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.
OllamaRun an open-weight model in one command, with a local OpenAI-compatible API.	App	Run an open-weight model in one command, with a local OpenAI-compatible API.	Free	1 click	9.7	Security: nothing to flag
Frontend Design (Anthropic)RisingOfficial Anthropic skill that pushes Claude to produce polished, distinctive interfaces rather than generic templates.	Skill	Official Anthropic skill that pushes Claude to produce polished, distinctive interfaces rather than generic templates.	Free	1 click	9.6	Security: nothing to flag
Ultimate Vocal RemoverRisingVoice and instrument separation running locally with multiple models (MDX, Demucs).	App	Voice and instrument separation running locally with multiple models (MDX, Demucs).	Free	1 click	9.6	Security: nothing to flag
mcp-scanRisingScans your MCP servers and installed skills for tool poisoning, rug pulls, and injections.	App	Scans your MCP servers and installed skills for tool poisoning, rug pulls, and injections.	Free	1 click	9.3	Security: nothing to flag
JanRisingOpen-source alternative to LM Studio, with zero telemetry.	App	Open-source alternative to LM Studio, with zero telemetry.	Free	1 click	9.2	Security: nothing to flag
React best practices (Vercel)RisingReact and Next.js rules maintained by Vercel, read by the agent before coding.	Skill	React and Next.js rules maintained by Vercel, read by the agent before coding.	Free	1 click	9.2	Security: nothing to flag
spec-kit (GitHub)Spec-driven development toolkit: constitution, spec, plan, tasks, then implementation.	App	Spec-driven development toolkit: constitution, spec, plan, tasks, then implementation.	Free	5 min	9.2	Security: nothing to flag
Buzz (Whisper)RisingLocal transcription with Whisper, SRT and VTT export, no account or cloud required.	App	Local transcription with Whisper, SRT and VTT export, no account or cloud required.	Free	1 click	9.1	Security: nothing to flag
Claude Code Setup (Anthropic)Official plugin that analyses your repository and recommends the hooks, skills, MCP servers, and sub-agents suited to your stack.	Plugin	Official plugin that analyses your repository and recommends the hooks, skills, MCP servers, and sub-agents suited to your stack.	Free	1 click	9.1	Security: nothing to flag
grill-me (Matt Pocock)The agent questions you relentlessly on your plan, branch by branch, until every decision is clear, before writing a single line of code.	Skill	The agent questions you relentlessly on your plan, branch by branch, until every decision is clear, before writing a single line of code.	Free	1 click	9.1	Security: nothing to flag
UpscaylRisingEnlarges and restores images up to 16x locally, without watermark.	App	Enlarges and restores images up to 16x locally, without watermark.	Free	1 click	9.1	Security: nothing to flag
vLLMRisingHigh-performance serving engine for running LLMs for multiple users in parallel.	App	High-performance serving engine for running LLMs for multiple users in parallel.	Free	Technical	9.1	Security: nothing to flag
awesome-claude-codeRisingA curated list of commands, hooks, skills, and workflows for Claude Code.	Skill	A curated list of commands, hooks, skills, and workflows for Claude Code.	Free	1 click	9.0	Security: nothing to flag
BMAD MethodRisingAgile method for agents: roles (PM, architect, dev) and structured documents before the code.	Skill	Agile method for agents: roles (PM, architect, dev) and structured documents before the code.	Free	5 min	9.0	Security: nothing to flag
Docling (IBM)RisingLocal PDF and document parsing, tables and layout included.	Tool	Local PDF and document parsing, tables and layout included.	Free	5 min	9.0	Security: nothing to flag
REAL Video EnhancerRisingFree interface to interpolate and upscale videos using RIFE and ESRGAN.	App	Free interface to interpolate and upscale videos using RIFE and ESRGAN.	Free	1 click	9.0	Security: nothing to flag
