{
  "markdown": "# Echomindr\n\n**3,500+ real founder moments from 60+ podcasts — searchable by AI agents.**\n\nEach moment: a named founder, a verbatim quote, a decision taken, an outcome observed, a lesson extracted — with a timestamped link to the source. Not summaries. Not paraphrases. What actually happened.\n\n## Why\n\nAI agents give generic startup advice. Echomindr gives them access to what founders actually did.\n\nAsk: *\"How did founders handle their first pricing?\"*\nGet: Kevin Hale's 10-5-20 rule, Josh Pigford charging $249/month from day one, Madhavan Ramanujam's options trick — with quotes, outcomes, and source links.\n\nAsk: *\"What did founders do when they nearly ran out of money?\"*\nGet: Airbnb selling cereal boxes, Notion's near-collapse during COVID, Calm's years of slow growth before the breakout — directly from the founders who lived it.\n\n## Quick start\n\n### API (REST)\n\n```bash\n# Search for founder experiences\ncurl \"https://echomindr.com/search?q=pricing&limit=5\"\n\n# Describe a situation, get matching experiences (vector search)\ncurl -X POST \"https://echomindr.com/situation\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"situation\": \"B2B SaaS founder with free pilots that won'\\''t convert to paid\"}'\n\n# Get moment details\ncurl \"https://echomindr.com/moments/{id}\"\n\n# Find similar moments\ncurl \"https://echomindr.com/similar/{id}?limit=5\"\n```\n\nAPI docs: [echomindr.com/docs](https://echomindr.com/docs)\n\n### MCP (for AI agents)\n\nConnect via remote MCP: `https://echomindr.com/mcp/`\n\nOr add to Claude Desktop (`claude_desktop_config.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"echomindr\": {\n      \"command\": \"python\",\n      \"args\": [\"echomindr_mcp.py\"],\n      \"env\": {\n        \"ECHOMINDR_API_URL\": \"https://echomindr.com\"\n      }\n    }\n  }\n}\n```\n\n3 MCP tools:\n- `search_experience` — semantic search for founder stories by situation\n- `get_experience_detail` — full details of a moment (quote, decision, outcome, lesson)\n- `find_similar_experiences` — related founder stories by shared themes\n\n### llms.txt\n\n```\nhttps://echomindr.com/llms.txt\n```\n\n## Data\n\n- **3,500+ moments** from 340+ podcast episodes across 60+ shows\n- **52 canonical situations** across 10 thematic families (PMF, growth, pricing, fundraising, team, operations, resilience, strategy, founder psychology, hostile environments)\n- **5 moment types:** decision, problem, lesson, signal, advice\n- **5 stages:** idea, mvp, traction, scale, mature\n- Sources: How I Built This, Lenny's Podcast, 20 Minute VC, Acquired, Y Combinator, My First Million, GDIY (Génération Do It Yourself), Disrupting Japan, Silicon Carne, Startup Ministerio, Kevin Kamis, Wall Street Paper, Valy Sy (China), Matt & Ari (Canada), Oscar Lindhardt (Denmark), Aidan Walsh (USA)\n\nEach moment: summary · verbatim quote · decision · outcome · lesson · stage · tags · timestamp link\n\n## Self-hosting\n\nTo run your own instance with the sample data:\n\n```bash\ngit clone https://github.com/echomindr/echomindr.git\ncd echomindr\npip install -r requirements.txt\n\n# Build a sample database\npython echomindr_build_db.py --sample\n\n# Start the API\npython echomindr_api.py\n# → http://localhost:8000/docs\n```\n\nTo build the full database, you need your own podcast transcriptions and Claude API key. See `echomindr_extract_v2.py` for the extraction pipeline.\n\n## Architecture\n\n```\nPodcast audio → Deepgram (transcription) → Claude (extraction) → SQLite → FastAPI → MCP\n```\n\nThe extraction pipeline turns long-form podcast interviews into structured, searchable moments. Each episode yields 8–15 moments on average. Semantic search uses BAAI/BGE-M3 embeddings (1024-dim) via sqlite-vec.\n\n## Endpoints\n\n| Endpoint | Method | Description |\n|---|---|---|\n| `/search` | GET | Full-text search with stage/type filters |\n| `/situation` | POST | Describe a situation, get matching experiences (vector search) |\n| `/moments/{id}` | GET | Full moment detail |\n| `/similar/{id}` | GET | Similar moments by shared tags |\n| `/taxonomy` | GET | 52 canonical situations across 10 families |\n| `/stats` | GET | Database statistics |\n| `/llms.txt` | GET | LLM-optimized API description |\n| `/docs` | GET | Swagger documentation |\n\n## License\n\nMIT — the code is open source. The hosted database at echomindr.com is a managed service.\n\n---\n\nBuilt by [Thierry](https://www.linkedin.com/in/thierryfaucher/) — author of \"The System That Learns Wins\" and \"Designing for Permanent Hostility\".\n",
  "bytes": 4398,
  "sha": "68bf1e38f23aa6cdac1e0f7539f54af83a8c28ce73560c54321d5b2a0391e587",
  "repo_slug": "echomindr/echomindr",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_echomindr_echomindr_7b63dc45/readme"
}