Memory and context

Reusable skills and lifecycle skills (/spec to /ship) for software projects, including PR review, memory, and planning workflows

Build and operate Azure SQL Database applications, from provisioning and secure connections through schema design, deployment, data…

Build and manage Azure SQL Database applications in Visual Studio Code with the MSSQL extension, including connections, schema and ORM…

Cortex. A host-portable Markdown second brain shared by Claude, ChatGPT Work, and Codex.

Build, deploy, and operate applications on AWS. Skills to author infrastructure-as-code (CDK, CloudFormation), use core services (Lambda,…

Official TITANOS seller skills for agents (Cursor, Claude Code) — skills oficiais de vendedor TITANOS para agentes. Amazon Ads, listing,…

Zettelkasten-style LLM wikis across a set of subject-matter domains, built from reference texts and packaged as Open Knowledge Format (OKF)…

Build, deploy, and operate applications on AWS. Skills to author infrastructure-as-code (CDK, CloudFormation), use core services (Lambda,…

Search, extract, crawl, map, and research the web with Tavily MCP tools and bundled skills for research, enrichment, monitoring, and…

Durable PostgreSQL knowledge and agent-friendly issue tracking for coding agents.

Agent skills for building, deploying, evaluating, and monitoring LLM pipelines on the orq.ai platform.

XTrace MemHub team memory: search_memory / save_artifact / import_conversation MCP tools plus skills for setup, login, onboarding, artifact…

Develop and test applications locally with the Azure SQL Database container, including setup, secure connections, schema and data…

Self-maintaining, self-proving skills and knowledge: adaptive web research on four tracks (the subject, the skills, plugins, MCP servers…

AI/ML pipeline skills: prompts, LLM costs, RAG, embeddings, guardrails.

Personalized AWS guidance built on patterns from 350,000+ startups—architecture, cost, security, and migration, from day-one account setup…

Write SurrealQL, design schemas and indexes, run and operate SurrealDB from the CLI, manage migrations with SurrealKit, build vector…

Rigorous AI software-engineering toolkit for Kiro, adapted from the Cursor plugins pstack, thermos, continual-learning, and ralph-loop.…

Full AI context layer over MCP — tree-sitter code-map, document RAG (PDF/Office/HTML/email + OCR + reranker), shared agent memory,…

A set of Copilot skills for capturing, documenting, and implementing repository context.

Official Kaddo Agent Plugin for Knowledge Driven Development. Packages portable Kaddo Skills, agent guidance and @kaddo/mcp integration;…

WinDbg diagnosis workflows and report validation for applications, services, UMDF/user-mode drivers, and kernel-mode drivers.

Adam's machine-bound skills that need local resources (WSL/Windows homes, local files, a signed-in browser): PDF tooling, Claude Code…

Agylite: deterministic routing, budgeted context, project state and local test-first verification over a curated bundle of engineering,…

Research customer feedback, support, surveys and product usage in your connected BuildBetter workspace. Chat-first workflows with source…

DreamerOS starts agents with shared rules, verifies intent, carries memory across sessions, checks claims, and routes work through one…

Ennoia에서 에이전트 생성, 문서 지식 연결, App 실행, 운영 진단과 제품 피드백을 수행합니다.

A governed Copilot squad that can create bounded research and worktree swarms.

Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore (Strands, LangGraph), connecting…

Data lake, analytics, and ETL workflows with S3 Tables, AWS Glue, and Athena. Covers managed Iceberg tables on S3 Tables, ingestion from…

Data lake, analytics, and ETL workflows with S3 Tables, AWS Glue, and Athena. Covers managed Iceberg tables on S3 Tables, ingestion from…

Your project's memory: the sessions that happened, the durable observations drawn from them, and the plans. Skills and tools for reading…

Cross-tool memory for AI agents through Nowledge Mem skills and MCP.

Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore (Strands, LangGraph), connecting…

Universal LLM API client for 174 providers — chat, streaming, tools, embeddings, search, OCR, plus an OpenAI-compatible proxy and an MCP…

Memory House: persistent, scoped agent memory (personal, team, org) backed by Azure Cosmos DB, delivered through the Inference Platform…

Work on qi — a local-first text river running Granite 4.1, with research that verifies its own citations and a standalone Mac app. Covers…

Run your e-commerce business from ChatGPT: stores, orders, listings, catalog, suppliers, ads, market research and product media, through…

Installs the official Titanos OAuth MCP server plus operating skills for marketplace, Amazon, listings, research and safe writes.

Harness-agnostic curation tooling for Zettelkasten-style OKF wiki bundles: skills to onboard sources, dispatch domain curators, review…

Asks TypeSafe's Jev which bulky tool results the session still needs, and replaces the rest with a bounded head plus a note.

Secure HydraDB automation for Codex with workspace sync, prompt recall, and conversation capture.

Recall and save decisions, preferences and facts in your Kumiho Cloud workspace. Hosted OAuth MCP and six memory skills for Grok Bot and…

LangChain4j skills for agent design and orchestration patterns, MCP client integration, official/Azure OpenAI SDK usage, code review, and…

Cross-session memory and token savings for coding agents.

Markdown-first long-term memory shared across your coding agents: one local memtomem store, searchable from Hermes, Claude Code, Codex CLI…

Plan, verify, and challenge analytics with governed, multi-source context and interview-built ground truth.

usectx Memory kit: attach hosted MCP, session lease, hop, extract. Tokens stay out of mcp.json.

Cross-harness memory from Beacon traces: recall reviewed project lessons, distill agent sessions into approved memory, promote memory to…

Saved rules, corrections, and decisions that every new chat loads first.

Compute embeddings with Helical foundation models, hosted on Helical's GPUs or locally on your own GPU with the open-source package.

How the agent runs itself. Scheduled automations and saved workflows, the assistant that coordinates them, and the user memory that carries…

Memory abstraction layer for Claude Code, Codex CLI and Pi: deterministic capture hooks plus model-driven skills over a markdown wiki in…

Specification-driven Chinese novel planning, drafting, retrieval, and continuity review.

Use this plugin for obsidian documentation, capture, research, and planning workflows.

Semantic long-term memory and context engine for coding agents. Recall prior knowledge with the find/search/read MCP tools and persist…

Semantic long-term memory and context engine for coding agents. Recall prior knowledge with the find/search/read MCP tools and persist…

Skill Heaven is live. Summon one skill into a session with nothing installed: manual /summon at every rung, a clean-room launcher floor…

Portable Agent Plugins package for the Agent Toolkit for AWS. Bundles the AWS MCP Server (secure, IAM-governed access to 300+ AWS services,…

Build agents and their interfaces: write prompts, skills, and MCP servers, delegate across subagents, enforce output schemas, and use…

Haoman discussion, repository adoption, planning, and Virtual CTO skills with an OAuth-enabled MCP connector.

Local-first memory skills and MCP tools for grounded recall, briefs, and governed capture.

Mozeček — agent memory: MCP tools (search, list, remember, recall, timeline, ask), session capture and memory skills.

Connect to Nestly, turn business ideas into verified Spaces, and steward agents and living Things.

Search, read and capture your Retain meetings, tasks and threads from your assistant.

Structured web data for Hermes Agent: web search, page extraction, and structured commerce, social, travel, jobs, real-estate, app-store,…

Substrate long-term memory for ChatGPT Work, Codex in the ChatGPT desktop app, and Codex CLI.

Nothing an AI session learned is lost when you change model, session, tool or vendor. Two tiers of plain-markdown knowledge: a per-project…

Read your NOEIS Library, compare source passages with your thinking, and file research with provenance.

Use this plugin for notion capture, meeting, research, and implementation-planning workflows.

