Hlido
About
Independent, evidence-backed reviews of AI agents — machine-readable scorecards, claim audits, C2PA-signed proof. Public data mirror of hlido.eu
Details
- Author
- ankitkapur1992-hlido
- Downloads
- 292
- Categories
- Developer Tools
Jump to
- Independent, evidence-backed reviews of AI agents
- Consistent Laddoo Score (0–100) across all agents
- C2PA-signed screenshots and terminal casts for proof
- Live MCP server with 9 JSON-RPC 2.0 tools
- Structured machine-readable scorecards in JSON format
- Independent MCP-server safety register with per-flag evidence
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
HlidoCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Use the MCP server at https://hlido.eu/mcp via JSON-RPC 2.0. No authentication is required, and it is free to call. Tools include trust_check, find_similar_agents, get_scorecard, request_quick_audit, verify_claim, and compare_agents. You can also access the public mirror repository on GitHub to use the scorecard JSON files directly from your own scripts, agents, or analysis pipelines.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"hlido": {
"hlido": {
"type": "streamable-http",
"url": "https://hlido.eu/mcp"
}
}
}
}
McpServers
{
"hlido": {
"type": "streamable-http",
"url": "https://hlido.eu/mcp"
}
}
Hlido — the trust layer for AI agents
Independent, evidence-backed reviews of AI agents. C2PA-signed proof, machine-readable scorecards, and a Laddoo Score that's consistent across every reviewed agent — so buyers, teams, and other agents can tell which ones live up to their pitch.
This repository is the public mirror of hlido.eu. Every review pushed live on the canonical site is mirrored here automatically — sanitized, machine-readable, fork-friendly. Use it from your own scripts, agents, or analysis pipelines without scraping HTML.
---
Why Hlido exists
Every week, dozens of new AI agents launch. Each one claims to write code, run workflows, handle support, or close deals. Some deliver. Most don't — at least not the way their landing page implies.
Until now, the only way to know was to sign up, burn a weekend, and find out yourself. That doesn't scale — not for procurement teams choosing vendors, not for builders wiring agents into production, and crucially not for other agents that will increasingly make those calls on our behalf.
Hlido is the independent party that actually tests every claim. We publish verdicts grounded in captured evidence, track them over time, and surface the patterns the market needs to see.
What we provide
- Independent reviews of AI agents — public-surface tested for web tools, live CLI tested for terminal tools, claim-by-claim verification for everything
- A consistent score — every agent gets a Laddoo Score (0–100) derived from a fixed evaluation framework. Tier mapping: VITAL ≥ 90 · STEADY ≥ 70 · FADING ≥ 40 · FLATLINE < 40
- C2PA-signed evidence — screenshots and (where applicable) terminal casts are cryptographically signed, so the captured proof can be verified as un-tampered
- A live MCP server — 9 tools exposed at https://hlido.eu/mcp for human and agent consumers. JSON-RPC 2.0, no auth required, free to call. Tools include trust_check, find_similar_agents (semantic search), get_scorecard (full claim table), request_quick_audit, verify_claim, compare_agents, and more
