agent-memory
/agent-memory
Design memory for an AI agent so it recalls what matters and forgets the rest, without drowning in its own history. Use when adding persistence, context recall, or long-running state to an agent.
- Author
- Amey-Thakur ↗
- Repository
- AI-SKILLS ↗
- Licence
- MIT
- Last repository change
- 05.09.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 05.09.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Design memory for an AI agent so it recalls what matters and forgets the rest, without drowning in its own history. Use when adding persistence, context recall, or long-running state to an agent.
Original author description
Design memory for an AI agent so it recalls what matters and forgets the rest, without drowning in its own history. Use when adding persistence, context recall, or long-running state to an agent.
How it works
- Method
- Failure modes
- Boundaries
SKILL.md preview
---
name: agent-memory
description: Design memory for an AI agent so it recalls what matters and forgets the rest, without drowning in its own history. Use when adding persistence, context recall, or long-running state to an agent.
---
# Agent memory
An agent with no memory repeats itself; an agent that remembers everything
buries the signal and pays for it every turn. Memory design is the discipline
of keeping the right things, in the right form, retrievable at the right
moment.
## Method
1. **Separate the kinds of memory, because they have different lifetimes:**
- Working memory: the current task's context, held for the task and
discarded after. Keep it small and relevant; it is the most expensive
tokens you spend.
- Episodic memory: what happened (past conversations, actions, outcomes),
stored and retrieved by relevance when a similar situation returns.
- Semantic memory: durable facts the agent should always know (the user's
name, preferences, standing constraints), kept small and always
available.
Conflating these is the root of most memory bloat.
2. **Write less than you are tempted to.** Not every turn deserves to be
remembered. Store decisions, facts, outcomes, and preferences; discard the
turn-by-turn chatter. A memory that records everything is a transcript,
and a transcript is not memory.
3. **Retrieve by relevance, not recency alone.** When a task starts, pull the
episodic and semantic memories that match it (by embedding similarity,
keyword, or entity), not simply the last N. The useful memory is often
from three sessions ago, not the last three turns.
4. **Summarize to survive growth.** When history exceeds the budget, compress
older stretches into summaries that keep the load-bearing facts and drop
the detail. Summarize hierarchically (turns into a session summary,
sessions into a profile) so recall stays cheap as history grows without
bound.
5. **Make memory correctable and inspectable.** The user or operator can see
what the agent remembers and remove or edit it. A wrong fact remembered
forever is worse than a fact forgotten, and memory is where quiet errors
compound.
6. **Never store secrets or sensitive personal data in memory** unless it is
required, scoped, and the user consented. Memory persists, which means a
leak persists.
## Failure modes
- Context bloat: every turn appended verbatim until the window overflows and
cost climbs. Fix with selective writes and summarization.
- Stale facts: a preference changed but the old one is still recalled and
acted on. Timestamp memories and prefer the newest when they conflict.
- Irrelevant recall: recency-only retrieval floods the task with unrelated
history. Retrieve by relevance.
- Silent drift: summaries lose a fact that later mattered. Keep the source
retrievable, and summarize toward facts, not vibes.
## Boundaries
Memory is a system concern; use the platform's or framework's memory store
where one exists rather than inventing a parallel one. And memory is not a
substitute for the user telling the agent what they want now: recall informs
the current instruction, it never overrides it.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · Amey-Thakur/AI-SKILLS | 90 | MIT |
| TerminalSkills/skills | 100 | Apache-2.0 |
| komluk/scaffolding | 100 | MIT |
| nirholas/three.ws | 100 | Apache-2.0 |
| nimadorostkar/Claude-Skills-collection | 100 | MIT |
| alirezarezvani/claude-skills | 100 | MIT |
| norifumi3/cc-marketplace | 100 | MIT |
| OpenHands/extensions | 92 | MIT |
| HelixDevelopment/agent | 92 | MIT |
Database snapshot: 13.11.2026 · package version 9d3c3ee5f55e (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90review-agent-memory
Reviews agent memory and state-store configuration for correctness. Use for "review agent memory", "check state store config" or "audit agent persistence". - 100add-agent-memory
Wire Redis Agent Memory into an existing agent with redis-iris so it remembers users across sessions. Asks five questions (what to remember, what to share, what never to keep, how long to keep it, whether users can be forgotten), writes the answers to service.yaml, provisions… - 90memory-design
Design memory for an LLM agent — what to keep, where to keep it, and when memory hurts more than it helps. Use when the user is adding memory to an agent and mentions short-term memory, long-term memory, episodic, semantic, conversation history, summary memory, vector memory,… - 100build-memory
Use this skill when the user wants to build, refresh, or teach their Aicoo agent memory from their real context — files, repo, git history, docs, or Claude/agent memory. Triggers on: 'build my memory', 'build my agent memory', 'teach my agent about me', 'what should my agent… - 90wiki-memory
Use when designing, building, or discussing the memory architecture for a legal-AI agent — including user memory (persistent preferences and context), agent memory (matter-level state, cross-session recall), embedding stores for RAG, recall and forget controls, and the privacy… - 90agent-experience-persistence
基于 TencentDB Agent Memory(TencentCloud/TencentDB-Agent-Memory)做 Agent 经验的 跨会话持久化:当长任务上下文被工具日志撑爆需要「卸载但可回溯」、要把对话沉淀为 L0-L3 分层画像/场景/SOP 且要求白盒可审计、或在 OpenClaw/Hermes 宿主上零改码接入 记忆插件时触发。边界:不做通用记忆层选型、不优化检索排序算法、不为代码库建静态 知识图谱。