Catalog / search
Find agents, prompts, guides, architectures, and glossary entries. Narrow by type, or open advanced search for field, match, and sort.
26 results · All · “memory”
system prompt
Memory Poisoning Attack AuditorYour job is to audit LLM-agent memory systems for vulnerabilities that let untrusted inputs persistently poison the memory the agent trusts in later sessions.
system prompt
Agent Memory ArchitectYour job is to design memory systems that let long-running agents learn from experience, avoid repetitive mistakes, and retrieve the right context at the right time—without drowning in token bloat or stale recollections.
system prompt
Agent-Native Memory System ArchitectYour job is to design memory subsystems for long-running agents as first-class data-management systems — not as after-thought retrieval plugins.
system prompt
agentmemory Persistent Memory ArchitectYour job is to design a cross-session memory layer that lets a coding agent remember what matters, forget what does not, and retrieve the right context without bloating the prompt window.
system prompt
Local-First Memory EngineerYour job is to design and harden a verbatim, locally-stored, benchmark-driven memory system for long-running agents — one that does not depend on any remote API for the core recall path, never paraphrases what the user …
glossary
Long-Term MemoryLong-term memory is durable notes stored across sessions.
glossary
MemoryIn agents, memory is stored information that can be retrieved later.
glossary
Memory StoreA memory store is the durable system that saves and retrieves agent notes.
glossary
Short-Term MemoryShort-term memory is the working set for the current run: notes, tool results, and the active goal.
guide
Tool-Using Agents: Calling, Design, Memory, MiddlewareTool calling is how models take actions. Tool design, memory, and middleware decide whether those actions are safe to repeat.
system prompt
A2A Agent Protocol ArchitectYour job is to design agent-to-agent communication that is interoperable, asynchronous, and opaque: agents delegate work to each other without ever needing access to each other's internal state, memory, or tools.
guide
Agent ArchitectureArchitecture is how model, tools, memory, and control flow are arranged.
glossary
Agent Architecture — Glossary DefinitionAgent architecture is the arrangement of model, tools, memory, and control flow.
system prompt
Codebase Memory MCP ArchitectYour job is to make the agent treat the codebase as a queryable knowledge graph: index once, then answer structural questions via the 15 MCP tools with citations, impact analysis, and minimal token spend.
system prompt
ContextNest Verifiable Context Governance ArchitectYour job is to design a governance layer beneath retrieval — a system that decides which artifacts are approved, current, attributable, and integrity-verified before any RAG pipeline, agent memory, or MCP tool operates …
prompt
Deep Copy FunctionalityAct as a Programming Expert. You are highly skilled in software development, specializing in data structure manipulation and memory management. Your task is to instruc…
system prompt
Elastic Context OrchestratorYour job is to design adaptive context-management systems for long-horizon agents that dynamically reshape their working memory—preserving important evidence, summarizing resolved information, discarding unhelpful branc…
agent
Memory Agentarchitecture
Memory Agent ArchitectureDurable notes are stored and retrieved as data.
tool
Memory Store Tool ReferenceWrites and retrieves durable notes across turns or sessions.
system prompt
Proactive Memory Agent for Long-Horizon AgentsYour job is to fight behavioral state decay.
Page 1 of 2