Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to research potential clients
-
Since Jan 2024, Google's models have been #1 on Arena for 227 of 1003 days, third among labs.
-
claude-opus-4-6-high leads Arena coding at 1535. Anthropic has held #1 for 280 days, but Z.ai.
-
On 11 Sept 2026, Claude's best model rates 40 points above OpenAI's and 16 above Gemini's..
-
OpenAI was the #1 lab on Arena for 95% of 2024. On 25 Sept 2026 it ranks 8th among labs, and.
-
evaluation-guidebook
Docs & tutorialsSharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!
git clone https://github.com/huggingface/evaluation-guidebook.git -
The gap between Arena's #1 and #10 models fell from 148 points in Feb 2024 to 18. #10 now wins.
-
all-agentic-architectures
Agents & frameworks35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard.
git clone https://github.com/FareedKhan-dev/all-agentic-architectures.git -
tokscale
Agents & frameworks🛰️ Track token usage across AI coding agents from your terminal. 🏅 Global leaderboard with trillions of tokens tracked.
git clone https://github.com/junhoyeo/tokscale.git -
ghfind
Tools & appsDiscover the best developers — and become one. Drop a GitHub handle for a 0–100 value & trust score in 30s: see your gaps, discover top devs, get found. Exposes PR farmers, AI bots & fork-hoarders. Deterministic scoring, self-hostable.
git clone https://github.com/FindAny/ghfind.git -
opentai.github.io
SkillsThe official website of the Open Trustworthy AI Community (OpenTAI).
git clone https://github.com/OpenTAI/opentai.github.io.git -
WakaTime
Public APIsAutomated time tracking leaderboards for programmers
-
docext
AI repositoriesAn on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)
git clone https://github.com/NanoNets/docext.git -
mcp-geraquest
MCP serversAI prompt engineering game: challenges, leaderboards, community prompts.
@gera-services/mcp-geraquest@0.1.1 -
F1Laps
MCP serversRead-only F1 game laps, telemetry, setups, leaderboard benchmarks, and progress.
-
forgejudge
MCP serversOpen eval leaderboard + CI gate for autonomous coding agents (solve, score, trace).
forgejudge@0.1.0 -
specter-skills
MCP serversConfigure a Specter game backend from chat: economy, progression, leaderboards, multiplayer.
specter-skills@0.11.1 -
speedrun-mcp
MCP serversMCP server for speedrun.com, world records, category leaderboards, runner profiles.
speedrun-mcp@1.0.1 -
bottrade
MCP serversBenchmark for AI trading agents: historic market scenarios, public leaderboard.
-
Fantopy
MCP serversFree World Cup 2026 prediction game with fixtures, picks, brackets, and leaderboards
-
ari-mcp
MCP serversFair-price checks, leaderboards, and Ed25519 receipt verification for x402/MPP services.
ari-mcp@0.1.3 -
three.ws Intel
MCP serversCoin smart-money scores, wallet reputation, signal feeds, and KOL leaderboards.
@three-ws/intel-mcp@0.1.3 -
waitlist-kit
MCP serversViral waitlists with referral tracking, leaderboards, analytics, and built-in themes.
-
speedrun.com
MCP serversspeedrun.com records, leaderboards (subcategories, ILs), players, PBs, moderation. No key needed.
speedrun-mcp@0.3.4 -
HiveLearn
MCP serversRead and author HiveLearn courses, events, quizzes, certificates, resources, leaderboards, tracks.
hivelearn-mcp@0.1.2
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.