{"id":48670571,"url":"https://github.com/sportmind/sportmind","last_synced_at":"2026-05-13T16:01:10.932Z","repository":{"id":349735518,"uuid":"1202821440","full_name":"SportMind/SportMind","owner":"SportMind","description":"The Sports Intelligence Library For AI Agents","archived":false,"fork":false,"pushed_at":"2026-04-24T22:41:44.000Z","size":3026,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-25T00:19:22.790Z","etag":null,"topics":["ai-agents","chiliz-chain","fan-tokens","llm-context","mcp","open-source","sportfi","sports-intelligence"],"latest_commit_sha":null,"homepage":"https://sportmind.dev","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/SportMind.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-06T12:42:49.000Z","updated_at":"2026-04-24T22:39:19.000Z","dependencies_parsed_at":"2026-04-26T22:00:47.802Z","dependency_job_id":null,"html_url":"https://github.com/SportMind/SportMind","commit_stats":null,"previous_names":["sportmind/sportmind"],"tags_count":63,"template":false,"template_full_name":null,"purl":"pkg:github/SportMind/SportMind","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SportMind%2FSportMind","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SportMind%2FSportMind/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SportMind%2FSportMind/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SportMind%2FSportMind/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SportMind","download_url":"https://codeload.github.com/SportMind/SportMind/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SportMind%2FSportMind/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32314116,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-26T21:09:39.134Z","status":"ssl_error","status_checked_at":"2026-04-26T21:09:21.240Z","response_time":129,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agents","chiliz-chain","fan-tokens","llm-context","mcp","open-source","sportfi","sports-intelligence"],"created_at":"2026-04-10T12:07:29.904Z","updated_at":"2026-04-26T22:00:51.756Z","avatar_url":"https://github.com/SportMind.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SportMind\n\n**The open sports intelligence library for AI agents and developers.**\n\nSportMind teaches AI agents how to reason about sports — not just react to data.\nLoad a skill, and your agent immediately understands the sport, the athlete,\nthe commercial landscape, and the external forces acting on it.\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Version](https://img.shields.io/badge/version-3.86.0-green)]()\n[![Sports](https://img.shields.io/badge/sports-42-blue)]()\n[![Calibration](https://img.shields.io/badge/calibration-126%20records%20%7C%2096%25%20accuracy-green)]()\n[![Fan Tokens™](https://img.shields.io/badge/fan%20tokens-90%20verified-orange)]()\n[![Validator](https://img.shields.io/badge/validator-passing-green)]()\n\n---\n\n## Find your starting point in 60 seconds\n\n→ **[WHO-USES-THIS.md](WHO-USES-THIS.md)** — Developer, agent builder, analyst, researcher,\nor contributor? This maps you to exactly the files you need.\n\n---\n\n## What problem does this solve?\n\nAI agents that analyse fan tokens, run prediction markets, or power sports GameFi\nneed more than raw data. They need context:\n\n- That a weigh-in miss in MMA is categorically different from a team losing a regular season game\n- That a cricket match on a Mumbai evening will be affected by dew in the second innings\n- That a DAXA Investment Warning on a Korean exchange is a staged lifecycle event with\n  a predictable intervention window — not a binary delisting signal\n- That a new Binance listing aligned with a club's actual fanbase geography extends CDI\n  durability; a misaligned listing does not\n- That Galatasaray equity on Borsa Istanbul (GSRAY.IS) leads the GAL fan token by 24–72\n  hours on commercial news — both instruments are pricing the same underlying entity\n- That a liquidity pool with $80k TVL will absorb your signal's value in slippage before you execute\n\nThis contextual reasoning is currently rebuilt from scratch by every developer\nin the space. **SportMind is the shared layer.**\n\n---\n\n## Five-minute quickstart\n\n**Option A — Paste into any LLM (zero setup)**\n\n```\n1. Open Claude, GPT-4, Gemini, Groq, Mistral, or any LLM\n2. Paste: contents of core/sportmind-purpose-and-context.md\n3. Paste: contents of sports/football/sport-domain-football.md\n4. Ask: \"PSG vs Arsenal UCL tonight. PSG full squad. Arsenal striker injured.\n         Using SportMind, generate a pre-match signal.\"\n```\n\nWorking in under 3 minutes.\n\n**Option B — Skills API**\n\n```bash\npython scripts/sportmind_api.py   # start local API\n\ncurl \"http://localhost:8080/bundle/ftier1-football\"   # named bundle\ncurl \"http://localhost:8080/stack?sport=football\u0026use_case=fan_token_tier1\"\n```\n\n**Option C — Clone and run**\n\n```bash\ngit clone https://github.com/SportMind/SportMind\npip install aiohttp --break-system-packages\npython examples/starter-pack/01-simple-signal.py\n```\n\n---\n\n## Five layers — one system\n\n| Layer | Directory | What it teaches |\n|---|---|---|\n| **1 — Sport domain** | `sports/` (42 sports) | How each sport works; event playbooks; risk variables |\n| **2 — Athlete intelligence** | `athlete/` (29 sports) | Who is playing; form; composite modifier (0.55–1.25×) |\n| **3 — Fan token commercial** | `fan-token/` (64 skills) | Lifecycle; DeFi; governance; exchange intelligence; RWA |\n| **4 — Market intelligence** | `market/` (43 docs) | Commercial tier; fanbase; sports equity signals; competition calendar |\n| **5 — Macro intelligence** | `macro/` (9 docs) | Crypto cycles; regulatory (MiCA, SEC/CFTC); geopolitical |\n\n**Load order:** macro → market → sport domain → athlete → fan token → output schema\n\nUse a named bundle: `ftier1-football` · `ftier1-cricket` · `prematch-mma` · `governance-brief`\n→ `platform/skill-bundles.md` for all 14 bundles with token estimates.