UZE's own agentic Skills: making a project's instructions context (AGENTS.md and its harness bridges) portable, working in the checkout UZE…

Local-first RAG memory for AI agents: hybrid BM25/semantic search, GraphRAG, and an MCP server with OAuth 2.1. Index docs and code, then…

Typed facts for agents via @quarkos/cairn. Assert, recall, and retract beliefs that outlive the session. Never the unscoped npm package…

Run this workflow from Codex. Generate and maintain .claudeignore files for Claude Code projects. Analyzes repository structure to identify…

Harvest documentation websites into structured local references and navigate existing documentation sets.

대화에서 자신을 발견하고, 개인 프롬프트와 실제 대화 맥락으로 기록하는 플러그인

Skills for building document pipelines with the gaik Python toolkit: choosing a document parser that preserves table structure, designing…

Session handoff and continuation for Codex. Compact conversations into structured handoff documents for task continuity, then find and…

Portable Agent Plugins package for Kyberion governed operations, knowledge access, mission control, approvals, and audit workflows.

Precise local semantic code search for coding agents, powered by local embedding models.

Durable, revision-aware memory for AI conversations.

NCP — an agent-to-agent memory bus over MCP. Bounded, trust-weighted context assembly, durable cross-session memory, and directed whispers…

Olympus answers questions from your own mail, files and notes, with citations. The engine runs privately on your Mac; ChatGPT asks it…

POMA Grill — ingest documents into the Grill context engine and run semantic search over them from any agent.

Expert PostgreSQL guidance and live database tools for Postgres anywhere

Search the private, read-only Rockaway Q and QAQ brain through team-scoped MCP services.

Search the private, read-only Rockaway Ventures brain through team-scoped MCP services.

Search Scio for facts, explanations and sources. Use for factual research and verification; contribute, translate or review when asked.…

Sourced project context and reviewed memory through Snipara Hosted MCP.

Personal and company context from Unabyss, available to your agent through the Unabyss MCP server.

Knowledge-first workflow for agents backed by Usable. Search team knowledge before implementing, retrieve complete sources, separate…

Connects Codex to Virlow, your end-to-end encrypted notes, and makes memory automatic: recall at the start of a task and a reminder to save…

Secure secrets management, multi-chain signing, agent memory, automations, and 155 tools (offered per agent entitlement, in toolsets) for…

Discover storage engines, configure global and project policies, and route tasks, notes, and artifacts with verified synchronization.

Shared project memory and cooperative edit ownership through a local memd daemon.

A git-tracked memory for this repo: Claude recalls the rule before it edits a file or runs a command, and captures one after a failure.…

Create, review, and repair authored interfaces using retrieved code and visual references.

Read-only first-party Aperture Wallet product, security, network, release, and Journal knowledge for AI agents.

AI memory for fractional CMOs — client-partitioned minds, meeting prep, brand voice, and Business OS (EOS) tools via Armbrain MCP.

Use Axiom as the persistent Mind behind a replaceable AI reasoning host.

Plugin that includes the Blutui MCP server and Skills for building Blutui projects.

Give AI coding agents access to your product strategy, customer research, decisions, and current priorities through Brief.

Answer company questions from accepted ByteRover Company Brain context and submit knowledge for governed learning.

Hosted CentricMem librarian: organise and retrieve Markdown memory via host MCP.

CM GPT — the Critical Manufacturing MES documentation assistant. Answers questions on MES features, configuration, APIs, architecture and…

Local hybrid code search for your workspace — tree-sitter symbols, BM25 full-text and MiniLM semantic embeddings, fused. Claudinio Code's…

Read local Codex conversation history by deeplink or thread ID without modifying Codex state.

High-security, fully offline, encrypted vector memory for AI agents. AEAD-encrypted vault, locked by default after restart, no API key and…

Structural code-context slicing for Java, TypeScript/TSX, JavaScript, Python, Rust, Go, C, C++, C#, and Kotlin. Serves a budget-bounded,…

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM…

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM…

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM…

Customer memory with recall, confirmation, forgetting, and pre-action evidence checks.