ccusageRisingReads local Claude Code logs and displays cost by day, session or model.	App	Reads local Claude Code logs and displays cost by day, session or model.	Free	5 min	8.9	Security: nothing to flag
garakRisingNVIDIA's LLM vulnerability scanner: jailbreaks, leaks, hallucinations, injections.	App	NVIDIA's LLM vulnerability scanner: jailbreaks, leaks, hallucinations, injections.	Free	5 min	8.9	Security: nothing to flag
llama.cppRisingThe C/C++ inference engine behind Ollama, LM Studio, and most local AI tools.	App	The C/C++ inference engine behind Ollama, LM Studio, and most local AI tools.	Free	Technical	8.9	Security: nothing to flag
Awesome CursorRulesCommunity library of rule files by framework and language to guide Cursor.	Skill	Community library of rule files by framework and language to guide Cursor.	Free	5 min	8.8	Security: nothing to flag
CavemanMakes the agent respond in telegraphic style: fewer pleasantries and filler, code and error messages kept exactly as-is.	Skill	Makes the agent respond in telegraphic style: fewer pleasantries and filler, code and error messages kept exactly as-is.	Free	1 click	8.8	Security: nothing to flag
cursor.directoryRisingDirectory of Cursor rules and MCP servers, with prompts ready to paste.	Skill	Directory of Cursor rules and MCP servers, with prompts ready to paste.	Free	1 click	8.8	Security: nothing to flag
Questionnaire fournisseur (skill nAIvigate)Pre-fills a security questionnaire from your policies, tagging each answer Sourced, Inferred or To complete.	Skill	Pre-fills a security questionnaire from your policies, tagging each answer Sourced, Inferred or To complete.	Free	1 click	8.8	Security: nothing to flag
Cisco mcp-scannerRisingOpen source scanner by Cisco based on YARA to analyze MCP tool descriptions and schemas.	App	Open source scanner by Cisco based on YARA to analyze MCP tool descriptions and schemas.	Free	5 min	8.7	Security: nothing to flag
DSPyRisingFramework that replaces prompt writing with programming and automatic optimization.	App	Framework that replaces prompt writing with programming and automatic optimization.	Free	Technical	8.7	Security: nothing to flag
Home AssistantOpen source home automation with local voice assistant Assist.	App	Open source home automation with local voice assistant Assist.	Free	Technical	8.7	Security: nothing to flag
mcp-builder (Anthropic)RisingOfficial skill that helps design and code a clean MCP server.	Skill	Official skill that helps design and code a clean MCP server.	Free	1 click	8.7	Security: nothing to flag
SGLangRisingA serving engine competing with vLLM, very fast thanks to the RadixAttention prefix cache.	App	A serving engine competing with vLLM, very fast thanks to the RadixAttention prefix cache.	Free	Technical	8.7	Security: nothing to flag
skill-creator (Anthropic)RisingOfficial skill that guides Claude to write, structure, and test a new skill.	Skill	Official skill that guides Claude to write, structure, and test a new skill.	Free	1 click	8.7	Security: nothing to flag
ToolHiveRisingRuns each MCP server in an isolated container with managed permissions and secrets.	App	Runs each MCP server in an isolated container with managed permissions and secrets.	Free	5 min	8.7	Security: nothing to flag
Krita AI DiffusionRisingPlugin that brings AI generation and inpainting locally into the free painting software Krita.	Plugin	Plugin that brings AI generation and inpainting locally into the free painting software Krita.	Free	5 min	8.5	Security: nothing to flag
NeMo GuardrailsRisingNVIDIA's programmable guardrails to control dialogues, topics, and tool calls.	App	NVIDIA's programmable guardrails to control dialogues, topics, and tool calls.	Free	Technical	8.5	Security: nothing to flag
