
MacWhisperLocal Whisper transcription on Mac, with a polished interface.	App	Local Whisper transcription on Mac, with a polished interface.	Freemium · from 59 €	1 click	8.3	Security: nothing to flag
FrigateRisingLocal NVR for cameras with 100% local AI object detection.	App	Local NVR for cameras with 100% local AI object detection.	Freemium	Technical	8.2	Security: nothing to flag
ExaSearch engine designed for agents, with an official MCP integration.	App	Search engine designed for agents, with an official MCP integration.	Freemium	5 min	8.1	Security: nothing to flag
Firecrawl scrape, crawl, searchRisingFull website extraction to markdown, callable by an agent.	Tool	Full website extraction to markdown, callable by an agent.	Freemium	5 min	8.1	Security: one caveat, see the card
LangSmithObservability and evaluation platform from LangChain, usable outside LangChain.	App	Observability and evaluation platform from LangChain, usable outside LangChain.	Freemium	5 min	8.1	Security: nothing to flag
BraintrustEvaluation and logging platform for AI products, oriented towards product teams.	App	Evaluation and logging platform for AI products, oriented towards product teams.	Freemium	5 min	7.9	Security: nothing to flag
FirecrawlRisingTurns any website into clean markdown for AI, with an MCP server.	App	Turns any website into clean markdown for AI, with an MCP server.	Freemium	5 min	7.9	Security: one caveat, see the card
InvokeAIRisingLocal generation studio with a retouching canvas, more accessible than ComfyUI.	App	Local generation studio with a retouching canvas, more accessible than ComfyUI.	Freemium	5 min	7.9	Security: nothing to flag
TavilySearch and extraction API optimized for LLMs, with MCP support.	App	Search and extraction API optimized for LLMs, with MCP support.	Freemium	5 min	7.9	Security: nothing to flag
LiteLLMSelf-hosted gateway that unifies 100+ providers behind an OpenAI API, with budgets and virtual keys.	App	Self-hosted gateway that unifies 100+ providers behind an OpenAI API, with budgets and virtual keys.	Freemium	Technical	7.8	Security: one caveat, see the card
Codex CLI (OpenAI) et ses extensionsRisingOpenAI's terminal coding agent, with sandbox, skills, and integrations.	Plugin	OpenAI's terminal coding agent, with sandbox, skills, and integrations.	Freemium	5 min	7.7	Security: one caveat, see the card
LlamaParseComplex document parsing for RAG.	Tool	Complex document parsing for RAG.	Freemium	5 min	7.7	Security: nothing to flag
StrixOpen-source AI agent pentesting: agents run your application, find vulnerabilities, and prove each one with a PoC.	App	Open-source AI agent pentesting: agents run your application, find vulnerabilities, and prove each one with a PoC.	Freemium	5 min	7.7	Security: one caveat, see the card
UnstructuredDocument chunking and extraction across all formats.	Tool	Document chunking and extraction across all formats.	Freemium	5 min	7.7	Security: nothing to flag
Wolfram AlphaSymbolic computation and factual data callable by an agent.	Tool	Symbolic computation and factual data callable by an agent.	Freemium	5 min	7.7	Security: nothing to flag
AnythingLLMRisingAll-in-one application to chat with your documents, locally or via API, with built-in agents.	App	All-in-one application to chat with your documents, locally or via API, with built-in agents.	Freemium	5 min	7.6	Security: one caveat, see the card
Mem0RisingPersistent memory layer for agents and assistants, hosted or self-hosted.	App	Persistent memory layer for agents and assistants, hosted or self-hosted.	Freemium	5 min	7.6	Security: one caveat, see the card
Composio (connect-apps)RisingGives the agent actions across 1,000+ applications (Gmail, Slack, Notion, GitHub…) via centralized authentication.	Plugin	Gives the agent actions across 1,000+ applications (Gmail, Slack, Notion, GitHub…) via centralized authentication.	Freemium	5 min	7.5	Security: one caveat, see the card
GitHub Copilot CLIRisingCopilot agent in the terminal, with built-in GitHub MCP integration.	Plugin	Copilot agent in the terminal, with built-in GitHub MCP integration.	Freemium	5 min	7.5	Security: one caveat, see the card
LM StudioA graphical interface to download and chat with open-weight models on your own PC.	App	A graphical interface to download and chat with open-weight models on your own PC.	Freemium	1 click	7.5	Security: one caveat, see the card
Postshot (Jawset)Watch outLocal Gaussian splat training on NVIDIA GPU.	App	Local Gaussian splat training on NVIDIA GPU.	Freemium	5 min	7.5	Security: nothing to flag
google_search (Gemini)Grounds Gemini responses on Google Search, with sources.	Tool	Grounds Gemini responses on Google Search, with sources.	Freemium	1 click	7.4	Security: one caveat, see the card
Not DiamondSmart router that selects the cheapest model capable of handling each request.	App	Smart router that selects the cheapest model capable of handling each request.	Freemium	5 min	7.4	Security: nothing to flag
