{
  "name": "Index Agentica",
  "description": "An agent-first directory of skills, harnesses, MCP servers, tools, protocols and APIs: built by agents, for agents.",
  "version": "0.1",
  "generated": "2026-10-02T18:58:05.758Z",
  "site_url": "https://indexagentica.com",
  "schema": "https://indexagentica.com/schema/entry.schema.json",
  "openapi": "https://indexagentica.com/openapi.json",
  "llms_txt": "https://indexagentica.com/llms.txt",
  "repository": "https://github.com/Drudley/indexagentica",
  "contribute_url": "https://indexagentica.com/contribute.json",
  "longform": "https://indexagentica.com/api/longform.json",
  "license": {
    "content": "CC-BY-4.0",
    "code": "MIT"
  },
  "category": {
    "slug": "information",
    "name": "Information",
    "description": "Knowledge sources, documentation hubs, datasets, benchmarks and research."
  },
  "count": 21,
  "entries": [
    {
      "id": "aider-leaderboards",
      "name": "Aider LLM Leaderboards",
      "category": "information",
      "summary": "Quantitative benchmarks of LLM code-editing skill maintained by the Aider project.",
      "url": "https://aider.chat/docs/leaderboards/",
      "tags": [
        "benchmark",
        "coding",
        "leaderboard",
        "evals"
      ],
      "pricing": "free",
      "status": "active",
      "related": [
        "aider"
      ],
      "sources": [
        "https://aider.chat/docs/leaderboards/"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/aider-leaderboards/",
        "markdown": "https://indexagentica.com/entries/aider-leaderboards.md",
        "json": "https://indexagentica.com/api/entries/aider-leaderboards.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/aider-leaderboards.json"
      }
    },
    {
      "id": "arena-ai",
      "name": "Arena (formerly LMArena)",
      "category": "information",
      "summary": "Public, crowd-voted leaderboard comparing AI models on text, image and code through real-world head-to-head evaluation.",
      "description": "lmarena.ai now redirects to arena.ai.",
      "url": "https://arena.ai",
      "tags": [
        "leaderboard",
        "llm-evaluation",
        "human-preference"
      ],
      "pricing": "free",
      "status": "active",
      "related": [
        "artificial-analysis"
      ],
      "sources": [
        "https://arena.ai",
        "https://lmarena.ai"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/arena-ai/",
        "markdown": "https://indexagentica.com/entries/arena-ai.md",
        "json": "https://indexagentica.com/api/entries/arena-ai.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/arena-ai.json"
      }
    },
    {
      "id": "artificial-analysis",
      "name": "Artificial Analysis",
      "category": "information",
      "summary": "Independent benchmarks comparing AI models and API providers on quality, price, output speed and latency.",
      "url": "https://artificialanalysis.ai",
      "tags": [
        "benchmark",
        "model-comparison",
        "pricing",
        "latency"
      ],
      "status": "active",
      "related": [
        "arena-ai",
        "openrouter-rankings"
      ],
      "sources": [
        "https://artificialanalysis.ai"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/artificial-analysis/",
        "markdown": "https://indexagentica.com/entries/artificial-analysis.md",
        "json": "https://indexagentica.com/api/entries/artificial-analysis.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/artificial-analysis.json"
      }
    },
    {
      "id": "arxiv-cs-ai",
      "name": "arXiv cs.AI (Artificial Intelligence)",
      "category": "information",
      "summary": "arXiv's listing of the latest preprints in Artificial Intelligence, a primary source for new agent research.",
      "url": "https://arxiv.org/list/cs.AI/recent",
      "tags": [
        "research",
        "papers",
        "preprints"
      ],
      "pricing": "free",
      "status": "active",
      "related": [
        "hf-daily-papers",
        "arxiv-api"
      ],
      "sources": [
        "https://arxiv.org/list/cs.AI/recent"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "maintainer": "arXiv (Cornell)",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/arxiv-cs-ai/",
        "markdown": "https://indexagentica.com/entries/arxiv-cs-ai.md",
        "json": "https://indexagentica.com/api/entries/arxiv-cs-ai.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/arxiv-cs-ai.json"
      }
    },
    {
      "id": "bfcl",
      "name": "Berkeley Function Calling Leaderboard (BFCL)",
      "category": "information",
      "summary": "UC Berkeley leaderboard evaluating how accurately LLMs call functions and tools; part of the Gorilla project.",
      "url": "https://gorilla.cs.berkeley.edu/leaderboard.html",
      "repo": "https://github.com/ShishirPatil/gorilla",
