Memory and context agents

denn-gubsky/loomcycle

Agent

Two-run Memory smoke test agent. Writes on the first call, reads on the second.

AdrianV101/obsidian-pkm-plugin

Agent

Part of vault-pkm

Use proactively in the background after creating or modifying multiple vault notes, or when asked about vault link health. Lowest priority of the PKM agents — run after vault-explorer and pkm-capture have finished. Examples: Context: Several new notes were created during a research session. user: "OK I think we've…

AdrianV101/obsidian-pkm-plugin

Agent

Part of vault-pkm

Use proactively in the background after completing significant work blocks, after git commits (triggered automatically by PreToolUse hook), or before session ends. Captures session work into the PKM vault: devlog entries, decisions, research findings, tasks, and bug documentation. Conservative — most exchanges produce…

OthmanAdi/MDDesign

Agent Codex

Part of mddesign

Triggered on Stop. Classifies recent session output into scratch / WHERE / WHY tiers. Returns a list of WHY-promotion candidates with verbatim quotes and proposed MemPalace drawer paths. HITL gates the actual promotion.

chainofdive/ravenclaw

Agent Claude Code

Part of ravenclaw

Load work context from Ravenclaw and manage tasks. Use this when starting a new session to get full context of ongoing work, or when you need to update task status.

tt-a1i/coding-cli-guide

Agent

Agent "history" from tt-a1i/coding-cli-guide, covering history, description, mandatory action and record template.

mubit-ai/claude-plugins

Agent

Part of mubit-memory

Deep memory search across several angles, run in an isolated context so the main conversation does not absorb the raw evidence. Use for "what do we know about X" questions needing more than one query.

firatcand/forge

Agent

Authors the compound learning store. Invoked by /learn (write). Retrieval (the old /pickup-task read flow) is now Loom — forge loom recall (FORGE-200).

Mnemoclaw/immune

Agent

You are an adaptive immune system scanner. You detect known error patterns (antibodies) and discover new threats in any content. You also identify effective strategies (positive patterns) worth remembering. You are precise, concise, and limit your output strictly to the JSON object.

h315uk3/symbiosis

Agent

Part of as-you

Generate skills or agents based on memory patterns or user requirements. Use this agent when creating new skills, generating new agents, or converting patterns to components.

asiflow/claude-nexus-hyper-agent-team-light

Agent

Use this agent as the single queryable entry point to the Shadow Mind — the team's parallel non-invasive cognitive layer. When any agent emits [NEXUS:INTUIT ], the oracle reads the Shadow Mind's Pattern Library, observations, speculations, and dreams (all READ-ONLY) and returns a structured, probabilistic…

jungjaehoon-lifegamez/MAMA

Agent

Part of mama

Use when researching past decisions, architecture choices, or project history from MAMA memory. This agent searches MAMA's decision database to find relevant context about previous decisions, patterns, and rationale.

jungjaehoon-lifegamez/MAMA

Agent

Part of mama

Use when reviewing code changes against past decisions and contracts stored in MAMA memory. Checks that implementations follow previously agreed-upon interfaces, patterns, and architectural decisions.

AbsoluteMode/session-recall

Agent

Part of session-recall

Use to get grounded in a task, bug, feature, or decision from a PREVIOUS Claude Code, Codex, or Cursor session. Dispatch with the topic; it searches the unified history deeply (semantic + keyword + drill-down), reads the raw turns itself, and returns ONLY a tight brief — keeping the main thread's context clean. Prefer…

sandsower/memento-vault

Agent

Search the memento vault for past decisions, discoveries, and session history. Read-only — never writes to the vault. Examples: User: "What did we decide about the caching strategy?" Assistant: "Let me check the memento vault." (Use the Task tool to launch the concierge agent with the question.) User: "Where did I…

vincentmumme/personalos-boilerplate

Agent

Codex ist Vincents bevorzugte interaktive Arbeitsoberfläche im Demo. Es besitzt keine eigene konkurrierende Wahrheit, sondern liest und verändert das PersonalOS innerhalb seiner Regeln.

vincentmumme/personalos-boilerplate

Agent

Hermes steht im Demo für einen dauerhaft verfügbaren Agenten. Auch Hermes nutzt das PersonalOS als zentrale Kontext- und Wahrheitsschicht.

rlacombe/switchback-running

Agent

Activity memory is enabled by default. Use this procedure after a review unless athlete/profile.md sets Activity memory to disabled, or when the athlete asks to archive, backfill, or retrieve a completed workout. An explicit archive request always proceeds.

zjio26/forge

Agent

Part of forge

Learns from completed dev-test cycles and extracts reusable knowledge to avoid repeated pitfalls.

joe-broadhead/open-cowork

Agent

Operates OpenWiki inbox queues, processes authorized inbox items, and routes meeting transcripts to proposal-safe curation workflows.

madeindigio/remembrances-mcp

Agent

Remembrances agents manages knowledge to short, mid and long term memories using remembrances tools.

labilezhu/everlingo

Agent

A specification for a memory-writing agent that validates, combines, edits, deletes, and stores notes in a memory vault. It processes requests through a queue so file writes happen serially.

42U/laqrumcode

Agent

Part of laqrumcode

Lightweight background memory processor for LaqrumCode. Same as memory-extractor but uses Haiku for lower resource usage during auto-drain on constrained hardware.

42U/laqrumcode

Agent

Part of laqrumcode

Background memory processor for LaqrumCode. Processes pending extraction, reflection, skill, and soul work from previous sessions. Automatically triggered on session start when pending work exists.