OpenRouterOne API key to access 400+ models, with automatic fallback between providers.	App	One API key to access 400+ models, with automatic fallback between providers.	Freemium	Nothing to install	7.4	Security: one caveat, see the card
Zep / GraphitiRisingTemporal knowledge graph memory for agents, with Graphiti in open source.	App	Temporal knowledge graph memory for agents, with Graphiti in open source.	Freemium	Technical	7.4	Security: one caveat, see the card
E2B Code InterpreterRisingIsolated micro-VM for executing code produced by an agent.	Tool	Isolated micro-VM for executing code produced by an agent.	Freemium	Technical	7.3	Security: one caveat, see the card
LettaRisingManaged-memory agent platform, successor to MemGPT.	App	Managed-memory agent platform, successor to MemGPT.	Freemium	Technical	7.2	Security: one caveat, see the card
code_execution (Gemini)Python executed on Google's side, results returned to the model.	Tool	Python executed on Google's side, results returned to the model.	Freemium	1 click	7.0	Security: one caveat, see the card
ConductormacOS app that runs multiple Claude Code agents in parallel with a dashboard.	App	macOS app that runs multiple Claude Code agents in parallel with a dashboard.	Freemium	1 click	7.0	Security: one caveat, see the card
code_execution (Anthropic)Runs Python and bash in an Anthropic sandbox, with a file editor.	Tool	Runs Python and bash in an Anthropic sandbox, with a file editor.	Freemium	5 min	6.9	Security: one caveat, see the card
Exa SearchEmbedding-based semantic search, designed for agents.	Tool	Embedding-based semantic search, designed for agents.	Freemium	5 min	6.9	Security: one caveat, see the card
Tavily SearchWeb search and extraction designed for agents.	Tool	Web search and extraction designed for agents.	Freemium	5 min	6.9	Security: one caveat, see the card
Invariant GuardrailsWatch outSecurity rules applied in real time to agent tool calls.	App	Security rules applied in real time to agent tool calls.	Freemium	Technical	6.8	Security: nothing to flag
Browserbase et StagehandRisingHosted Chrome browsers and act, extract, observe SDK for agents.	Tool	Hosted Chrome browsers and act, extract, observe SDK for agents.	Freemium · from 18 €	Technical	6.7	Security: serious reservations
Browser UseRisingLLM-driven browser control, open source.	Tool	LLM-driven browser control, open source.	Freemium	Technical	6.7	Security: serious reservations
Jina Reader et SearchConverts a URL into clean Markdown for a language model.	Tool	Converts a URL into clean Markdown for a language model.	Freemium	1 click	6.7	Security: one caveat, see the card
MstyA polished desktop client that combines local models and cloud APIs in a single interface.	App	A polished desktop client that combines local models and cloud APIs in a single interface.	Freemium	1 click	6.7	Security: one caveat, see the card
url_context (Gemini)Reads the content of URLs you pass in the prompt.	Tool	Reads the content of URLs you pass in the prompt.	Freemium	1 click	6.6	Security: one caveat, see the card
Actors Apify comme outils7,000+ scrapers and automations callable by an agent.	Tool	7,000+ scrapers and automations callable by an agent.	Freemium	5 min	6.5	Security: one caveat, see the card
SerperCheap Google results for agents.	Tool	Cheap Google results for agents.	Freemium	5 min	6.5	Security: one caveat, see the card
MCP DefenderDesktop app that intercepts and filters MCP traffic from installed AI clients.	App	Desktop app that intercepts and filters MCP traffic from installed AI clients.	Freemium	5 min	6.3	Security: one caveat, see the card
QdrantNewOpen source vector database written in Rust: it stores your documents as vectors and retrieves the closest passages by meaning, the search building block of a RAG system.	App	Open source vector database written in Rust: it stores your documents as vectors and retrieves the closest passages by meaning, the search building block of a RAG system.	Freemium	Technical	6.2	Security: one caveat, see the card
DaytonaFast-starting sandboxes for agents.	Tool	Fast-starting sandboxes for agents.	Freemium	Technical	6.1	Security: one caveat, see the card

App : A product you use directly · Tool : A precise action the AI can call · MCP : Standardises the connection between an AI application and systems that expose tools or data · Built-in mode : A feature to switch on inside an assistant you already use (ChatGPT, Claude, Gemini): nothing to install · Skill : A reusable method: instructions, procedures, sometimes scripts or templates · Plugin : A set of capabilities installed into an AI application or a host

Method

Overall score = utility (rated by the editorial team), reliability (GitHub activity, official publisher, reachable site), security (where data goes, permissions, known incidents) and accessibility (install, required level, price), weighted per category. A tool inactive for over six months is flagged and leaves the recommendations. No ranking is sold.

Missing a tool? A score looks wrong?

Write to the editors