{
 "schema_version": 1,
 "generated": "2026-10-23",
 "id": "aru-labs-lossless-memory--keep-assistant-oriented-after-context-compaction",
 "repo": "aru-labs/lossless-memory",
 "repo_url": "https://github.com/aru-labs/lossless-memory",
 "repo_slug": "aru-labs-lossless-memory",
 "title": "Keep a long-running assistant on topic after context compaction",
 "page_title": "How to keep a long-running assistant on topic after context compaction with Lossless Memory",
 "summary": "Maintain a short timestamped topic index that is injected into the model's context every turn.",
 "who": "A person running a long-lived AI assistant whose context window gets compacted, so it loses track of the current thread.",
 "problem": "After compaction or a new session, the assistant has no clear record of which subject the conversation is on.",
 "outcome": "A small LLL topic index the model reads each turn, with priority and completion marks set by the human.",
 "steps": [
  "`git clone https://github.com/aru-labs/lossless-memory`",
  "`cd lossless-memory`",
  "`pip install -e .`",
  "Read docs/lll.md to learn the human and AI division of labor for topic markers.",
  "Write short timestamped topic marker lines whenever the conversation moves to a new subject.",
  "Inject the rendered LLL index into the model context at the start of each turn."
 ],
 "agent_prompt": "Using the repo aru-labs/lossless-memory, read docs/lll.md and set up an LLL topic index for <assistant name>. Expected output: a short list of timestamped topic markers that can be injected each turn. Verify that the human-set priority and completion marks are not edited by the model.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "1 hour",
 "basis": "readme",
 "caveat": "The README describes LLL as a design and gives no ready-made injection command, so you must wire it into your own assistant.",
 "category": "Personal productivity",
 "tags": [
  "Personal productivity"
 ],
 "lang": "python",
 "requirements": [
  "Python with pip, and git to clone the repository",
  "A machine you own; the README describes no server or cloud component",
  "Conversation logs as per-day JSONL files with ts, role, and text fields, or Claude Code transcript files",
  "Optional: a local sentence-transformers embedding model if you want semantic search as a fallback"
 ],
 "risk": "sensitive",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.7,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/aru-labs-lossless-memory/keep-assistant-oriented-after-context-compaction/",
 "md": "https://dedupedai.com/use-cases/aru-labs-lossless-memory/keep-assistant-oriented-after-context-compaction/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/aru-labs-lossless-memory--keep-assistant-oriented-after-context-compaction.json",
 "api_version": "v1"
}