Basic MemoryRisingAgent memory stored as local Markdown files, readable in Obsidian.	MCP	Agent memory stored as local Markdown files, readable in Obsidian.	Free	5 min	8.4	Security: nothing to flag
brand-guidelines (Anthropic)RisingExample skill that applies a brand charter (colors, typography, tone) to what Claude produces.	Skill	Example skill that applies a brand charter (colors, typography, tone) to what Claude produces.	Free	1 click	8.4	Security: nothing to flag
Wan2GPRisingInterface to run Wan, Hunyuan and LTX on modest GPUs.	App	Interface to run Wan, Hunyuan and LTX on modest GPUs.	Free	5 min	8.4	Security: nothing to flag
ACE-Step 1.5RisingFull music generation (vocals, structure, style) running locally, open source.	App	Full music generation (vocals, structure, style) running locally, open source.	Free	Technical	8.3	Security: nothing to flag
Cartographie AI Act (skill nAIvigate)Sorts your AI use cases by AI Act risk level, with role, obligations, deadlines and points to confirm.	Skill	Sorts your AI use cases by AI Act risk level, with role, obligations, deadlines and points to confirm.	Free	1 click	8.3	Security: nothing to flag
LocalAIRisingSelf-hosted OpenAI-compatible API covering text, image, audio and embeddings.	App	Self-hosted OpenAI-compatible API covering text, image, audio and embeddings.	Free	Technical	8.3	Security: nothing to flag
MLX (mlx-lm)RisingApple framework for running LLMs on M-series chips using unified memory.	App	Apple framework for running LLMs on M-series chips using unified memory.	Free	Technical	8.3	Security: nothing to flag
PyRITRisingMicrosoft's AI red-teaming toolkit.	App	Microsoft's AI red-teaming toolkit.	Free	Technical	8.3	Security: nothing to flag
Revue de PSSI (skill nAIvigate)Reviews a security policy and lists the gaps against ISO 27001:2022, with corrected wording.	Skill	Reviews a security policy and lists the gaps against ISO 27001:2022, with corrected wording.	Free	1 click	8.3	Security: nothing to flag
SuperpowersRisingComplete development methodology for agents, built on composable skills that activate automatically: brainstorming, TDD, debugging, review.	Plugin	Complete development methodology for agents, built on composable skills that activate automatically: brainstorming, TDD, debugging, review.	Free	1 click	8.3	Security: one caveat, see the card
Veille CVE ciblée (skill nAIvigate)Filters vulnerability bulletins against your actual estate and sorts them into 72 h, 30 days, to plan.	Skill	Filters vulnerability bulletins against your actual estate and sorts them into 72 h, 30 days, to plan.	Free	1 click	8.3	Security: nothing to flag
Applio (RVC)RisingModern interface for RVC voice conversion, training and inference running locally.	App	Modern interface for RVC voice conversion, training and inference running locally.	Free	5 min	8.2	Security: one caveat, see the card
Approbation humaine (human-in-the-loop)Pauses the agent and requests confirmation before a sensitive action.	Tool	Pauses the agent and requests confirmation before a sensitive action.	Free	5 min	8.2	Security: nothing to flag
KoboldCppRisingSingle executable to run GGUF models with an interface oriented towards writing and roleplay.	App	Single executable to run GGUF models with an interface oriented towards writing and roleplay.	Free	5 min	8.2	Security: nothing to flag
Permissions (Claude Code)Allow, deny, and ask rules per tool and per pattern.	Tool	Allow, deny, and ask rules per tool and per pattern.	Free	5 min	8.2	Security: nothing to flag
Claude Code Usage MonitorRisingReal-time monitor for Claude Code quotas and tokens in the terminal.	App	Real-time monitor for Claude Code quotas and tokens in the terminal.	Free	5 min	8.1	Security: nothing to flag
TRELLIS.2 (Microsoft)RisingMicrosoft image-to-3D model producing a PBR mesh in seconds, running locally.	App	Microsoft image-to-3D model producing a PBR mesh in seconds, running locally.	Free	Technical	8.1	Security: nothing to flag