- Structured machine-readable scorecards — every review is also published as a JSON file in this repo (scorecards/{slug}.json) with the full claim-vs-evidence table, source-surface citations, and stable schema (schema_version: 1.0)
- An independent MCP-server safety register — MCP servers scored safety-first (tool-poisoning / dangerous-capability / auth-posture red-flags → SAFE / CAUTION / RISKY / DANGEROUS) with published per-flag evidence, never a bare number. Early first cohort: hlido.eu/mcp/ · data at /data/mcp-register.json
- Distribution everywhere — also indexed on Smithery, HuggingFace dataset, and the community awesome-mcp-servers list
Reviewed agents (825)
| Slug | Name | Category | Laddoo | Tier |
|---|---|---|---|---|
| klariqo | Klariqo | Voice | 58 | FADING |
| baton | Baton | Frameworks & Eval | 64 | FADING |
| openowl | OpenOwl | Workflow & Automation | 50 | FADING |
| naoma-ai-demo-agent | Naoma AI Demo Agent | Customer Experience | 80 | — |
| holo | Holo | Marketing & Content | 50 | FADING |
| parakeeet-ai | Parakeeet AI | Sales | 80 | STEADY |
| workbeaver | WorkBeaver | Productivity | 63.4 | — |
| gumloop | Gumloop | Workflow & Automation | 80 | — |
| aider | Aider | Coding | 90 | — |
| jared-so | jared-so | Productivity | 40 | — |
| raccoon-ai | raccoon-ai | Productivity | 70 | — |
| needle-2-0 | needle-2-0 | Productivity | 80 | — |
| zooclaw | zooclaw | Productivity | 40 | — |
| agentpulse-by-rectify | agentpulse-by-rectify | Workflow & Automation | 40 | — |
| genspark | genspark | Research | 40 | — |
| askiva | askiva | Research | 40 | — |
| influcio | influcio | AI Agent | 65 | — |
| lindy-ai | lindy-ai | AI Agent | 50 | — |
| ovren | ovren | AI Agent | 40 | — |
| panorama | panorama | AI Agent | 40 | — |
| poke | poke | AI Agent | 60 | — |
| spine-ai | spine-ai | AI Agent | 65 | — |
| synthflow-ai | synthflow-ai | AI Agent | 80 | — |
| flux | flux | AI Agent | 40 | — |
| agentmail | agentmail | AI Agent | 53 | — |
| lmarena | Chatbot Arena (LMArena) | Frameworks & Eval | 40 | — |
| perplexity | Perplexity | Research | 53 | — |
| happycapy | happycapy | AI Agent | 90 | — |
| back4app-ai-agent | Back4app AI Agent | AI Agent | 40 | — |
| luma-ai-agents | Luma AI Agents | AI Agent | 65 | — |
| agent-ai | Agent.ai | AI Agent | 78 | — |
| windsurf | Windsurf | Coding | 65 | — |
| cal-com-ai-agents | Cal.com AI Agents | AI Agent | 78 | — |
| usercall | UserCall | AI Agent | 40 | — |
| mindstudio | MindStudio | AI Agent | 78 | — |
| foyer | Foyer | AI Agent | 40 | — |
| hubspot-breeze | HubSpot Breeze | AI Agent | 53 | — |
| octoclaw | OctoClaw | AI Agent | 40 | — |
| molmoweb | MolmoWeb | AI Agent | 40 | — |
| guide-ai | Guide | AI Agent | 53 | — |
| adobe-firefly | Adobe Firefly | AI Agent | 53 | — |
| tad-ai | Tad AI | AI Agent | 65 | — |
| genfuse-ai | GenFuse AI | AI Agent | 78 | — |
| outset-ai | Outset AI | AI Agent | 65 | — |
| autonoly | Autonoly | AI Agent | 78 | — |
| cockpit-ai | Cockpit AI | AI Agent | 53 | — |
| lessie-ai | Lessie AI | AI Agent | 78 | — |
| aiagent-app | AiAgent.app | AI Agent | 65 | — |
| klipy | Klipy | AI Agent | 40 | — |