Search your CoralSwarm knowledge and save snippets you choose.

Corkboard wiki integration: MCP server tools for reading, writing, and searching your workspace, plus a CLI skill for surgical page edits,…

deja-vu: memory for coding agents from the sessions already on your disk — Claude Code, Codex, Cursor, opencode and thirty-eight more —…

Persistent memory for AI coding agents. Survives across sessions and compactions.

Auditable context selection, exact recovery, and receipts for AI coding agents.

Esment memory for your AI assistant — recall before you answer, save what matters.

Your team's shared, verified knowledge for AI agents: ask what's true about your org and how work gets done, then record what you learn.…

GuruSup Brain: your company's memory in your AI. Search decisions, people, customers and projects across every connected source.

Gyrus: Unified Context Control Plane & Memory Engine for AI Agents

Long-term memory for AI agents. Recalls relevant past context before you answer and retains durable facts as you work, backed by…

Residual-honest product edge memory MCP package map for public iomesh-memory-mcp via stdio. Available, optional beside TTFH · dual_write…

Make IronGraph the agent's durable second brain: query and change graph data with Cypher, preserve documents, and semantically recall…

Project-scoped durable memory, recall, Skills, and governed context for AI agents.

Local-first persistent memory: store durable facts, recall them in any session. Zero cloud, zero telemetry, SQLite-backed.

Local-first semantic memory for coding agents, packaged with a minimal-profile MCP server and LLM skill.

Semantic recall over past sessions and journal entries.

Cross-tool AI memory over MCP. Checkpoint chats in Cursor, resume them in Claude or ChatGPT. EU-hosted full-text search — not another local…

Private persistent memory and hybrid search for ChatGPT with zero-config Cloudflare account sign-in.

Permissioned search and cited answers over Slack, Drive, Gmail, Jira, and 50+ workplace sources.

Reusable PowerContext skills and MCP configuration for agent integrations.

Qdrant stores semantic memories and finds related memories with vector search

Qdrant stores semantic memories and finds related memories with vector search

Retail AI plugin bundling semantic product catalog search and generative image/video virtual try-on skills on Google Cloud.

Find people with real experience. Let your agent learn from their work.

Shared project memory and tasks for your AI agents.

thinqOS Mind: the persistent memory your AI tools share. Recall what matters, consult before consequential work, and keep what you decide,…

Reduce context bloat deterministically without requiring an OpenAI API key.

Typesense v30 API rules and recipes for schemas, syncing data, search, API keys, relevance, vector search and running a cluster, plus the…

Connect your AI assistants to your Upsy memory, files, connected accounts, and cloud browser with the access you choose.

Private organization knowledge and recent computer context from YourAI.

自然角色对话、角色切换与 OOC；连接后端后支持独立长期记忆。

Agents Best Practices — provider-neutral agent-harness architecture: loops, tools, permissions, planning, memory, compaction, evals, safety

A durable, cross-project OKF markdown knowledge base for Claude Code and Codex.

Guided setup for Claude Cowork: confirms your workspace folder, connects your tools, builds your context files (about you, your voice, how…

AI memory made of plain markdown notes you can read and edit in Obsidian or the web app.

Recall locally stored agent memories through the Fidelis MCP server.

Connect Kiro to your GreatArrow.ai workspace — persistent semantic memory shared across every AI you use, 22 agents, and deep integrations…

Destilliert die laufende Session in ein Übergabe-Dokument, mit dem ein anderer Agent direkt weiterarbeiten kann. Die letzte Antwort ist das…

Nightly deterministic memory consolidation for Hermes: corroborate facts with real conversations, propose the few worth keeping, ask about…

Field notes for a Hermes install: pitfalls with root cause, local core patches checked after every update, and a pinned Telegram dashboard.

JustOnce: persistent memory for AI coding assistants over MCP. Remembers your projects, stack, conventions, decisions and preferences…

Ledger-backed persistent memory for coding agents: append-only facts with retraction vaccines, scars, and a generated MEMORY.md projection

Read any web page as a clean, token-efficient AIDocument. Built for AI agents, backed by Lyrenth's independent web index of 2B+ pages.

