Memory and context

Goldentrii/AgentRecall-X

Command

AgentRecall consolidation & reflection — periodic triage of recurring corrections; proposes rule changes, never applies them without the owner.

Wxw-Gu/TraceMemo

Skill Claude CodeCodex

A skill for reading WeChat messages and images through TraceMemo, a local service that provides data the user is allowed to access. It can find contacts or group chats and help understand or summarise conversations and images.

mengjian-github/xiaomo-starter-kit

Instructions file CodexOpenCode

A repository-specific instruction file for the Xiaomo Starter Kit, a software project template. It tells coding agents how to handle sessions, memory, security, and internal versus external information.

Xuanwo/xurl

Skill Claude CodeCodex

Use xurl to access AI agent conversations via agents:// URIs. Invoke when the user: gives an agents:// URI, a provider shorthand like provider/..., or a bare thread/session ID; mentions conversations, threads, or sessions from any AI coding agent; wants to search, read, summarize, compare, or continue agent threads…

ReflexioAI/reflexio

Skill Claude CodeCodex

Captures user facts and procedural corrections into .reflexio/ so the agent learns across sessions. Use when: (1) user states a preference, fact, config, or constraint; (2) user corrects the agent and confirms the fix with an explicit 'good'/'perfect' or by moving on without re-correcting for 1-2 turns; (3) at start…

EXXETA/exxperts

Agent

Fast codebase recon that returns compressed context for handoff to other agents.

melonelish/context-engine

MCP server Claude CodeCodexCursor +2

Task-aware context compression for logs, RAG, and coding workflows. Runs locally from the melonelish-context-engine Python package.

ttommyth/interactive-mcp

Instructions file GitHub Copilot

Instructions for ttommyth/interactive-mcp, covering interaction with user and ai notes - cursor documentation system.

Lyellr88/marm-memory

Instructions file CodexOpenCode

AGENTS.md instructions for Lyellr88/marm-memory, covering marm-memory - agent instructions, architecture, consistency rules, code patterns and testing.

xiaoheizi8/crush-skills

Skill Claude CodeCodex

A tool for turning information about a romantic interest into an AI skill that can remember their personality and relationship history. It can work with chat records, photos, and social media content, and supports English and Chinese.

awizemann/harness

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

MCP server "memophant" as configured in awizemann/harness. Launched with ./.memophant/mcp/memophant-mcp --project-root . --default-project harness.

SakuraByteCore/codexmate

Skill Claude CodeCodex

Recovers project handoff context from local Codex, Claude Code, Gemini, CodeBuddy, and codexmate-derived sessions. Use when the user asks what happened in prior project/PR/branch/file/error work, needs a handoff brief, wants old decisions or validations recovered, or asks to summarize cross-session project activity…

Gnosil/semantix

Skill Claude CodeCodex

Install and use the semantix memory kernel as a middleware in your agent: extract user preferences / workflows / experience from past sessions, retrieve and inject them on demand. One binary + your agent's own tools.

cognesy/instructor-php

Agent

Agent loop, state model, tools, context management, hooks, and subagent orchestration.

rush-db/rushdb

Skill Claude CodeCodex

Build RushDB queries, searches, filters, and aggregations. Use whenever an agent needs to list or filter records, count or group data, traverse relationships, run semantic/vector search, construct a findRecords call, discover live labels and properties, or recall canonical EPISODE and MEMORYFACT records with mandatory…

aayoawoyemi/Ori-Mnemos

Skill Claude CodeCodex

Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.

Josverl/micropython-stubs

Agent

Use when auditing and improving all stubs under reference/micropython by iterating module-by-module, invoking Stub Source Auditor for each module, committing each accepted change to auditupdate, and recording durable learnings in repo memory.

AGI-is-going-to-arrive/Memory-Palace

Skill Claude CodeCodex

Use this skill for Memory Palace durable-memory work in this repository: saving facts for later, recalling cross-session memory, deciding create vs update, handling guardaction or guardtargeturi, or using readmemory("system://boot"), searchmemory, compactcontext, rebuildindex, or indexstatus. Also use it when the user…

disler/claude-code-is-programmable

Command Claude Code

Command "prime" from disler/claude-code-is-programmable, covering context prime, run the following commands and parallel read the following files.

sopaco/cortex-mem

Skill Claude CodeCodex

Persistent memory enhancement for AI agents. Store conversations, search memories with semantic retrieval, and recall context across sessions. Use this skill when you need to remember user preferences, past conversations, project context, or any information that should persist beyond the current session. Provides…

cyberchitta/llm-context.py

Skill Claude CodeCodex

Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch. Load when choosing what code to put in front of a model, packing…

AbdoKnbGit/tau

Plugin Claude Code

Bundles 2 skills, 4 commands, 2 hooks · 0 tokens together

Git-backed local memory store for Tau sessions, with branch-aware recall and manual capture.

ThibautMelen/agentic-ai-systems

Agent

Agent "multi-window" from ThibautMelen/agentic-ai-systems, covering 🖥️ multi-window context, diagram, when to use, implementation and flow example.

keli-wen/agentic-harness-patterns-skill

Skill Claude CodeCodex

Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.