| fuseai | FuseAI | AI Agent | 53 | — |
| relay-app | Relay.app | AI Agent | 78 | — |
| canary-ai | Canary | AI Agent | 53 | — |
| augment-code | Augment Code (Intent) | Coding | 78 | — |
| cursor | Cursor | Coding | 78 | — |
| cto-new | cto.new | AI Agent | 90 | — |
| orange-slice | Orange Slice | AI Agent | 90 | — |
| claimcheck | ClaimCheck | Coding | 65 | — |
| kaily | Kaily | AI Agent | 78 | — |
| magine | Magine | AI Agent | 65 | — |
| blink-ai | Blink | AI Agent | 65 | — |
| cosyra-2 | Cosyra | AI Agent | 78 | — |
| catdoes-v4 | CatDoes v4 | AI Agent | 65 | — |
| denovo | Denovo | AI Agent | 78 | — |
| athena-intel | Athena Intelligence | Workflow & Automation | 53 | — |
| anthropic-computer-use | Anthropic Computer Use | Infrastructure | 40 | — |
| anyword | Anyword | Marketing & Content | 90 | — |
| axe | Axe | AI Agent | 40 | — |
| bolt-new | Bolt.new | Coding | 65 | — |
| braintrust | Braintrust | Frameworks & Eval | 90 | — |
| cerebras | Cerebras | Infrastructure | 65 | — |
| cassidy-ai | Cassidy | Workflow & Automation | 78 | — |
| chatgpt | ChatGPT | Chat & Companion | 65 | — |
| character-ai | Character.AI | Chat & Companion | 53 | — |
| chatwithads | ChatWithAds | AI Agent | 78 | — |
| claude-ai | Claude.ai | Chat & Companion | 53 | — |
| cline-bot | Cline | Coding | 78 | — |
| codeium | Codeium | Coding | 65 | — |
| continue-dev | Continue | Coding | 78 | — |
| cohere | Cohere | Chat & Companion | 78 | — |
| copy-ai | Copy.ai | Marketing & Content | 78 | — |
| crewai | CrewAI | Frameworks & Eval | 90 | — |
| datagrout | DataGrout | AI Agent | 40 | — |
| dust-tt | Dust | Workflow & Automation | 90 | — |
| descript | Descript | Voice | 65 | — |
| elevenlabs | ElevenLabs | Voice | 78 | — |
| flux-bfl | FLUX (Black Forest Labs) | Image & Design | 65 | — |
| flowith | Flowith | Workflow & Automation | 78 | — |
| fireworks-ai | Fireworks AI | Infrastructure | 90 | — |
| gemini | Gemini | Chat & Companion | 53 | — |
| granola | Granola | Productivity | 65 | — |
| github-copilot | GitHub Copilot | Coding | 90 | — |
| glean | Glean | Research | 65 | — |
| helicone | Helicone | Frameworks & Eval | 90 | — |
| groq | Groq | Infrastructure | 78 | — |
| heygen | HeyGen | Voice | 78 | — |
| humanloop | Humanloop | Frameworks & Eval | 40 | — |
| ideogram | Ideogram | Image & Design | 40 | — |
| inflection-pi | Inflection Pi | Chat & Companion | 53 | — |
| jasper | Jasper | Marketing & Content | 90 | — |
| krea | Krea | Image & Design | 78 | — |
| langchain | LangChain | Frameworks & Eval | 90 | — |
| langsmith | LangSmith | Frameworks & Eval | 53 | — |
| leonardo-ai | Leonardo AI | Image & Design | 78 | — |
| llamaindex | LlamaIndex | Frameworks & Eval | 78 | — |
| lovable | Lovable | Coding | 78 | — |
| mem-ai | Mem | Productivity | 90 | — |
| microsoft-copilot | Microsoft Copilot | Chat & Companion | 53 | — |
| midjourney | Midjourney | Image & Design | 53 | — |
| mendable | Mendable | Research | 78 | — |
| mistral-le-chat | Mistral Le Chat | Chat & Companion | 40 | — |
| notion-ai | Notion AI | Research | 65 | — |
| murf-ai | Murf AI | Voice | 65 | — |
| nyx | Nyx | AI Agent | 40 | — |
| openai-operator | OpenAI Operator | Infrastructure | 65 | — |
