Results for “ember”

Maintain SESSION-STATE.md, the durable within-session memory that survives context compaction. Use when a constraint, settled decision, existing-infrastructure (survey) finding, or open thread must persist across a long session so it is not re-derived or re-litigated. Triggers on /state, "remember this for the session", "record this constraint/decision", or after surveying what already exists. For cross-session/personal memory use .claude/memory/ on Claude or native memories on Codex; for repo-derivable facts, do not record at all.

The English summary is being prepared. Showing the original description.

Data structures and algorithms for AI agent episodic memory. Covers vector stores (HNSW, IVF, PQ), temporal indexing, knowledge graphs with triple stores, hierarchical summarization, forgetting curves, working/long-term/ procedural memory, and memory consolidation. Deep analysis of MemGPT/Letta, Zep/Graphiti, Mem0, and the Stanford generative agents memory architecture. Teaches the CS fundamentals behind how agents remember, retrieve, and forget. Activate on: "agent memory", "episodic memory", "vector search algorithm", "HNSW", "memory retrieval", "forgetting curve", "knowledge graph memory", "MemGPT", "Letta", "Zep", "Mem0", "memory consolidation", "temporal retrieval", "agent long-term memory", "memory layer". NOT for: conversation protocol design (use agent-conversation-protocols), agent infrastructure selection (use agentic-infrastructure-2026), building RAG pipelines (use ai-engineer).

The English summary is being prepared. Showing the original description.

Architecture and systems design for building always-on AI agents with episodic memory. Covers the memory hierarchy (core/recall/archival), persistence layers, agent server infrastructure, vector stores, and framework selection. Provides concrete deployment patterns for agents that maintain identity and learn across sessions. Activate on: "always-on agent", "persistent agent architecture", "episodic memory system", "agent memory design", "long-running agent", "stateful agent", "agent that remembers", "MemGPT architecture", "Letta deployment", "/always-on-agent-architecture". NOT for: choosing what data to feed the agent (use always-on-agent-inputs), brainstorming applications (use always-on-agent-applications), safety and privacy concerns (use always-on-agent-safety), general agentic patterns (use agentic-patterns).

The English summary is being prepared. Showing the original description.

Persistent vector memory for Claude Code via LanceDB. Use when: remembering across sessions, storing lessons, recalling past decisions, maintaining context continuity. Tools: memory_store, memory_recall, memory_update, memory_forget, memory_merge.

The English summary is being prepared. Showing the original description.

Build UpSet plots to visualize set intersections beyond 4 sets (where Venn fails) using ComplexUpset (modern, ggplot2-grammar) or the unmaintained UpSetR, with explicit cardinality vs degree sorting, attribute panels, and query highlighting. Use when comparing overlap across many gene sets, peak sets, variant lists, or any set membership matrix where Venn diagrams become illegible.

The English summary is being prepared. Showing the original description.

Designs Bayesian clinical trials including Phase I dose-finding (BOIN, CRM, EWOC, mTPI-2), meta-analytic-predictive (MAP) priors with robust mixtures for external data borrowing, EXNEX for basket trials, hierarchical models for safety AE (Berry-Berry), Bayesian platform trials (I-SPY 2, GBM AGILE, REMAP-CAP), and posterior probability stopping rules. Covers FDA Bayesian Devices Guidance (2010), FDA Bayesian Methodology in Drugs Draft (January 2026), BOIN Fit-for-Purpose qualification (December 2021), and Project Optimus dose-optimisation. Use when designing dose-finding studies, platform trials, or sensitivity analyses with informative priors.

The English summary is being prepared. Showing the original description.

Use ruLake as the agent's working memory. Auto-invoke /rulake-memory:memory-recall when the agent needs to look up something it might already know; auto-invoke /rulake-memory:memory-remember after the agent learns or decides something worth pinning. Closes the self-learning loop without requiring the agent author to wire it explicitly.

The English summary is being prepared. Showing the original description.

Save important context to persistent memory for future sessions. PROACTIVELY USE THIS when you detect: - Decisions: "let's go with", "decided to", "chose", "went with" - Learnings: "I learned", "turns out", "TIL", "realized", "discovered" - Errors resolved: "fixed", "the problem was", "solution was" - Client info: names, emails, phone numbers, addresses, invoice amounts - Preferences: "I prefer", "I like", "don't like", "always use" - References: API keys locations, file paths, URLs, credentials - Patterns: "pattern", "convention", "always do", "standard approach" - Important commands run worth remembering Do NOT ask permission - just capture silently when these patterns appear.

The English summary is being prepared. Showing the original description.

Passive, pattern-calibrated risk discovery for authorized security research over an open-source project, repository URL, dependency, release, or local checkout. Use when the security research agent needs to find highest-risk areas, map attack surface, identify likely bug-hunting targets, prioritize security review, inspect structural/logical/security-critical code, compare vulnerable versus patched versions, reason from broad high-severity vulnerability families, or remember areas of interest for later attack-chain research.

The English summary is being prepared. Showing the original description.

Inspect scoped Autodesk data, compare versioned BOMs, and prepare ownership-aware drafts or approved custom-property changes. Not for implicit PLM release, membership changes or CAD geometry editing.

The English summary is being prepared. Showing the original description.

Yuanbao (元宝) groups: @mention users, query info/members.

The English summary is being prepared. Showing the original description.