Compte-rendu de comité sécurité (skill nAIvigate)Turns raw committee notes into decisions, dated actions with owners, open risks and deferred items.	Skill	Turns raw committee notes into decisions, dated actions with owners, open risks and deferred items.	Free	1 click	8.0	Security: nothing to flag
GitHub MCPRisingOfficial GitHub MCP server: issues, PRs, code, and Actions accessible to the agent.	MCP	Official GitHub MCP server: issues, PRs, code, and Actions accessible to the agent.	Free	5 min	8.0	Security: one caveat, see the card
Open WebUIRisingSelf-hosted chat interface in the style of ChatGPT, connected to Ollama or any OpenAI API.	App	Self-hosted chat interface in the style of ChatGPT, connected to Ollama or any OpenAI API.	Free	5 min	8.0	Security: one caveat, see the card
Playwright MCPRisingGives the agent a controllable browser: read pages, click, fill forms, test.	MCP	Gives the agent a controllable browser: read pages, click, fill forms, test.	Free	5 min	8.0	Security: one caveat, see the card
Plugins officiels Claude CodeRisingAnthropic's official marketplace of plugins and skills for Claude Code.	Plugin	Anthropic's official marketplace of plugins and skills for Claude Code.	Free	1 click	8.0	Security: one caveat, see the card
Skills documents Anthropic (docx, xlsx, pptx, pdf)RisingThe four official skills for reading, creating and editing Word, Excel, PowerPoint and PDF files from Claude.	Skill	The four official skills for reading, creating and editing Word, Excel, PowerPoint and PDF files from Claude.	Free	1 click	8.0	Security: one caveat, see the card
AGENTS.md (convention)A file of instructions at the root of the repository, read by most coding agents.	Skill	A file of instructions at the root of the repository, read by most coding agents.	Free	5 min	7.9	Security: nothing to flag
AutoGenRisingMicrosoft's multi-agent framework, a pioneer in the field.	App	Microsoft's multi-agent framework, a pioneer in the field.	Free	Technical	7.9	Security: nothing to flag
awesome-agent-skills (VoltAgent)RisingCatalogue of more than one thousand multi-agent skills, organised by domain.	Skill	Catalogue of more than one thousand multi-agent skills, organised by domain.	Free	1 click	7.9	Security: one caveat, see the card
Claude SquadRisingManages multiple terminal agents (Claude Code, Codex, OpenCode, Amp) in isolated workspaces.	App	Manages multiple terminal agents (Claude Code, Codex, OpenCode, Amp) in isolated workspaces.	Free	5 min	7.9	Security: one caveat, see the card
find-skills (Vercel)RisingSkill that searches and installs other skills from skills.sh on demand.	Skill	Skill that searches and installs other skills from skills.sh on demand.	Free	1 click	7.9	Security: one caveat, see the card
Video2XWatch outLocal video upscaling and frame interpolation (Real-ESRGAN, RIFE), open source.	App	Local video upscaling and frame interpolation (Real-ESRGAN, RIFE), open source.	Free	5 min	7.9	Security: nothing to flag
claude-code-templates (davila7)RisingComponent library for Claude Code: agents, commands, hooks, settings, with a web selection interface.	Plugin	Component library for Claude Code: agents, commands, hooks, settings, with a web selection interface.	Free	5 min	7.8	Security: one caveat, see the card
ComfyUIRisingA node-based workshop for running open-source image and video models locally.	App	A node-based workshop for running open-source image and video models locally.	Free	5 min	7.8	Security: one caveat, see the card
Filesystem MCPRisingReference MCP server for reading and writing files within authorized folders.	MCP	Reference MCP server for reading and writing files within authorized folders.	Free	5 min	7.8	Security: one caveat, see the card