| openrouter | OpenRouter | Infrastructure | 78 | — |
| phind | Phind | Chat & Companion | 40 | — |
| pika | Pika | Image & Design | 40 | — |
| otter-ai | Otter.ai | Productivity | 90 | — |
| pydantic-ai | Pydantic AI | Frameworks & Eval | 78 | — |
| reflect-app | Reflect | Productivity | 65 | — |
| read-ai | Read AI | Productivity | 78 | — |
| resemble-ai | Resemble AI | Voice | 78 | — |
| replit-agent | Replit Agent | Coding | 90 | — |
| relevance-ai | Relevance AI | Workflow & Automation | 90 | — |
| runway | Runway | Image & Design | 78 | — |
| sonarly | Sonarly | AI Agent | 53 | — |
| retool-agents | Retool Agents | Workflow & Automation | 78 | — |
| stability-ai | Stability AI | Image & Design | 90 | — |
| sourcegraph-cody | Sourcegraph Cody | Coding | 90 | — |
| stack-ai | Stack AI | Workflow & Automation | 78 | — |
| suno | Suno | Voice | 53 | — |
| superhuman | Superhuman | Productivity | 78 | — |
| synthesia | Synthesia | Voice | 90 | — |
| tabnine | Tabnine | Coding | 90 | — |
| tana | Tana | Productivity | 65 | — |
| tavus | Tavus | Voice | 78 | — |
| v0 | v0 | Coding | 65 | — |
| together-ai | Together AI | Infrastructure | 65 | — |
| vercel-ai-sdk | Vercel AI SDK | Frameworks & Eval | 78 | — |
| vellum-ai | Vellum | Frameworks & Eval | 78 | — |
| you-com | You.com | Chat & Companion | 78 | — |
| writer-com | Writer | Marketing & Content | 78 | — |
| zapier-central | Zapier Central | Workflow & Automation | 90 | — |
| bland-ai | Bland AI | Voice | 78 | — |
| retell-ai | Retell AI | Voice | 90 | — |
| vapi-ai | Vapi | Voice | 90 | — |
| deepgram | Deepgram | Voice | 90 | — |
| assemblyai | AssemblyAI | Voice | 90 | — |
| hume-ai | Hume AI | Voice | 65 | — |
| daily-co | Daily | Voice | 90 | — |
| livekit | LiveKit | Voice | 78 | — |
| speechmatics | Speechmatics | Voice | 78 | — |
| rev-ai | Rev AI | Voice | 78 | — |
| salesloft | Salesloft | Customer Experience | 78 | — |
| chorus-ai | Chorus | Customer Experience | 65 | — |
| outreach-io | Outreach | Customer Experience | 65 | — |
| gong-io | Gong | Customer Experience | 78 | — |
| apollo-io | Apollo.io | Customer Experience | 40 | — |
| clay-com | Clay | Customer Experience | 90 | — |
| regie-ai | Regie AI | Customer Experience | 78 | — |
| instantly-ai | Instantly | Customer Experience | 90 | — |
| smartlead | Smartlead | Customer Experience | 78 | — |
| lavender-ai | Lavender | Customer Experience | 78 | — |
| kore-ai | Kore.ai | Customer Experience | 65 | — |
| ada-cx | Ada | Customer Experience | 78 | — |
| decagon | Decagon | Customer Experience | 65 | — |
| ultimate-ai | Ultimate | Customer Experience | 65 | — |
| intercom-fin | Intercom Fin | Customer Experience | 65 | — |
| forethought | Forethought | Customer Experience | 90 | — |
| cresta | Cresta | Customer Experience | 65 | — |
| sierra-ai | Sierra | Customer Experience | 53 | — |
| netomi | Netomi | Customer Experience | 53 | — |
| cognigy | Cognigy | Customer Experience | 78 | — |
| devin-cognition | Devin (Cognition) | Coding | 65 | — |
| openhands | OpenHands | Coding | 90 | — |
| sweep-ai | Sweep | Coding | 90 | — |
| openinterpreter | Open Interpreter | Coding | 78 | — |
| metagpt | MetaGPT | Coding | 65 | — |
| gpt-engineer | GPT Engineer | Coding | 78 | — |
| agentgpt | AgentGPT | Coding | 53 | — |
| autogen-studio | AutoGen Studio | Coding | 78 | — |
| smol-ai | Smol Developer | Coding | 40 | — |
| superagi | SuperAGI | Coding | 78 | — |
| plandex | Plandex | Coding | 65 | — |
| warp-ai | Warp AI | Coding | 78 | — |
| elicit | Elicit | Research | 65 | — |
| zed-ai | Zed AI | Coding | 90 | — |
| scite-ai | Scite | Research | 78 | — |
| consensus-app | Consensus | Research | 53 | — |
| scholarcy | Scholarcy | Research | 78 | — |
| exa-ai | Exa | Research | 90 | — |
| kagi | Kagi | Research | 78 | — |
| andi-search | Andi Search | Research | 53 | — |
| komo-ai | Komo | Research | 53 | — |
| notebooklm | NotebookLM | Research | 65 | — |
| hebbia | Hebbia | Research | 78 | — |
| casetext | Casetext | Specialized verticals | 40 | — |
| ironclad | Ironclad | Specialized verticals | 78 | — |
| harvey-ai | Harvey | Specialized verticals | 53 | — |
| evisort | Evisort | Specialized verticals | 53 | — |
| spellbook-legal | Spellbook | Specialized verticals | 90 | — |
| luminance | Luminance | Specialized verticals | 65 | — |
| hippocratic-ai | Hippocratic AI | Specialized verticals | 53 | — |
| suki-ai | Suki | Specialized verticals | 90 | — |
| glass-health | Glass Health | Specialized verticals | 78 | — |
| abridge | Abridge | Specialized verticals | 53 | — |
| nabla | Nabla | Specialized verticals | 78 | — |
| mutiny | Mutiny | Marketing & Content | 65 | — |
| persado | Persado | Marketing & Content | 53 | — |
| optimizely-opal | Optimizely Opal | Marketing & Content | 90 | — |
| smartwriter | Smartwriter | Marketing & Content | 65 | — |
| rytr | Rytr | Marketing & Content | 78 | — |
| hyperwrite | HyperWrite | Marketing & Content | 78 | — |
| simplified | Simplified | Marketing & Content | 78 | — |
| khanmigo | Khanmigo | Specialized verticals | 53 | — |
| quizizz | Quizizz AI | Specialized verticals | 65 | — |
| magic-school | MagicSchool | Specialized verticals | 78 | — |
| brisk-teaching | Brisk Teaching | Specialized verticals | 78 | — |
| galileo-ai-design | Galileo (Design) | Image & Design | 40 | — |
| uizard | Uizard | Image & Design | 78 | — |
| framer-ai | Framer AI | Image & Design | 65 | — |
| browser-base | Browserbase | Infrastructure | 78 | — |
| recraft-ai | Recraft | Image & Design | 78 | — |
| figma-make | Figma Make | Image & Design | 65 | — |
| anchor-browser | Anchor Browser | Infrastructure | 78 | — |
| simular | Simular | Infrastructure | 78 | — |
| scrapybara | Scrapybara | Infrastructure | 78 | — |
| multion | MultiOn | Infrastructure | 53 | — |
| browser-use | Browser Use | Infrastructure | 78 | — |
| pinecone | Pinecone | Infrastructure | 90 | — |
| weaviate | Weaviate | Infrastructure | 90 | — |
| voyage-ai | Voyage AI | Infrastructure | 65 | — |
| jina-ai | Jina AI | Infrastructure | 65 | — |
| qdrant | Qdrant | Infrastructure | 90 | — |
| hex-tech | Hex | Infrastructure | 78 | — |
| julius-ai | Julius | Infrastructure | 78 | — |
| n8n | n8n | Workflow & Automation | 90 | — |
| make-com | Make | Workflow & Automation | 90 | — |
| activepieces | Activepieces | Workflow & Automation | 90 | — |
| zapier | Zapier | Workflow & Automation | 90 | — |
| integrately | Integrately | Workflow & Automation | 90 | — |