\n\n---\n\n## What the library contains\n\n```\n579 files · 364 markdown skill files\n\nSport domain:      42 sports · event playbooks · risk variables · agent reasoning prompts\nAthlete:           29 sports · form models · availability · composite modifier (0.55–1.25×)\nFan token:         64 skills · 90 verified tokens (63 active Chiliz + 18 expired + 9 multi-chain)\n                   Lifecycle phases 1–6 · DeFi liquidity · exchange intelligence (EDLI/IPS/RRS)\n                   New listing intelligence · Fan Token Play PATH_2 · governance · KOL influence\n                   Sports equity signals (GSRAY.IS, MANU, JUVE.MI, FWONK, TKO) · CHZ macro layer\nMarket:            43 documents · club operations · broadcaster intelligence · World Cup 2026\nMacro:             9 documents · MiCA · SEC/CFTC joint guidance (March 2026) · US market opening\n\nCore frameworks:   57 files · reasoning patterns · autonomous agent framework · modifier system\n                   breaking news · squad intelligence · historical framework · contextual signals\nPlatform:          28 files · MCP server (45 tools, 8 servers) · data connectors · API providers\n                   Chiliz Agent Kit · social intelligence · web agent connectors · fraud signals\nCommunity:         177 files · 126 calibration records (96% accuracy, 21 sports) · benchmarks\nDeveloper tools:   11 application blueprints · 13 agentic workflow patterns · 22 agent prompts\n                   3 copy-paste templates · 69 compressed summaries · Skills API · starter pack\n```\n\n---\n\n## Agent output format\n\n```json\n{\n  \"sportmind_score\":   {\"sms\": 79, \"sms_tier\": \"GOOD\"},\n  \"signal\":            {\"adjusted_score\": 72.4, \"direction\": \"HOME\",\n                        \"recommended_action\": \"ENTER\"},\n  \"modifiers_applied\": {\"athlete_modifier\": 1.10, \"macro_modifier\": 1.00,\n                        \"composite_modifier\": 1.08},\n  \"flags\":             {\"lineup_unconfirmed\": false,\n                        \"macro_override_active\": false}\n}\n```\n\nFull schema: `core/confidence-output-schema.md`\n\n---\n\n## MCP server\n\nSportMind is available as an MCP tool server — connect any AI agent to the\nfull library without loading files manually.\n\n```bash\ngit clone https://github.com/SportMind/SportMind\npip install mcp aiohttp\n\n# stdio (Claude Desktop / Claude Code)\npython scripts/sportmind_mcp.py\n\n# HTTP/SSE (hosted agents)\npython scripts/sportmind_mcp.py --http --port 3001\n```\n\n45 tools across 8 servers: `sportmind_signal` · `sportmind_macro` · `sportmind_stack` ·\n`sportmind_fan_token_lookup` · `sportmind_sentiment_snapshot` · `sportmind_pre_match` ·\n`sportmind_disciplinary` · `sportmind_governance` · `sportmind_verifiable_source` · and more.\n\n**→ Full deployment guide: [MCP-SERVER.md](MCP-SERVER.md)**\n\n---\n\n## Integration\n\n**Data connections:** `platform/data-connector-templates.md` — lineup data, fan token TVL,\nmacro state.\n\n**Execution layer:** `platform/chiliz-agent-kit-integration.md` — SportMind intelligence\n→ Chiliz Agent Kit → on-chain execution.\n\n**Web agents:** `platform/web-agent-connectors.md` — lineup confirmation (T-2h), PATH_2\nsupply verification, exchange monitoring, regulatory/macro monitoring.\n\n**MCP deployment:** `platform/sportmind-mcp-deployment.md` — live endpoint in 30 minutes.\n\n**Compatible with:** Claude · GPT-4 · Gemini · LangChain · CrewAI · AutoGen ·\nany LLM (skills are structured markdown, not API wrappers).\n\n---\n\n## The calibration record\n\n126 records. 96% accuracy. Zero wrong-direction records outside European football draws.\n\nAll records are in `community/calibration-data/` — publicly verifiable, pre-submitted\nbefore real matches. Includes all 5 wrong predictions with root-cause analysis.\nNot cherry-picked.\n\nEight modifiers with zero wrong-direction records across their entire evidence base:\nqualifying_delta (F1) · india_pakistan ×2.00 · morning_skate (NHL) · dew_factor (cricket) ·\ntaper_modifier (swimming) · raider_primacy (kabaddi) · goalkeeper_save_rate (handball) ·\nsuperspeedway_specialist (NASCAR)\n\n---\n\n## Contributing\n\n**The fastest contribution: one calibration record.** No coding required.\nSee **[FIRST-RECORD-CHALLENGE.md](FIRST-RECORD-CHALLENGE.md)**.\n\nWhat the community needs most:\n- Football calibration records (athlete_modifier: 25/50 threshold)\n- Cricket dew_factor records (evening T20 matches)\n- Records from any underrepresented sport (rowing, netball, kabaddi)\n\nFull process: `community/calibration-data/CONTRIBUTING.md`\nRecognition: `community/CONTRIBUTORS.md`\n\n---\n\n## License\n\nMIT — free to use, modify, and redistribute for any purpose.\n\n---\n\n*WHO-USES-THIS.md → FIRST-RECORD-CHALLENGE.md → examples/starter-pack/*\n\n*SportMind is an independent open-source project. Not affiliated with Chiliz,\nSocios, or any sports data provider, though designed to complement them.*\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsportmind%2Fsportmind","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsportmind%2Fsportmind","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsportmind%2Fsportmind/lists"}