Google Agent Development Kit (ADK)NewGoogle's open-source kit for designing multi-agent systems in Python, Java, Go, or TypeScript, with the A2A protocol and direct deployment to Vertex AI.	App	Google's open-source kit for designing multi-agent systems in Python, Java, Go, or TypeScript, with the A2A protocol and direct deployment to Vertex AI.	Free	5 min	7.8	Security: one caveat, see the card
Microsoft Agent FrameworkNewMicrosoft open-source framework for .NET and Python, successor to Semantic Kernel and AutoGen: agents, graph-based workflows, A2A and MCP.	App	Microsoft open-source framework for .NET and Python, successor to Semantic Kernel and AutoGen: agents, graph-based workflows, A2A and MCP.	Free	5 min	7.8	Security: one caveat, see the card
OpenAI Agents SDKNewOpenAI's open source framework for building agents and agent teams: handoffs between agents, guardrails, sessions, and built-in tracing.	App	OpenAI's open source framework for building agents and agent teams: handoffs between agents, guardrails, sessions, and built-in tracing.	Free	5 min	7.8	Security: one caveat, see the card
wshobson/agentsCommunity marketplace of 200+ agents, 180 skills, and 100 commands for Claude Code and others.	Plugin	Community marketplace of 200+ agents, 180 skills, and 100 commands for Claude Code and others.	Free	5 min	7.8	Security: one caveat, see the card
Blender MCPRisingMCP server that lets Claude or Cursor control Blender: scenes, objects, materials, rendering.	MCP	MCP server that lets Claude or Cursor control Blender: scenes, objects, materials, rendering.	Free	5 min	7.7	Security: one caveat, see the card
FooocusWatch outUltra-simplified local interface to generate high-quality SDXL images without technical adjustments.	App	Ultra-simplified local interface to generate high-quality SDXL images without technical adjustments.	Free	5 min	7.7	Security: nothing to flag
GPT-SoVITSVoice cloning and synthesis from a few seconds of audio, running locally.	App	Voice cloning and synthesis from a few seconds of audio, running locally.	Free	Technical	7.7	Security: one caveat, see the card
tool_search (Anthropic)Lets Claude find the right tool among hundreds without loading all schemas upfront.	Tool	Lets Claude find the right tool among hundreds without loading all schemas upfront.	Free	5 min	7.7	Security: nothing to flag
Tools et toolkits LangChainRisingOver 300 integrations usable as tools by a LangChain agent.	Tool	Over 300 integrations usable as tools by a LangChain agent.	Free	5 min	7.7	Security: one caveat, see the card
Tools Vercel AI SDKTyped tool definitions for agents in TypeScript.	Tool	Typed tool definitions for agents in TypeScript.	Free	5 min	7.7	Security: nothing to flag
TripoSRImage to 3D in under one second, open source, runs locally.	App	Image to 3D in under one second, open source, runs locally.	Free	Technical	7.7	Security: nothing to flag
andrej-karpathy-skillsRisingPortable skills inspired by Andrej Karpathy's practices for coding with an agent.	Skill	Portable skills inspired by Andrej Karpathy's practices for coding with an agent.	Free	5 min	7.6	Security: one caveat, see the card
LLM Guard (Protect AI)Watch outOpen source input and output scanners: injection, personal data, toxicity.	Tool	Open source input and output scanners: injection, personal data, toxicity.	Free	Technical	7.4	Security: nothing to flag
OpenClawRisingOpen-source self-hosted personal agent that acts on your behalf: emails, calendar, files, commands, browser, controlled from your messaging apps.	App	Open-source self-hosted personal agent that acts on your behalf: emails, calendar, files, commands, browser, controlled from your messaging apps.	Free	5 min	7.4	Security: one caveat, see the card
whisper.cppRisingC/C++ implementation of Whisper, very fast on CPU and Apple Silicon.	App	C/C++ implementation of Whisper, very fast on CPU and Apple Silicon.	Free	Technical	7.4	Security: nothing to flag
F5-TTSRisingSpeech synthesis and voice cloning via flow matching, fast and local.	App	Speech synthesis and voice cloning via flow matching, fast and local.	Free	Technical	7.3	Security: one caveat, see the card