| langflow | Langflow | Workflow & Automation | 78 | — |
| flowiseai | Flowise | Workflow & Automation | 78 | — |
| pipedream | Pipedream | Workflow & Automation | 90 | — |
| magic-dev | Magic | Coding | 53 | — |
| dify-ai | Dify | Workflow & Automation | 78 | — |
| poolside-ai | Poolside | Coding | 65 | — |
| contextual-ai | Contextual AI | Research | 78 | — |
| phoenix-arize | Phoenix (Arize) | Frameworks & Eval | 90 | — |
| langfuse | Langfuse | Frameworks & Eval | 90 | — |
| traceloop | Traceloop | Frameworks & Eval | 90 | — |
| promptlayer | PromptLayer | Frameworks & Eval | 65 | — |
| ragas | Ragas | Frameworks & Eval | 78 | — |
| trulens | TruLens | Frameworks & Eval | 65 | — |
| portkey-ai | Portkey | Frameworks & Eval | 90 | — |
| inkeep | Inkeep | Customer Experience | 78 | — |
| kapa-ai | Kapa AI | Customer Experience | 90 | — |
| guru-ai | Guru | Productivity | 78 | — |
| self-operating-computer | Self-Operating Computer | Workflow & Automation | 90 | — |
| skyvern-ai | Skyvern | Infrastructure | 65 | — |
| fathom-video | Fathom | Productivity | 65 | — |
| fellow-app | Fellow | Productivity | 78 | — |
| clay-relationship | Clay (relationships) | Productivity | 65 | — |
| spinach-ai | Spinach | Productivity | 78 | — |
| anyscale | Anyscale | Infrastructure | 90 | — |
| baseten | Baseten | Infrastructure | 78 | — |
| modal-com | Modal | Infrastructure | 90 | — |
| ollama | Ollama | Infrastructure | 90 | — |
| replicate | Replicate | Infrastructure | 78 | — |
| lmstudio | LM Studio | Infrastructure | 65 | — |
| deepseek-chat | DeepSeek | Chat & Companion | 53 | — |
| xai-grok | Grok (xAI) | Chat & Companion | 65 | — |
| hugging-face | HuggingFace | Infrastructure | 78 | — |
| qwen-chat | Qwen Chat | Chat & Companion | 40 | — |
| kimi-moonshot | Kimi (Moonshot) | Chat & Companion | 53 | — |
| replika | Replika | Chat & Companion | 53 | — |
| yi-01ai | Yi (01.AI) | Chat & Companion | 53 | — |
| scenario-gg | Scenario | Image & Design | 65 | — |
| playground-ai | Playground AI | Image & Design | 78 | — |
| nightcafe | NightCafe | Image & Design | 53 | — |
| luma-genie | Luma Genie | Image & Design | 65 | — |
| meshy-ai | Meshy | Image & Design | 90 | — |
| clickup-ai | ClickUp AI | Productivity | 78 | — |
| monday-ai | Monday AI | Productivity | 53 | — |
| smartsheet-ai | Smartsheet AI | Productivity | 90 | — |
| openai-realtime | OpenAI Realtime | Infrastructure | 90 | — |
| perplexity-api | Perplexity API | Infrastructure | 90 | — |
| tavily-api | Tavily | Infrastructure | 78 | — |
| airtable-ai | Airtable AI | Productivity | 90 | — |
| dia-browser | Dia (The Browser Company) | Infrastructure | 53 | — |
| arc-browser | Arc Browser | Infrastructure | 78 | — |
| aria-opera | Aria (Opera) | Infrastructure | 65 | — |
| serpapi | SerpAPI | Infrastructure | 78 | — |
| brave-leo | Brave Leo | Infrastructure | 78 | — |
| kensho | Kensho | Specialized verticals | 53 | — |
| ravenpack | RavenPack | Specialized verticals | 65 | — |
| alphasense | AlphaSense | Specialized verticals | 90 | — |
| paradigm-ai | Paradigm | Productivity | 78 | — |
| lutra | Lutra | Workflow & Automation | 78 | — |
| you-com-search |
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.