      "tags": [
        "benchmark",
        "function-calling",
        "tool-use",
        "leaderboard"
      ],
      "license": "Apache-2.0",
      "pricing": "free",
      "status": "active",
      "related": [
        "tau-bench"
      ],
      "sources": [
        "https://gorilla.cs.berkeley.edu/leaderboard.html",
        "https://github.com/ShishirPatil/gorilla"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "maintainer": "UC Berkeley Gorilla team",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/bfcl/",
        "markdown": "https://indexagentica.com/entries/bfcl.md",
        "json": "https://indexagentica.com/api/entries/bfcl.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/bfcl.json"
      }
    },
    {
      "id": "building-effective-agents",
      "name": "Building Effective AI Agents (Anthropic)",
      "category": "information",
      "summary": "Anthropic engineering essay (Dec 19, 2024) on agent design patterns: workflows vs. agents, and when to use simple composable patterns.",
      "url": "https://www.anthropic.com/engineering/building-effective-agents",
      "tags": [
        "guide",
        "agent-design",
        "patterns"
      ],
      "pricing": "free",
      "related": [
        "claude-code"
      ],
      "sources": [
        "https://www.anthropic.com/engineering/building-effective-agents"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "maintainer": "Anthropic",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/building-effective-agents/",
        "markdown": "https://indexagentica.com/entries/building-effective-agents.md",
        "json": "https://indexagentica.com/api/entries/building-effective-agents.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/building-effective-agents.json"
      }
    },
    {
      "id": "common-crawl",
      "name": "Common Crawl",
      "category": "information",
      "summary": "Open repository of web crawl data that anyone can access and analyze.",
      "url": "https://commoncrawl.org",
      "tags": [
        "dataset",
        "web-crawl",
        "open-data"
      ],
      "pricing": "free",
      "status": "active",
      "sources": [
        "https://commoncrawl.org"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "maintainer": "Common Crawl Foundation",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/common-crawl/",
        "markdown": "https://indexagentica.com/entries/common-crawl.md",
        "json": "https://indexagentica.com/api/entries/common-crawl.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/common-crawl.json"
      }
    },
    {
      "id": "epoch-ai-benchmarks",
      "name": "Epoch AI Benchmarking Hub",
      "category": "information",
      "summary": "Epoch AI's hub of benchmark results for leading AI models, with trends over time by benchmark and by model.",
      "url": "https://epoch.ai/benchmarks",
      "tags": [
        "benchmark",
        "ai-trends",
        "research"
      ],
      "pricing": "free",
      "status": "active",
      "sources": [
        "https://epoch.ai/benchmarks"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "maintainer": "Epoch AI",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/epoch-ai-benchmarks/",
        "markdown": "https://indexagentica.com/entries/epoch-ai-benchmarks.md",
        "json": "https://indexagentica.com/api/entries/epoch-ai-benchmarks.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/epoch-ai-benchmarks.json"
      }
    },
    {
      "id": "gaia-benchmark",
      "name": "GAIA",
      "category": "information",
      "summary": "Benchmark for general AI assistants (\"Benchmarking General AI Agents\"), published as a Hugging Face dataset under the gaia-benchmark org.",
      "url": "https://huggingface.co/gaia-benchmark",
      "docs": "https://huggingface.co/datasets/gaia-benchmark/GAIA",
      "tags": [
        "benchmark",
        "agents",
        "dataset",
        "evals"
      ],
      "pricing": "free",
      "status": "active",
      "sources": [
        "https://huggingface.co/gaia-benchmark",
        "https://huggingface.co/datasets/gaia-benchmark/GAIA"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/gaia-benchmark/",
        "markdown": "https://indexagentica.com/entries/gaia-benchmark.md",
        "json": "https://indexagentica.com/api/entries/gaia-benchmark.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/gaia-benchmark.json"
      }
    },
    {
      "id": "hf-daily-papers",
      "name": "Hugging Face Daily Papers",
      "category": "information",
      "summary": "Daily curated feed of new AI research papers on Hugging Face.",
      "url": "https://huggingface.co/papers",
      "tags": [
        "research",
        "papers",
        "daily-feed"
      ],
      "pricing": "free",
      "status": "active",
      "sources": [
        "https://huggingface.co/papers"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "maintainer": "Hugging Face",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/hf-daily-papers/",
        "markdown": "https://indexagentica.com/entries/hf-daily-papers.md",
        "json": "https://indexagentica.com/api/entries/hf-daily-papers.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/hf-daily-papers.json"
      }
    },
    {
      "id": "hf-datasets",
      "name": "Hugging Face Datasets Hub",
      "category": "information",
      "summary": "Hugging Face hub of ready-to-use datasets for AI models, plus the open-source `datasets` library for loading and manipulating them.",
      "url": "https://huggingface.co/datasets",
      "repo": "https://github.com/huggingface/datasets",
      "docs": "https://huggingface.co/docs/datasets",
      "tags": [
        "dataset",
        "open-data",
        "hugging-face"
      ],
      "status": "active",
      "related": [
        "huggingface-mcp"
      ],
      "sources": [
        "https://huggingface.co/datasets",
        "https://github.com/huggingface/datasets"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "maintainer": "Hugging Face",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/hf-datasets/",
        "markdown": "https://indexagentica.com/entries/hf-datasets.md",
        "json": "https://indexagentica.com/api/entries/hf-datasets.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/hf-datasets.json"
      }
    },
    {
      "id": "humanitys-last-exam",
      "name": "Humanity's Last Exam",
      "category": "information",
      "summary": "Multi-modal benchmark of 2,500 expert-written questions at the frontier of human knowledge, from the Center for AI Safety and Scale AI.",
      "url": "https://lastexam.ai",
      "repo": "https://github.com/centerforaisafety/hle",
      "tags": [
        "benchmark",
        "dataset",
        "frontier-models",
        "evals"
      ],
      "license": "MIT",
      "pricing": "free",
      "status": "active",
      "sources": [
        "https://lastexam.ai",
        "https://github.com/centerforaisafety/hle"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/humanitys-last-exam/",
        "markdown": "https://indexagentica.com/entries/humanitys-last-exam.md",
        "json": "https://indexagentica.com/api/entries/humanitys-last-exam.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/humanitys-last-exam.json"
      }
    },
    {
      "id": "metr-time-horizons",
      "name": "METR Task-Completion Time Horizons",
      "category": "information",
      "summary": "METR's up-to-date measurements of how long tasks frontier AI models can complete autonomously (time horizons).",
      "url": "https://metr.org/time-horizons",
      "tags": [
        "benchmark",
        "agents",
        "ai-trends",
        "research",
        "evals"
      ],
      "pricing": "free",
      "status": "active",
      "sources": [
        "https://metr.org/time-horizons",
        "https://metr.org"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "maintainer": "METR",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/metr-time-horizons/",
        "markdown": "https://indexagentica.com/entries/metr-time-horizons.md",
        "json": "https://indexagentica.com/api/entries/metr-time-horizons.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/metr-time-horizons.json"
      }
    },
    {
      "id": "mle-bench",
      "name": "MLE-bench",
      "category": "information",
      "summary": "OpenAI benchmark measuring how well AI agents perform machine learning engineering tasks.",
      "url": "https://github.com/openai/mle-bench",
      "repo": "https://github.com/openai/mle-bench",
      "tags": [
        "benchmark",
        "machine-learning",
        "agents",
        "evals"
      ],
      "pricing": "free",
      "status": "active",
      "sources": [
        "https://github.com/openai/mle-bench"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "maintainer": "OpenAI",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/mle-bench/",
        "markdown": "https://indexagentica.com/entries/mle-bench.md",
        "json": "https://indexagentica.com/api/entries/mle-bench.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/mle-bench.json"
      }
    },
    {
      "id": "models-dev",
      "name": "Models.dev",
      "category": "information",
      "summary": "Open-source database of AI model specifications, pricing and features, also served as JSON.",
      "url": "https://models.dev",
      "repo": "https://github.com/anomalyco/models.dev",
      "tags": [
        "model-database",
        "pricing",
        "specs",
        "open-data"
      ],
      "license": "MIT",
      "pricing": "free",
      "status": "active",
      "agent_access": {
        "auth": "none",
        "notes": "Full dataset as JSON at https://models.dev/api.json."
      },
      "related": [
        "openrouter",
        "opencode"
      ],
      "sources": [
        "https://models.dev",
        "https://models.dev/api.json",
        "https://github.com/anomalyco/models.dev"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/models-dev/",
        "markdown": "https://indexagentica.com/entries/models-dev.md",
        "json": "https://indexagentica.com/api/entries/models-dev.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/models-dev.json"
      }
    },
    {
      "id": "openrouter-rankings",
      "name": "OpenRouter LLM Rankings",
      "category": "information",
      "summary": "LLM leaderboard by real-world usage, ranked by tokens processed through the OpenRouter API.",
      "url": "https://openrouter.ai/rankings",
      "tags": [
        "leaderboard",
        "usage-data",
        "models"
      ],
      "pricing": "free",
      "status": "active",
      "related": [
        "openrouter",
        "models-dev"
      ],
      "sources": [
        "https://openrouter.ai/rankings"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "maintainer": "OpenRouter",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/openrouter-rankings/",
        "markdown": "https://indexagentica.com/entries/openrouter-rankings.md",
        "json": "https://indexagentica.com/api/entries/openrouter-rankings.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/openrouter-rankings.json"
      }
    },
    {
      "id": "osworld",
      "name": "OSWorld",
      "category": "information",
      "summary": "NeurIPS 2024 benchmark of multimodal agents on open-ended tasks in real computer environments.",
      "url": "https://github.com/xlang-ai/OSWorld",
      "repo": "https://github.com/xlang-ai/OSWorld",
      "tags": [
        "benchmark",
        "computer-use",
        "multimodal",
        "evals"
      ],
      "license": "Apache-2.0",
      "pricing": "free",
      "status": "active",
      "related": [
        "webarena"
      ],
      "sources": [
        "https://github.com/xlang-ai/OSWorld"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/osworld/",
        "markdown": "https://indexagentica.com/entries/osworld.md",
        "json": "https://indexagentica.com/api/entries/osworld.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/osworld.json"
      }
    },
    {
      "id": "swe-bench",
      "name": "SWE-bench",
      "category": "information",
      "summary": "Benchmark and leaderboards (Verified, Lite, Multimodal, Multilingual) testing whether LLM agents can resolve real-world GitHub issues.",
      "url": "https://www.swebench.com",
      "repo": "https://github.com/SWE-bench/SWE-bench",
      "tags": [
        "benchmark",
        "coding-agents",
        "leaderboard"
      ],
      "license": "MIT",
      "pricing": "free",
      "status": "active",
      "related": [
        "terminal-bench"
      ],
      "sources": [
        "https://www.swebench.com",
        "https://github.com/SWE-bench/SWE-bench"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/swe-bench/",
        "markdown": "https://indexagentica.com/entries/swe-bench.md",
        "json": "https://indexagentica.com/api/entries/swe-bench.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/swe-bench.json"
      }
    },
    {
      "id": "terminal-bench",
      "name": "Terminal-Bench",
      "category": "information",
      "summary": "Benchmark and leaderboard measuring how well AI agents complete complicated tasks in the terminal.",
      "url": "https://www.tbench.ai",
      "repo": "https://github.com/harbor-framework/terminal-bench-1",
      "tags": [
        "benchmark",
        "agents",
        "terminal",
        "leaderboard"
      ],
      "license": "Apache-2.0",
      "pricing": "free",
      "status": "active",
      "related": [
        "swe-bench"
      ],
      "sources": [
        "https://www.tbench.ai",
        "https://github.com/harbor-framework/terminal-bench-1"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/terminal-bench/",
        "markdown": "https://indexagentica.com/entries/terminal-bench.md",
        "json": "https://indexagentica.com/api/entries/terminal-bench.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/terminal-bench.json"
      }
    },
    {
      "id": "webarena",
      "name": "WebArena",
      "category": "information",
      "summary": "A realistic web environment for building autonomous agents, with benchmark tasks used to evaluate web agents.",
      "url": "https://webarena.dev",
      "repo": "https://github.com/web-arena-x/webarena",
      "tags": [
        "benchmark",
        "web-agents",
        "browser-automation",
        "evals"
      ],
      "license": "Apache-2.0",
      "pricing": "free",
      "status": "active",
      "related": [
        "osworld"
      ],
      "sources": [
        "https://webarena.dev",
        "https://github.com/web-arena-x/webarena"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/webarena/",
        "markdown": "https://indexagentica.com/entries/webarena.md",
        "json": "https://indexagentica.com/api/entries/webarena.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/webarena.json"
      }
    },
    {
      "id": "tau-bench",
      "name": "τ-bench (tau2-bench)",
      "category": "information",
      "summary": "Sierra's benchmark for tool-agent-user interaction in real-world domains.",
      "description": "Successor repository to the original sierra-research/tau-bench.",
      "url": "https://github.com/sierra-research/tau2-bench",
      "repo": "https://github.com/sierra-research/tau2-bench",
      "tags": [
        "benchmark",
        "tool-use",
        "conversational-agents"
      ],
      "license": "MIT",
      "pricing": "free",
      "status": "active",
      "related": [
        "bfcl"
      ],
      "sources": [
        "https://github.com/sierra-research/tau2-bench",
        "https://github.com/sierra-research/tau-bench"
      ],
      "added": "2026-10-02",
      "updated": "2026-10-02",
      "last_verified": "2026-10-02",
      "submitted_by": "agentica-curator",
      "maintainer": "Sierra",
      "longform": [],
      "links": {
        "html": "https://indexagentica.com/entries/tau-bench/",
        "markdown": "https://indexagentica.com/entries/tau-bench.md",
        "json": "https://indexagentica.com/api/entries/tau-bench.json",
        "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/tau-bench.json"
      }
    }
  ]
}