FramePackWatch outLocal long video generation with only 6 GB of VRAM.	App	Local long video generation with only 6 GB of VRAM.	Free	5 min	7.3	Security: nothing to flag
Goose (Block) et ses extensions MCPRisingBlock's open source agent, extensible via MCP servers, running on your machine.	Plugin	Block's open source agent, extensible via MCP servers, running on your machine.	Free	5 min	7.3	Security: one caveat, see the card
herdrAgent multiplexer in Rust that detects Claude Code, Codex or Amp and displays their status: blocked, working, done, idle.	App	Agent multiplexer in Rust that detects Claude Code, Codex or Amp and displays their status: blocked, working, done, idle.	Free	5 min	7.3	Security: one caveat, see the card
LivePortraitAnimates a portrait from a reference video, locally.	App	Animates a portrait from a reference video, locally.	Free	Technical	7.3	Security: one caveat, see the card
Memory MCP (officiel)RisingReference knowledge graph memory server, stored in a local file.	MCP	Reference knowledge graph memory server, stored in a local file.	Free	1 click	7.3	Security: one caveat, see the card
cmuxRisingNative macOS terminal built on Ghostty, designed for agents: vertical tabs, notifications, built-in browser.	App	Native macOS terminal built on Ghostty, designed for agents: vertical tabs, notifications, built-in browser.	Free	5 min	7.2	Security: one caveat, see the card
claude-flow (ruflo)Watch outMulti-agent orchestration for Claude Code: swarms, shared memory, hooks.	Plugin	Multi-agent orchestration for Claude Code: swarms, shared memory, hooks.	Free	Technical	7.1	Security: one caveat, see the card
Crawl4AIRisingOpen source crawler optimized for LLMs, running locally.	Tool	Open source crawler optimized for LLMs, running locally.	Free	Technical	7.1	Security: one caveat, see the card
Vibe KanbanRisingKanban board to dispatch tasks to coding agents and track their progress.	App	Kanban board to dispatch tasks to coding agents and track their progress.	Free	5 min	7.1	Security: one caveat, see the card
YuERisingGenerate complete songs with lyrics, locally, open source.	App	Generate complete songs with lyrics, locally, open source.	Free	Technical	7.1	Security: one caveat, see the card
GPT4AllWatch outLocal public chat client by Nomic, with document discussion support.	App	Local public chat client by Nomic, with document discussion support.	Free	1 click	7.0	Security: nothing to flag
Strands AgentsNewAWS open source SDK for writing an AI agent in a few lines of Python or TypeScript: the model drives the loop, you declare the tools.	App	AWS open source SDK for writing an AI agent in a few lines of Python or TypeScript: the model drives the loop, you declare the tools.	Free	5 min	7.0	Security: one caveat, see the card
oh-my-opencode-slimMulti-agent suite for OpenCode: mix models and automatically delegate sub-tasks.	Plugin	Multi-agent suite for OpenCode: mix models and automatically delegate sub-tasks.	Free	5 min	6.9	Security: one caveat, see the card
Task, sous-agents (Claude Code)Launches an autonomous sub-agent with its own tools.	Tool	Launches an autonomous sub-agent with its own tools.	Free	5 min	6.9	Security: one caveat, see the card
Tools Claude Agent SDKClaude Code tools exposed in your own agent, with the permissions system.	Tool	Claude Code tools exposed in your own agent, with the permissions system.	Free	5 min	6.9	Security: one caveat, see the card
Tools OpenAI Agents SDKWebSearchTool, FileSearchTool, ComputerTool and your own functions.	Tool	WebSearchTool, FileSearchTool, ComputerTool and your own functions.	Free	5 min	6.9	Security: one caveat, see the card
text-generation-webuiRisingHistoric web interface for local LLMs, highly configurable.	App	Historic web interface for local LLMs, highly configurable.	Free	Technical	6.7	Security: one caveat, see the card
