[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-83870":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":8,"htmlUrl":8,"language":9,"languages":8,"totalLinesOfCode":8,"stars":10,"forks":11,"watchers":12,"openIssues":13,"contributorsCount":11,"subscribersCount":11,"size":11,"stars1d":14,"stars7d":15,"stars30d":15,"stars90d":11,"forks30d":11,"starsTrendScore":16,"compositeScore":17,"rankGlobal":8,"rankLanguage":8,"license":8,"archived":18,"fork":18,"defaultBranch":19,"hasWiki":20,"hasPages":18,"topics":21,"createdAt":8,"pushedAt":8,"updatedAt":22,"readmeContent":23,"aiSummary":8,"trendingCount":11,"starSnapshotCount":11,"syncStatus":24,"lastSyncTime":25,"discoverSource":26},83870,"parcle-memory","Parcle-AI\u002Fparcle-memory","Parcle-AI",null,"Python",391,0,212,1,12,172,128,84,false,"main",true,[],"2026-06-12 04:01:42","\u003Cdiv align=\"center\">\n\n# Parcle\n\n**Long-term memory for AI agents**\n\nIngest conversations and files, then ask questions in natural language and get\ncited answers back. Give every user a private, persistent agent memory.\n\n\u003C\u002Fdiv>\n\n---\n\n## Why Parcle?\n\nLLMs forget everything between calls. Parcle gives every user a private memory you\ncan write to and search:\n\n- 🧠 **Per-user memory** — scope everything to a `user_id`.\n- 💬 **Ingest anything** — chat transcripts and files (PDF, Markdown, text, …) go in the same place.\n- 🔎 **Ask, don't query** — search returns a synthesized **answer** with **citations**, not just raw chunks.\n\n## Installation\n\n```bash\npip install parcle\n```\n\n## Quickstart\n\n```python\nfrom parcle import Parcle\n\n# Reads PARCLE_API_KEY from the environment if api_key is omitted.\nclient = Parcle(api_key=\"pk_live_...\")\n\n# 1. Write a conversation into a user's memory.\nclient.ingest_dialog(\n    user_id=\"ada\",\n    messages=[\n        {\"role\": \"user\", \"content\": \"I'm allergic to peanuts.\"},\n        {\"role\": \"assistant\", \"content\": \"Got it — I'll avoid peanuts in suggestions.\"},\n    ],\n)\n\n# 2. ...or ingest a file (PDF, Markdown, text, …).\nclient.ingest_file(user_id=\"ada\", file=\"diet-notes.pdf\")\n\n# 3. Ask a question. You get an answer with confidence and citations.\nresult = client.search(user_id=\"ada\", query=\"What food should I avoid?\")\n\nprint(result.answer)      # \"You're allergic to peanuts, so avoid them.\"\nprint(result.confidence)  # 0.92\nprint(result.citations)   # [Citation(type=\"dialog\", id=\"...\")]\n```",2,"2026-06-11 04:11:41","CREATED_QUERY"]