A dual-path memory system for proactive agents: a typed knowledge graph with evidence, contradictions and supersession, maintained in the…

Remembers your project across chats: characters, style decisions, naming rules, asset lists, and how they relate. Runs the official Model…

Never reconstruct where you left off. Local-first continuity for you and your coding agents — resume, decisions, and what's still in the…

Use Mnemosyne MCP as a selective, project-aware memory and handoff layer across agent sessions.

Search and read Notion workspaces, work with Custom Agents, and make permission-gated content changes.

Community package for the official Notion hosted MCP plugin for user-authorized workspace access. Search pages, read docs, edit content,…

Native OpenViking long-term memory integration for Antigravity (MCP tools + automatic recall + non-blocking background capture).

Build multimodal AI applications with Pixeltable using declarative tables, computed columns, retrieval, agents, and HTTP services.

Use RemDo notes and documents in ChatGPT and Codex.

Load and save durable project knowledge through seven Rementum MCP tools.

明示依頼された試行錯誤の学びを、重複確認後に ast-grep・AGENTS.md / CLAUDE.md・スキルとして固定する。タスク完了だけでは自動実行しない。

Encrypted portable agent memory via SaveState MCP

Search your synced Screenpipe history across devices. Requires Data Sync.

Preserve intent, evidence, and workspace state when moving long coding-agent work into a fresh session.

Search local Codex, Pi, and Claude Code session history to recover prior decisions, feedback, prompts, and conversation snippets.

SULCUS proactive memory and context engine for persistent cross-session recall and knowledge capture.

Extract a markdown heading, TeX section, or PDF outline item without loading the rest of the file. Skill for agents using the surf CLI.

Shared team memory for Cursor: remote MCP with email/OTP Connect, the recall-first memory rule, and hooks that capture Agent Chat plus…

Work with your TinyAssets command center, inspect workflows, and manage shared knowledge from chat.

Turn any file — PDF, spreadsheet, scan, email, 60+ formats — into clean, agent-ready structured data (Markdown or JSON) without leaving…

Shared Markdown memory with scoped retrieval, safe maintenance, and source-backed ingestion across assistants.

AnchorMind long-term memory hooks: session start memory injection and session end reflection

Cloudflare edge stack: multi-Worker pnpm/turbo monorepos, AI Search manual document sync, and RAG chat agents for Fumadocs sites

Tools and techniques for maximizing GitHub Copilot effectiveness through better context management. Includes guidelines for structuring…

Tools and techniques for maximizing GitHub Copilot effectiveness through better context management. Includes guidelines for structuring…

Tools and techniques for maximizing GitHub Copilot effectiveness through better context management. Includes guidelines for structuring…

Tools and techniques for maximizing GitHub Copilot effectiveness through better context management. Includes guidelines for structuring…

Local, explicit, human-readable cross-session memory for GitHub Copilot CLI.

Collect explicitly enabled Agent tool evidence, discover API metadata, preserve test history and return concise task memory.

Persistent memory for Codex. Stores decisions, bugs, and discoveries across sessions in a local SQLite database.

First-class Codex adapter for durable Musubi capture and recall. Shadow-only by default; verified delivery is an explicit deployment gate.…

The default assistant of an mwe-mcp memory server: every turn is remembered, every turn is recalled.

Persistent Markdown memory. Searches memory before answering and writes the conversation back in the background, as files you can read and…

Compaction that continues without a break: a handoff card written before the context is compacted, a pointer to it after, a hold while…

Codex-only SessionStart hook that injects ancestor AGENTS.md files and repo-configured instruction files.

Carry personal preferences, decisions, and verified facts across ChatGPT, Codex, and other agents.

Saves tokens by shunting I/O-heavy work to a cheap worker model. Hooks block large file reads and redirect to bulk-read/code-write, which…