- FastMetal @fastmetal/fastmetalRun and compare LLMs, generate images and video, with the real yen cost returned per call.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- FastGPU @fastgpu/fastgpuCompare live GPU cloud rental prices and match workloads to the cheapest provider.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agentgates MCP @agentgates/mcpConfidential compute and inference sold to agents over x402 USDC, plus an agent wallet over MCP.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- ScoreIA Open Chamber @scoreia/benchTest your AI agent over MCP in the Open Chamber: a timed public trial with signed cards.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- prism. MCP @prismnetwork/mcpRent real NVIDIA GPUs from your agent. Browse with no wallet; pay per second onchain.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- GPT-4o API — JoJ API @jojapi/gpt-4o-ksdwzwGPT-4o: GPT-4o (“o” for “omni”) is our versatile, high-intelligence flagship model. It accepts both.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- GPT-5 API — JoJ API @jojapi/gpt-5GPT-5: GPT‑5 is OpenAI’s most advanced and unified AI model, combining fast, real-time.20% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- NiceVois @nicevois/rvc-trainingFree stem, lead/backing vocal, noise and reverb splitting, no account. Train and use RVC voices.17% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Execute bias-drift-monitor-mcp @evozim/bias-drift-monitor-mcpPremium agentic endpoint for bias-drift-monitor-mcp.19% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Execute carbon-aware-inference-router-mcp @evozim/carbon-aware-inference-router-mcpPremium agentic endpoint for carbon-aware-inference-router-mcp.17% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- OpenWakeWord / microWakeWord — custom wake-word training @openwakeword/wake-word-trainingTrain custom wake words from your agent: estimator, GPU training, benchmarks. Card or crypto.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Qwen38 Free Gateway @khs0927/qwen38-free-gatewayFree Qwen3.8-27B gateway with isolated Minis provider, SSE, retry/failover, and MCP.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Frontier @openfrontier/frontierDiscover Frontier inference capabilities and read sanitized usage through read-only tools.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Genomic Intelligence @genomicintelligence/genomic-intelligenceHosted DNA language models: promoter, splice, enhancer, chromatin, expression, annotation3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- The Aggregate — LLM benchmark aggregate @theaggregate/the-aggregateLLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily.2% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Evalgate @ipezygj/evalgateStatistical checks an agent runs before trusting an AI eval number (is #1 real, judge bias, more).5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Terradev @theoddden/terradevCross-cloud GPU orchestration CLI.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Eval Engine API @invertedhoologan/eval-engine-mcpPay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- LMX Cloud LLM Inference @lmxcloud/mcp-serverOpenAI-compatible LLM MCP (7 tools); chat via balance key or x402 USDC on Base5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Oriora Router @orioralabs/routerAI model routing on your own vendor keys: pick the best model per prompt, or route and run it.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- EuEarth @chaot-kit/euearthEuEarth: agent-first commons — one free open model per domain on a stable keel; best wins.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- INKFLOW — ULTRA LoRA Actors & Worlds for AI Video, and Books to 900k Words @inkflowstudio/inkflowWrite a full-length novel free, no signup. A finished manuscript, not another workspace.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- good-sport @good-sport/good-sportSports-analytics research assistant that grades its own model and reports the losses. $9.99/mo.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Cheapestinference MCP @cheapestinference/mcpDiscover unlimited LLM inference pools, get USDC quotes, subscribe on Base, check key status.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