DeepFilterNetWatch outReal-time noise suppression, lightweight, works even on CPU.	App	Real-time noise suppression, lightweight, works even on CPU.	Free	Technical	6.6	Security: nothing to flag
Hunyuan3D 2.1 (Tencent)Watch outTextured PBR 3D generation from an image, running locally.	App	Textured PBR 3D generation from an image, running locally.	Free	Technical	6.6	Security: one caveat, see the card
Real-ESRGANWatch outLocal image and video upscaling, the backbone of many tools.	App	Local image and video upscaling, the backbone of many tools.	Free	Technical	6.6	Security: nothing to flag
RIFEWatch outAI-based video frame interpolation, running locally.	App	AI-based video frame interpolation, running locally.	Free	Technical	6.6	Security: nothing to flag
WebFetch, WebSearch (Claude Code)Web search and page retrieval from the code agent.	Tool	Web search and page retrieval from the code agent.	Free	5 min	6.6	Security: one caveat, see the card
memory (Anthropic)Persistent Claude memory stored in files you host.	Tool	Persistent Claude memory stored in files you host.	Free	5 min	6.5	Security: one caveat, see the card
Tools CrewAIReady-to-use tool catalogue for CrewAI agent teams.	Tool	Ready-to-use tool catalogue for CrewAI agent teams.	Free	5 min	6.5	Security: one caveat, see the card
Tools LlamaIndexLlamaHub tools and loaders for agents and RAG.	Tool	LlamaHub tools and loaders for agents and RAG.	Free	5 min	6.5	Security: one caveat, see the card
Tools smolagents (Hugging Face)Tools declared with a simple decorator, code execution by the agent.	Tool	Tools declared with a simple decorator, code execution by the agent.	Free	5 min	6.5	Security: one caveat, see the card
CrystalWatch outOpen source desktop app to launch and compare multiple Claude Code sessions in worktrees.	App	Open source desktop app to launch and compare multiple Claude Code sessions in worktrees.	Free	1 click	6.4	Security: one caveat, see the card
Mira-SceneNewReconstructs an editable 3D scene from a single photo: each object is modelled separately then placed back at its position and scale.	App	Reconstructs an editable 3D scene from a single photo: each object is modelled separately then placed back at its position and scale.	Free	Technical	6.4	Security: one caveat, see the card
Resemble EnhanceWatch outSpeech denoising and enhancement, open source.	App	Speech denoising and enhancement, open source.	Free	Technical	6.4	Security: nothing to flag
DiffRhythmWatch outGenerate complete tracks in seconds, locally.	App	Generate complete tracks in seconds, locally.	Free	Technical	6.1	Security: one caveat, see the card
LatentSync (ByteDance)Watch outHigh-quality diffusion-based lip sync, running locally.	App	High-quality diffusion-based lip sync, running locally.	Free	Technical	6.0	Security: one caveat, see the card
MuseTalkWatch outReal-time lip-sync running locally.	App	Real-time lip-sync running locally.	Free	Technical	6.0	Security: one caveat, see the card
MusicGen (Meta)Watch outMeta's text-to-music generation model with open weights.	App	Meta's text-to-music generation model with open weights.	Free	Technical	5.9	Security: one caveat, see the card
Qdrant MCP ServerNewOfficial Qdrant MCP server: gives Claude, Cursor, or any compatible agent semantic memory, with two actions, storing information and retrieving it by meaning.	MCP	Official Qdrant MCP server: gives Claude, Cursor, or any compatible agent semantic memory, with two actions, storing information and retrieving it by meaning.	Free	Technical	5.9	Security: one caveat, see the card
OmniRouteRisingLocal open-source gateway in front of 290+ providers with automatic quota-based switching.	App	Local open-source gateway in front of 290+ providers with automatic quota-based switching.	Free	Technical	5.5	Security: serious reservations

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