Productivity
hermes-ai-team
Phase-by-phase guide to building a team of Hermes agents: SOUL, memory, vault, nightly research, kanban and a chief of staff. Written to be read by the agent, not just about it. 36…
Productivity
hermes-workspace
Web-based workspace: chat, terminal, memory browser, skills manager, inspector. Most complete GUI for Hermes. 6.5k★.
Data
screenpipe
Records your screen continuously and feeds it to Hermes and 100+ other agents. Local and private.
Documentation
review-chamber
Captures and retrieves PR-review findings in memory palaces. Use after PR review to store architectural decisions, patterns, and standards for future reference
Productivity
session-palace-builder
Builds session-scoped temporary memory palaces for extended conversations
Engineering
python-performance
Profiles Python code for performance bottlenecks and memory issues
Productivity
context-optimization
Optimizes context window via MECW principles and memory tiering
Engineering
ai-coding-ok
USE THIS SKILL FIRST on any coding task (feat, fix, bug, refactor, plan, design, brainstorm, code review, implement, add feature, write tests, 新功能, 修复, 重构) when the project contain…
Productivity
claude-memory-kit
Persistent memory for Claude Code agents with an agent-audit-ritual architecture. User only talks; the agent captures, audits, proposes promotions, and writes. Memory lives in laye…
Data
Mnemosyne
Local-first, sub-millisecond memory system built specifically for Hermes. SQLite + sqlite-vec hybrid search (50% vector / 30% FTS5 / 20% importance), BEAM tiered architecture (work…
Productivity
memory-management
Guide Claude Code memory and CLAUDE.md management — what to record, how to write, when to update vs create new, and how to organize. Use when user asks to "记一下"、"新增记忆"、"更新记忆"、"沉淀本次…
Productivity
memorylane
Zero-config persistent memory for Claude with automatic cost savings. Use when you need to remember project context, reduce API token costs, track learned patterns, manage memories…
Engineering
claude-codex-collaboration
Enable automated collaboration between Claude Code and Codex CLI using Byterover as shared memory. This skill should be used when architectural review or code validation from Codex…
AI / ML
create-friend
Distill a friend into an AI Skill. Import chat history, photos, social media, generate Friendship Memory + Persona, with continuous evolution. Use this skill whenever the user ment…
AI / ML
integration-supermemory
Connect Supermemory (fast scalable memory + context engine for AI agents — add/search/graph memories with optional project scope) to a self-hosted Hermes Agent over SSH via Superme…
Productivity
total-recall
The only memory skill that watches on its own. No database. No vectors. No manual saves. Just an LLM observer that compresses your conversations into prioritised notes, consolidate…
Productivity
total-recall
The only memory skill that watches on its own. No database. No vectors. No manual saves. Just an LLM observer that compresses your conversations into prioritised notes, consolidate…
Productivity
saipen
Persistent .saipen/ memory enables any agent to resume prior work. Cold-start kernel loads first, with modules activated on demand per STATE. Reply language follows STYLE.md preced…
Productivity
context-engine
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context during conversations, and e…
Productivity
mem0-memory
Maintains persistent, cross-project memory via mem0 MCP—auto-records reusable technical insights, preferences, and patterns, then recalls them proactively when relevant topics surf…
AI / ML
longmemo-elite
Elite long-term memory system for agents: WAL protocol ensures context survives compression, crashes, and restarts. Hybrid vector-keyword-graph retrieval with RRF ranking prevents …
Automation
memory-distiller
Memory-distiller compresses AI agent logs into dense, structured summaries with 4-8x reduction while preserving critical events. It applies type-specific strategies for events, les…
General
baby-skill
Core baby intelligence skill. Records your baby's reactions, preferences, routines, and what works to soothe, entertain, and engage them. Builds a living profile that grows with yo…
AI / ML
secondmind
Autonomous three-tier memory system with proactive initiative, project tracking, and social intelligence. Ingests conversations, extracts knowledge and emotions, and suggests autom…
Research
dash-research-vault
Multi-agent research vault with Evensong-style memory causation, Ebbinghaus decay, and L2 pressure self-evolution. Three-tier memory (public/restricted/internal), trigger-based age…
Productivity
obsidian-openclaw-memory
Set up Obsidian + OpenClaw as a living AI memory system. Use when helping users configure their workspace so their AI assistant remembers context across sessions, builds a knowledg…
Productivity
hermes-skill-kit
Three community-vetted skills: **feishu-document-api** (programmatic Feishu/Lark document creation), **feishu-response-format** (Feishu response formatting with 3 table schemes, Ca…
Engineering
system-audit
System-wide evidence-based audit of orchestrator, docs, rules, memory, subagents, tools, and claimed delivery, followed by immediate fixes and ranked backlog. Triggered by explicit…
AI / ML
persistent-memory-engine
Infinite hierarchical memory engine providing structured, searchable local storage that runs parallel to an agent's built-in memory. Handles cross-session retention, precise retrie…
DevOps
hermes-memory
Configure Hermes memory (built-in by default, or an external provider like mem0) on a self-hosted Hermes Agent over SSH. Surfaces the memory-ceiling reality, installs the python de…
Productivity
narrative-keeper
Maintains the living product narrative — the evolving story of what this intelligence system is, where it came from, where it's going, and what it believes. Use for updating the pr…
Productivity
context-persistence
