ldclabs
from GitHub
工具与效率
- 📁 references/
- 📁 scripts/
- 📄 SKILL.md
Persistent graph-based memory for AI agents via KIP (Knowledge Interaction Protocol). Provides retrieval-first memory operations (KQL), durable writes (KML), schema discovery (META), and memory hygiene patterns. Use whenever the agent needs to consult or update persistent memory, especially for: remembering user preferences/identity/relationships, storing conversation events, answering questions that depend on past sessions, and any task involving `execute_kip`.
- 📁 examples/
- 📁 references/
- 📄 SKILL.md
This skill should be used when the user asks to 'set up memory', 'create memory files', 'create MEMORY.md', 'set up topic files', 'improve memory organization', 'what should I remember', 'how to structure memory files', 'MEMORY.md is too long', 'what goes in memory vs topic files', 'memory best practices', or wants to establish a persistent knowledge base across Claude Code sessions. Triggers on: memory setup, MEMORY.md, topic files, cross-session knowledge, persistent notes, memory maintenance, memory pruning.
tkellogg
from GitHub
工具与效率
- 📄 debugging-communication.md
- 📄 debugging-jobs.md
- 📄 SKILL.md
Diagnose agent behavior using event logs, journal history, and scheduler state. Use when you need to understand why something went wrong, review your own patterns, audit scheduled jobs, or debug communication issues. Do not use for one-off messaging or memory management (use the memory skill instead).
ten-builder
from GitHub
工具与效率
- 📁 agents/
- 📁 references/
- 📄 SKILL.md
세션 종료 시 Memory, Handoff를 자동 정리. /pack
keepnotes-ai
from GitHub
工具与效率
- 📁 .claude/
- 📁 .claude-plugin/
- 📁 .github/
- 📄 .gitignore
- 📄 CLAUDE.md
- 📄 CONTRIBUTING.md
Reflective Memory
webrenew
from GitHub
工具与效率
CLI reference and workflows for memories.sh — the persistent memory layer for AI agents. Use when: (1) Running memories CLI commands to add, search, edit, or manage memories, (2) Managing lifecycle workflows (session/checkpoint/compaction/consolidation/OpenClaw memory files), (3) Setting up memories.sh in a new project (memories init), (4) Generating AI tool config files (CLAUDE.md, .cursor/rules, etc.), (5) Importing existing rules from AI tools (memories ingest), (6) Managing cloud sync, embeddings, git hooks, or reminders, (7) Troubleshooting with memories doctor, (8) Working with memory templates, links, history, tags, or reminder schedules.
membrowse
from GitHub
工具与效率
Integrate MemBrowse memory tracking into a project that produces ELF binaries. Use when the user wants to set up MemBrowse, add memory analysis GitHub workflows, create membrowse-targets.json for tracking memory usage, or add a MemBrowse badge to the README. Works with embedded firmware (STM32, ESP32, nRF, RISC-V) and non-embedded ELF targets (Linux x86/x64, game engines, system software).
AIPMAndy
from GitHub
工具与效率
- 📁 .github/
- 📁 assets/
- 📁 references/
- 📄 .gitignore
- 📄 CONTRIBUTING.md
- 📄 LICENSE
DNA 记忆系统 - 让 AI Agent 像人脑一样学习和成长。 三层记忆架构(工作/短期/长期)+ 主动遗忘 + 自动归纳 + 反思循环 + 记忆关联。 激活场景:用户提到"记忆"、"学习"、"进化"、"成长"、"记住"、"回顾"、"反思"。 --- # DNA Memory - DNA 记忆系统 > 让 Agent 不只是记住,而是真正学会。 ## 核心理念 人脑不是硬盘,不会无差别存储所有信息。人脑会: - **遗忘**不重要的 - **强化**反复出现的 - **归纳**零散信息为模式 - **反思**过去的成功和失败 DNA Memory 模拟这个过程,让 Agent 真正"进化"。 --- ## 三层记忆架构 ``` ┌─────────────────────────────────────────────────┐ │ 工作记忆 (Working Memory) │ │ - 当前会话的临时信息 │ │ - 会话结束后自动筛选 │ │ - 文件:memory/working.json │ └─────────────────────────────────────────────────┘ ↓ 筛选 ┌─────────────────────────────────────────────────┐ │ 短期记忆 (Short-term Memory) │ │ - 近7天的重要信息 │ │ - 带衰减权重,不访问会逐渐遗忘 │ │ - 文件:memory/short_term.json │ └─────────────────────────────────────────────────┘ ↓ 巩固 ┌─────────────────────────────────────────────────┐ │ 长期记忆 (Long-term Memory) │ │ - 经过验证的持久知识 │ │ - 归纳后的认知模式 │ │ - 文件:memory/long_term.json + patterns.md │ └─────────────────────────────────────────────────┘ ``` --- ## 记忆类型 | 类型 | 说明 | 示例 | |------|------|------| | `fact` | 事实信息 | "Andy 的微信是 AIPMAndy" | | `preference` | 用户偏好 | "Andy 喜欢简洁直接的回复" | | `skill` | 学到的技能 | "飞书 API 限流时要分段请求" | | `error` | 犯过的错误 | "不要用 rm,用 trash" | | `pattern` | 归纳的模式 | "推送 GitHub 前先检查网络" | | `insight` | 深层洞察 | "Andy 更看重效率而非完美" | --- ## 核心操作 ### 1. 记录 (Remember) ```bash python3 scripts/evolve.py remember \ --type fact \ --content "Andy 的 GitHub 账号是 AIPMAndy" \ --source "用户告知" \ --importance 0.8 ``` ### 2. 回忆 (Recall) ```bash python3 scripts/evolve.py recall "GitHub 账号" ``` 返回相关记忆,按相关度和重要性排序。 ### 3. 反思 (Reflect) ```bash python3 scripts/evolve.py reflect ``` 触发反思循环: 1. 回顾近期记忆 2. 识别重复模式 3. 归纳成认知模式 4. 更新长期记忆 ### 4. 遗忘 (Forget) ```bash python3 scripts/evolve.py decay ``` 执行遗忘机制: - 7天未访问的短期记忆权重衰减 - 权重低于阈值的记忆被清理 - 重要记忆不会被遗忘
Bryptobricks
from GitHub
工具与效率
- 📁 benchmarks/
- 📁 bin/
- 📁 data/
- 📄 .gitignore
- 📄 .npmignore
- 📄 CHANGELOG.md
Structured memory system for AI workspaces. Indexes markdown memory files into SQLite FTS5 for fast, cited search. Extracts structured facts, maintains memory health, and provides an MCP server with live search + write-path for Claude Code integration. --- # Structured Memory Engine ## MCP Tools (v4) When running as an MCP server (`node lib/mcp-server.js`), exposes: - `sme_query` — Search memory. Supports `query`, `limit`, `since`, `type`, `minConfidence`, `includeStale`. - `sme_context` — Get relevant context for a message. Returns ranked, token-budgeted, formatted context for injection. Supports `message`, `maxTokens`. - `sme_remember` — Save a fact/decision/preference to today's memory log. Auto-indexed. - `sme_index` — Re-index workspace. Use `force: true` for full rebuild. - `sme_reflect` — Run maintenance: decay, reinforce, stale detection, contradictions, prune. Use `dryRun: true` to preview. - `sme_status` — Index statistics. ## CLI Commands ```bash # Index workspace memory files node lib/index.js index [--workspace PATH] [--force] [--include extra.md,other.md] # Search indexed memory node lib/index.js query "search terms" [--limit N] [--since 7d|2w|3m|2026-01-01] [--context N] [--type fact|confirmed|inferred|...] [--min-confidence 0.5] [--include-stale] # Show index status node lib/index.js status [--workspace PATH] # Memory maintenance node lib/index.js reflect [--workspace PATH] [--dry-run] node lib/index.js contradictions [--workspace PATH] [--unresolved] node lib/index.js archived [--workspace PATH] [--limit N] node lib/index.js restore <chunk-id> [--workspace PATH] ``` ## Configuration
atxp-dev
from GitHub
工具与效率
Agent memory management — cloud backup, restore, and local vector search of .md memory files
realmorrisliu
from GitHub
工具与效率
Manage persistent memory across sessions for long-running tasks. Automatically read memory at session start and write updates at session end. This enables coherent work that spans multiple context windows.
Civitasv
from GitHub
测试与安全
- 📁 references/
- 📄 .gitignore
- 📄 README.md
- 📄 SKILL.md
Use when deciding whether short-term session memory should be promoted into long-term memory or a knowledge store, and writes must stay auditable, conflict-safe, and privacy-scoped.