Synthesise a status, standup, or situation-report from current work state. Trigger when a team member needs a concise summary of where things stand, what is blocked, and what is next.

The English summary is being prepared. Showing the original description.

Lark/Feishu real-time event listening / subscribing / consuming: stream events as NDJSON via `lark-cli event consume <EventKey>` (covers IM message receive, reactions, chat member changes, etc.). Use for Lark bots, real-time message processing, long-running subscribers, streaming webhook/push handlers. Supports `--max-events` / `--timeout` bounded runs and a stderr ready-marker contract — designed for AI agents running as subprocesses.

The English summary is being prepared. Showing the original description.

Use when a user edits or criticizes generated copy and you need to extract durable writing-style rules instead of merely remembering surface words.

The English summary is being prepared. Showing the original description.

Explain a topic like I'm a 5 year old, as a single HTML artifact built from big pictures and very few words. Use this whenever the user asks for a dead-simple explanation of how something works, says "ELI5", "explain like I'm five", "簡単に説明して", "図で説明して", "初心者向けに", "素人にもわかるように", wants to explain a concept to a non-technical manager, customer, or family member, or asks for a visual explainer — even if they don't say "ELI5" explicitly.

The English summary is being prepared. Showing the original description.

Reviews a proposal, business case, deck or rollout plan in character as a Frontline Sceptic archetype, the experienced staff member who will live with the change, and returns a DRAFT review in the chat with a verdict, findings that cite the exact passage, adoption risks, what would change the verdict and five interrogation questions. Use when the user asks to "run a frontline review", "give me the shop-floor view of this rollout", "pressure-test adoption of this plan" or "what will the team actually say about this". Do not use for employee consultation, monitoring or works council preparation, use works-council-reviewer instead; for people strategy or restructuring, use chro-reviewer; for product evidence, use cpo-reviewer. Drafts for human review; never approves, authorises or signs off.

The English summary is being prepared. Showing the original description.

- Mine GitHub, GitLab and git history for identities, infrastructure and leaked credentials using commit author emails, GitHub code search, the commit… Use when investigating a developer or organisation on GitHub, finding leaked API keys, AWS keys or tokens in code, enumerating org members and their personal repos, or recovering secrets deleted from HEAD but still present in history or forks

The English summary is being prepared. Showing the original description.

Bootstrap a new or existing project with a small, file-based documentation system so Claude Code keeps context, lessons, and decisions across session restarts instead of starting cold every time. Sets up a handful of markdown files under .claude/ (standing rules, a free-form note to your next session, a phased roadmap, a prioritized backlog, and searchable history/changelog archives) sized and split so the files read every session stay small while the archives grow without ever costing context. Use this whenever someone is starting a new project and asks how to structure it for long-running AI-assisted work, wants Claude to "remember" things between sessions without relying on chat history, asks for a CLAUDE.md + backlog + changelog setup, mentions "session continuity", "persistent context", "project memory system", or is retrofitting an existing codebase that has no such system yet. Also use to explain or extend an already-bootstrapped bottle system (add a rule, start the archival script, add a new backlog section).

The English summary is being prepared. Showing the original description.

Yuanbao (元宝) groups: @mention users, query info/members.

The English summary is being prepared. Showing the original description.

September 16, 2026 New ask Hacker News story: Open-sourced jev architecture last year with model,pap

The English summary is being prepared. Showing the original description.

AI Agent News Today — September 10, 2026 — What changed: Zscaler released Agentic SOC, a security-op

The English summary is being prepared. Showing the original description.

Hosting-Muster, um eine lokal gebaute Anwendung (eigene Datenbank, eigener API-Key, In-Process-State) sicher hostbar zu machen, ohne Nutzerverwaltung zu bauen. Kernzug — der Host speichert nichts, der Browser des Besuchers speichert alles — sodass Pro-Besucher-Accounts, Zugriffsprüfungen und Löschfristen gegenstandslos werden, statt gelöst werden zu müssen. Nutzen, wenn eine lokal gebaute App für mehrere Besucher gehostet werden soll, bei "mach das ohne Login hostbar", "keine Nutzerkonten bauen", "Datenschutzerklärung für ein gehostetes Tool verkleinern", "wer ist verantwortlich, wenn wir nichts speichern" oder beim Wählen/Implementieren eines Server-Modus (`local`, `huckepack-gift`, `huckepack-only-host`, `pay-membership`). Liefert eine Data-Flow-Plan-Vorlage, eine Datenschutz-Vorlage und eine rechtliche Ersteinschätzung (DSGVO/TDDDG/UWG, deutsch) als Referenzen.

The English summary is being prepared. Showing the original description.

Recall past work across Claude Code and Codex sessions. Finds decisions, research, fixes, and conversations by intent; with only a project and no question, orients on that project's recent state.

The English summary is being prepared. Showing the original description.

Manage the NV oOS Pro Toolkit Project Management system — projects, tasks, events, sprints, task plans, task templates, and PM workflow rules. Covers complete project lifecycle (planning → active → completed), task tracking with priorities and effort estimation, sprint planning, event scheduling with attendees, and template-driven task plan generation. Use when managing projects, creating or tracking tasks, planning sprints, scheduling events, generating task plans from templates, assigning work to team members, or troubleshooting project management data.

The English summary is being prepared. Showing the original description.