Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
{ "role": "Calm, methodical home internet troubleshooting and service credit assistant who helps households log outages and slow speeds, run fair speed tests, work through fixes in a sensible order, claim credits or…
-
speed-to-lead
MCP serversField-service tools for agents: slot feasibility, drive time, service area, lead parsing, booking.
-
SpeedyIndex
MCP serversGoogle, Bing and Yandex index checks, link indexing, backlink checks and Google Rank Tracker.
speedyindex-mcp@0.1.2 -
Speed Reader
MCP serversTurn any article, document, or chat reply into a one-word-at-a-time RSVP reading session.
-
Typing Speed Test
PromptsBuild an interactive typing speed test using HTML5, CSS3, and JavaScript. Create a clean interface with text display and input area. Implement WPM and accuracy calculation in real-time. Add difficulty levels with…
-
surogate
AI repositoriesTrain and serve LLMs at extreme speed and massive throughput.
git clone https://github.com/invergent-ai/surogate.git -
Speedbot.dev — AI agent marketplace
MCP serversAI agent marketplace: hire independent agents for code review, research and data checks in USDC.
-
LightLLM
AI repositoriesLightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
git clone https://github.com/ModelTC/LightLLM.git -
ai-notes
Promptsnotes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references under the /Resources folder.
git clone https://github.com/swyxio/ai-notes.git -
mcp
MCP serversSearch live roles across hundreds of a16z portfolio startups and join the speedrun talent network.
-
openbench
Datasets & benchmarksSame model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open models on correctness, speed, and token cost
git clone https://github.com/minghinmatthewlam/openbench.git -
san
Agents & frameworksOpen-source terminal agent runtime. Lean context, native speed, open all the way down — in a single Go binary.
git clone https://github.com/genai-io/san.git -
flow-like
Tools & appsFlow-Like: Strongly Typed Enterprise Scale Workflows. Built for scalability, speed, seamless AI integration and rich customization.
git clone https://github.com/Rheosoph/flow-like.git -
seo
MCP serversSEO analysis - meta tags, keywords, links, page speed
@rog0x/mcp-seo-tools@1.0.1 -
blitzstrike
MCP serversBlitz Strike — a universal MCP security-audit toolbelt. Reconnaissance at speed. Analysis in depth. Validation before report.
git clone https://github.com/shinthink/blitzstrike.git -
paad
SkillsThe practices that made software work didn't stop working. They stopped keeping up. PAAD brings them back at AI speed.
git clone https://github.com/Ovid/paad.git -
Gemini 3.8 Flash
ModelsAgents and complex multi-step workflows at Flash speed.
-
GPT-6 Luna
ModelsFocused, high-volume tasks where speed and running cost matter most.
-
dapr-skills
SkillsA set of AI skills to speed up the creation of Dapr applications that use Workflow, Pub/Sub or Agents
git clone https://github.com/diagrid-labs/dapr-skills.git -
FCC Broadband Map
MCP serversBroadband availability, providers, speeds, and BEAD classification from the FCC
-
Relvato
MCP serversWebsite monitoring: uptime, checkout, SEO (Search Console, Bing), security, speed, DNS, compliance.
-
metrillm
MCP serversBenchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client
metrillm-mcp@0.2.6 -
Zovo Typing Test
MCP serversTake a typing speed test without leaving the chat.
-
BenchLeader
MCP serversDaily LLM leaderboard from independent benchmarks: ranks, scores, prices, speed and comparisons.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.