Pull what we already know about a topic before re-explaining. Say "what do we know about <topic>", "give me the prior context", or "remind me where we left off". Fires at session s…
Productivity
clawdi
Cross-agent long-term memory and session history capturing user preferences, coding habits, projects, past bugs, architecture decisions, and conversations across multiple agents. S…
Data
memory-load
Loads relevant entries from memory/ into context at conversation start or when topics may overlap stored facts, habits, goals, relationships, work, health, or hobbies. Reads memory…
AI / ML
hermes-snow-search
Global memory retrieval layer — cross-session SQLite FTS5 search (~0.1s) across full message history, memory, and facts, with CJK/English auto-routing (trigram vs unicode61 tokeniz…
Engineering
workflow-performance-investigation
Systematic performance profiling workflow: establish baseline metrics, select appropriate profiler across language ecosystems, capture CPU/alloc traces under load, classify bottlen…
Productivity
clawng-term-memory
Version-controls SOUL.md, MEMORY.md, and core knowledge files via git with automatic GitHub push, keeping your agent's identity, memory, and rules portable and restorable across an…
Productivity
memoir-onboard
Populates or refreshes a persistent high-level project snapshot. In git repos writes codebase:onboard with modules, goals, rules, and lessons for onboarding or codebase tours. In n…
Productivity
code-memory
Local-first memory layer combining semantic vectors, call/import graphs, episodes, and bi-temporal claims. Enables codebase orientation, topology queries, prior-work recall, index …
Security
memory-load-check
Reviews PRs and diffs for unbounded memory loading, concurrency issues, oversized payloads, and missing pagination or byte caps. Apply during cleanup jobs, data imports, file parsi…
Automation
memory-pipeline
Maintains agent memory across sessions through structured fact extraction, knowledge graphs, briefings, and execution discipline via pre-game routines, result compression, and afte…
AI / ML
zeref-os
Zeref OS — local-first context and memory engine for AI-assisted work. Harness-agnostic, model-agnostic, privacy-first. Flat memory layout, per-project wiki, append-only pattern lo…
Engineering
mobile-performance
Profiles mobile apps for startup time, memory leaks, battery usage, network efficiency, frame rate, and binary size. Detects image caching issues, undisposed controllers, aggressiv…
Productivity
Mcp Claude Code Browser Tools
mode: code instructions: general: - "Status Prefix: Begin EVERY response with either '[MEMORY BANK: ACTIVE]' or '[MEMORY BANK: INACTIVE]'" - "Implement features and maintain code q…
Productivity
Programming
mode: code instructions: general: - "Status Prefix: Begin EVERY response with either '[MEMORY BANK: ACTIVE]' or '[MEMORY BANK: INACTIVE]'" - "Implement features and maintain code q…
Productivity
bettermemory
Verification-grade memory between sessions. Use bettermemory's MCP tools (memory_search, memory_show, memory_write, memory_verify, memory_record_use, etc.) instead of writing to fi…
Productivity
build-my-memory-file
Builds a durable MEMORY.md capturing your decision patterns, preferences, and past failures with built-in privacy guardrails. Produces a structured personal-context file through ta…
AI / ML
folded-memory-implementation
Implements a three-tier memory system for agents: recent interactions remain detailed, prior sessions compress into episodic summaries, and long-term knowledge consolidates into se…
Automation
linggen
Durable cross-host memory and browser control via one local MCP server. Three-tier memory model stores user identity (core + long-term + episodic) rather than activity logs; browse…
AI / ML
anima-aios
AI agent cognitive growth system with five-layer memory architecture, knowledge palace organization, pyramid thinking, Ebbinghaus decay, persistent memory management, visual intima…
AI / ML
enhanced-memory
Hybrid vector and keyword retrieval with temporal and filepath scoring, adaptive weighting, pseudo-relevance feedback, and knowledge-graph cross-references. Replaces default memory…
Productivity
lightspeed-project-memory-manager
Maintains project memory banks for Figma-to-WordPress workflows across design systems, block themes, plugins, WooCommerce, and hybrid projects. Retrieves briefs, context, patterns,…
Productivity
memory-keeping
Syncs session progress to STATE.md, coverage.md, files-examined.md, and appends a sessions/ log entry for durable outputs like new knowledge docs, verified facts, gotchas, or locke…
Productivity
molt-life-kernel
Agent continuity and cognitive health infrastructure. Provides persistent memory, crash recovery, append-only audit trails, heartbeat monitoring, coherence enforcement, and witness…
Productivity
compact-task-memory
Produce a compact lossy summary of TASK_STATE.md once memory exceeds practical size, retaining key decisions and next steps while discarding stale entries. Use after multiple compl…
AI / ML
colony
Cross-agent memory provider that injects commitments, affect, facts, patterns, and world model into sessions while syncing turns for extraction; exposes tools for commitment checks…
AI / ML
titen-memory
Recall and store verified project memory via Titen MCP: retrieve evidence-grounded context, persist durable signals, submit feedback, and manage checkpoints, leases, or handoffs. U…
Security
memory-radar
Scans AI agent memory files for prompt injections, credential leaks, and cross-file threat chains using seven detection categories, five-tier risk scoring, and optional LLM analysi…
Automation
prime-the-agent
Fast 30-second session starter that loads the current site, detects the page builder, ingests inline schemas, and enforces the no-raw-HTML rule. Maintains persistent per-site memor…
DevOps
wakeup
Loads long-term memory and applies persona directives at session start. Fetches repository memory via read token with SHA pinning; private repos via PAT when needed. Writes back th…
Showing the top 60 of 1,444. See the full list →