1,698 tagged Memory and context, measured the same way as everything else here.
Browse within: agent-memory 176ai-memory 115local-first 86knowledge-graph 71context-engineering 64knowledge-base 59obsidian 57knowledge-management 56claude-code-plugin 55model-context-protocol 51ai-tools 49ai-coding 42context-management 41embeddings 41
Instructions file Claude Code
Instructions for s-annam/okfmem, covering claude.md, hard rules (no exceptions), project overview, confirmation discipline and stack and commands.
Instructions file CodexOpenCode
Instructions for AlexanderIstomin/barry-cache: Barry Cache remembers this repo through source-backed context files.
bcharleson/crystallized-intelligence
Instructions file CodexOpenCode
Instructions for bcharleson/crystallized-intelligence, covering agent guide — crystallized intelligence for agents, repo roles, quick start for agents, operating rules and fork → initialize → use.
Instructions file Claude Code
Instructions for lcvbeek/patina, covering patina cli, development and architecture.
Instructions file Claude Code
Instructions for DPBG/Engram.AI, covering claude.md — engram architecture & contributor guide, 1. what engram is, 2. the six architectural invariants (non-negotiable), invariant 1 — integrated multi-mechanism learning and invariant 2 — developmental critical periods.
Instructions file CodexOpenCode
AGENTS.md instructions for tvergho/agentdex, a project described as: Local search engine for your AI coding conversations.
Instructions file CodexOpenCode
An AGENTS.md instruction file for the gurutalks project, which turns the ideas of historical and modern thinkers into an agent memory library and conversation skills.
Instructions file Claude Code
Instructions for proofsh/obsidian-mcp, covering claude.md, project overview, development commands, sync dependencies and update lockfile and run the server locally (for development).
Instructions file Claude Code
Project instructions for a read-only MCP service that lets an AI agent inspect a code project’s files and context. MCP is a standard way for an AI agent to call tools provided by another service.
Instructions file CodexOpenCode
Instructions for lidless-labs/immichctrl, covering agents.md - working in this repo, every session, definition of done, memory owner and memory handoff (mandatory).
Instructions file CodexOpenCode
Instructions for FramY2/ctxwise, a project described as: CtxWise — see and control what Codex loads. Local-first context audit, profiles, drift detection, and honest token receipts.
Instructions file GitHub Copilot
Copilot instructions for jyunming/Axon, covering axon knowledge center — copilot instructions, what axon is, project namespaces, hierarchical projects (up to 5 levels) and merged read-only scopes.
Instructions file CodexOpenCode
AGENTS.md instructions for yoheinakajima/epistemedia, covering agents.md — epistemedia control contract, governing rule, mandatory orientation, authority map and epistemic rules.
Instructions file GitHub Copilot
Instructions for Byggarepop/TokenSaver, covering copilot instructions, supported file types (via minifyfile), when not to use these tools and reporting.
Instructions file CodexOpenCode
Instructions for dawitlabs/capsule, a project described as: Markdown context packs that help coding agents reduce repeated repository-discovery tokens.
Instructions file CodexOpenCode
Instructions for go-ports/echovault, covering agents.md, project overview, build & development commands, build for current platform (optimised) and build without cross-compile flags (fastest local build).
Instructions file CodexOpenCode
Instructions for ctxfile/ctxfile, covering claude.md, project, hard rules, commands (run from repo root) and release checklist (every ship, no step skipped).
Instructions file Claude Code
Claude Code instructions for Pseudogiant-xr/Pseudolife-MCP, covering pseudolife-mcp — project conventions, shipping checklist (any change that lands on master), derived state / caches / indexes, running tests (exit-code discipline) and review discipline.
Instructions file Claude Code
A project instruction file containing personal context, coding preferences, privacy rules, website details, and technology notes for Claude Code.
Instructions file Claude CodeCodexOpenCode
AGENTS.md instructions for buildinternet/releases-cli, covering agents guide — releases-cli, stack, commands, architecture and conventions.
Instructions file Claude Code
Instructions for Kit4Some/Oh-my-ClaudeClaw, covering openclaw-cc v2 — autonomous ai harness, mandatory behavior — execute on every interaction, phase 0: context injection (before responding), phase 1: automatic task analysis and phase 2: execution with quality gates.
Instructions file Claude Code
Instructions for ramybarsoum/prodkit, covering prodkit - schema, knowledge architecture, layer 1: raw sources (user-owned, immutable), layer 2: the wiki (llm-owned, compounding) and links.
Instructions file Claude Code
Instructions for AbdurRafay2004/handoff, covering claude.md, what this repo is, runtime model (how the pieces connect), invariants — do not break these when editing hooks and working / testing the hooks.
Instructions file Claude Code
Instructions for zzallirog/weighted-compact, covering claude.md — weighted-compact root, substrate framing, tl;dr in 30 seconds, repo map and architectural invariants (locked).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: