{"slug": "show-hn-documemory-persistent-memory-and-context-for-ai-coding-tools", "title": "Show HN: DocuMemory – Persistent memory and context for AI coding tools", "summary": "DocuMemory launched on Show HN as a persistent-memory tool that distills raw AI chat sessions into reusable context blocks for AI coding clients including Claude Code, ChatGPT and Cursor, connecting via a Model Context Protocol server at documemory.dev/api/mcp. The tool stores memory in the user's own PostgreSQL with pgvector HNSW indexing and combines semantic and full-text search through reciprocal rank fusion, with a local-first, self-hosted option. Pricing starts with 15 free distillations, then US $12/month or US $120 billed annually (US $10/month), and US $15 per seat per month for teams with a 2-seat minimum and no free trial.", "body_md": "BUILT FOR YOUR NEXT SESSION\n\n# The Living Memory Engine for AI-First Engineers\n\nPassively distil raw AI chat sessions into permanent architecture decisions and reusable, prompt-injectable context blocks.\n\n01 / THE MEMORY PIPELINE\n\n## From conversation to compounding knowledge.\n\nKeep the insight. Lose the noise. Give every new session a head start.\n\nAsk your AI client to save the session. Capture the reasoning in the same place you do the work.\n\n`save_chat_as_doc({ transcript, project_id })`\n02 / SIGNAL OVER NOISE\n\n## A long conversation.\n\nA lasting memory.\n\nYour next AI session doesn't need every debugging attempt. It needs what worked, why it worked, and the constraints worth remembering.\n\n```\n---\ndoc_type: MEMORY\nproject: Platform\ntags: [postgres, pgvector, search]\n---\n\n# Search architecture\n\n## Key facts\n- PostgreSQL + pgvector with HNSW indexing.\n- Semantic and full-text arms run independently.\n- Reciprocal rank fusion combines ranked results.\n- Every query is scoped to the authenticated user.\n```\n\nai_context_snippet\n\nUse PostgreSQL + pgvector with HNSW indexing. Fuse semantic and full-text search with RRF. Keep results scoped to the authenticated user.\n\n03 / ENGINEERED FOR CONTINUITY\n\n## A second brain for your engineering stack.\n\n### Passive Chat-to-Doc Distillation\n\nStay in Claude Code, ChatGPT, or Cursor. One capture turns your conversation into documentation that lasts.\n\n### Model Context Protocol (MCP) Native\n\nCapture, search, and recall from your AI client. Your engineering knowledge becomes a tool your model can use.\n\n### Subtractive Noise Reduction (Zero-Fluff Code)\n\nKeep the final implementation and the reasoning behind it. Leave the dead ends behind.\n\n### Hybrid Vector & Full-Text Search (RRF)\n\nSemantic understanding meets exact identifiers. Reciprocal rank fusion brings the right context to the surface.\n\n### Local-First & Self-Hosted Privacy\n\nYour infrastructure, your Postgres, your AI keys. Self-host with a local model to keep your knowledge on your machine.\n\n### Prompt Real-Estate Optimization\n\nCompact context snippets give your next session the facts it needs without the transcript it doesn't.\n\nPRICING\n\n## Try it first. Subscribe when you're ready.\n\n15 free distillations. No credit card required.\n\n### Free trial\n\nUS $0\n\n15 uses, once per account\n\nExplore your workspace and connect your AI client. Distillation and Enhance with AI share the free allowance.\n\n[Try for free](https://www.documemory.dev/signup)\n\n### monthly\n\nUS $12/month\n\nUS $12 billed monthly\n\nContinue after your free uses with documents, AI integrations, and private uploads. Cancel renewal from Settings.\n\n[Signup now](https://www.documemory.dev/signup)\n\n### annual\n\nSave US $24/year\nUS $10/month\n\nUS $120 billed annually\n\nContinue after your free uses with documents, AI integrations, and private uploads. Cancel renewal from Settings.\n\n[Signup now](https://www.documemory.dev/signup)\n\n### Team\n\nUS $15/seat\n\nper month, or US $150 per seat, billed annually · 2-seat minimum\n\nOne shared documentation repository for your team. Every member gets a seat; share projects with everyone or restrict them to specific people. No free trial: billing starts when you set up the organization.\n\n[Start a team](https://www.documemory.dev/signup?next=%2Forganizations%2Fnew)\n\n04 / CONNECT YOUR CLIENT\n\n## One connection.\n\nEvery decision, remembered.\n\nCreate an access token in Settings, add your MCP connection, and ask your client to save a conversation.\n\n```\n{\n  \"mcpServers\": {\n    \"documemory\": {\n      \"url\": \"https://documemory.dev/api/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_ACCESS_TOKEN\"\n      }\n    }\n  }\n}\n```\n\n", "url": "https://wpnews.pro/news/show-hn-documemory-persistent-memory-and-context-for-ai-coding-tools", "canonical_source": "https://www.documemory.dev/", "published_at": "2026-10-18 14:22:54+00:00", "updated_at": "2026-10-18 14:47:47.376862+00:00", "lang": "en", "topics": ["ai-tools", "ai-agents", "agent-protocols", "developer-tools", "ai-products"], "entities": ["DocuMemory", "Claude Code", "ChatGPT", "Cursor", "PostgreSQL", "pgvector", "Model Context Protocol"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-documemory-persistent-memory-and-context-for-ai-coding-tools", "markdown": "https://wpnews.pro/news/show-hn-documemory-persistent-memory-and-context-for-ai-coding-tools.md", "text": "https://wpnews.pro/news/show-hn-documemory-persistent-memory-and-context-for-ai-coding-tools.txt", "jsonld": "https://wpnews.pro/news/show-hn-documemory-persistent-memory-and-context-for-ai-coding-tools.jsonld"}}