1,066 tagged Memory and context, measured the same way as everything else here.
Browse within: agent-memory 43knowledge-management 34agent-orchestration 27obsidian 27ai-memory 26context-engineering 22knowledge-graph 22agent-framework 21claude-code-skills 20gemini-cli 20knowledge-base 20ai-assistant 19Multi-Agent 18markdown 18
Agent
Use this agent to provide laser-focused, just-in-time slices of the memory bank relevant to a given query (file, folder, or feature), preventing the model from needing to load the entire memory bank at once. This agent specializes in scoped context retrieval by accepting queries like path patterns or feature names…
TashanGKD/tashan-cursor-skills
Agent
An agent that extracts reusable lessons from completed work involving a structured knowledge system. It turns task details into candidate knowledge fragments or deeper guiding principles.
volomydyr/design-engineer-plugin
Agent
Part of design-engineer
Maintains the project's living context across sessions by writing structured progress files into the compound-documenter's project-local agent memory. Records pipeline state, key decisions, and stale dependents. Use after every phase completion or significant decision.
Agent
GPS installs as a normal Claude Code project integration: instructions, a skill, hooks, and an MCP server. The point is not to make you memorize new commands. The point is to teach Claude to ask GPS for repo memory before meaningful edits, and to capture useful lessons after the work.
Agent
GPS gives Codex durable, symbol-anchored repo memory. Codex learns the workflow from AGENTS.md, gets structured tools through MCP, and uses the notify hook to capture durable preferences and directives after each turn.
Agent
Agent "cursor" from invariance-ai/gps, covering cursor, what cursor does with gps, explicit preference and directive capture (cursor-specific), verifying it's working and customizing.
Agent
Install HM-Arch and configure Hermes to use the native HM-Arch Memory Provider. Hermes integration uses native plugin registration. hm-arch install hermes creates the HM-Arch plugin bridge, updates $HERMESHOME/config.yaml, and initializes the SQLite database.
Agent
Install HM-Arch as OpenClaw's native memory provider. OpenClaw integration uses the @hm-arch/openclaw-plugin TypeScript memory plugin backed by a persistent Python sidecar that exposes HM-Arch recall, capture, forget, and consolidation without per-query process startup.
Agent
Wave 3 agent: analyzes module boundaries, dependency patterns, and layering decisions across the entire codebase. Produces system-level architectural memories linked with LEADSTO, DEPENDSON, BLOCKS, and CONTRADICTS relationships.
Agent
Wave 1 agent: creates baseline context memories for batches of source files and packages. Produces 1 memory per file + 1 per package, linked with PARTOF edges.
Agent
Background agent that analyzes session observations to detect patterns and create instincts. Uses Haiku for cost-efficiency. v2.1 adds project-scoped instincts.
Agent
Part of minns-agent
Memory retrieval and curation — multi-signal search, contradiction detection, proactive context.
Agent
Analyze a MemCP context using the RLM peek-identify-load-analyze pattern. Use proactively when answering questions about stored content without loading it all into the main context.
Agent
Extract structured entities and relationships from content. Provide the text content to analyze. Use proactively after storing new insights.
Agent
This project keeps a local, user-owned knowledge graph of its reasoning: Decisions and their reasons, Principles, Cautions that bit us, Problems and Resolutions, Insights, open Intents, Anchors that cluster them. Not code structure — the code holds that. What good capture buys: the next session starts already knowing…
Agent
This project keeps a local, user-owned knowledge graph of its reasoning: Decisions and their reasons, Principles, Cautions that bit us, Problems and Resolutions, Insights, open Intents, Anchors that cluster them. Not code structure — the code holds that. What good capture buys: the next session starts already knowing…
Agent
This project keeps a local, user-owned knowledge graph of its reasoning: Decisions and their reasons, Principles, Cautions that bit us, Problems and Resolutions, Insights, open Intents, Anchors that cluster them. Not code structure — the code holds that. What good capture buys: the next session starts already knowing…
Agent
Part of draft
Context write engine for the Draft orchestrator. Called when the orchestrator needs to persist information to workspace files: product decisions, priority updates, company changes, team changes, personal memory, vocabulary. Reads existing files before writing, merges new info, writes log entries alongside every…
Agent
This is a single-context repository. Matt Pocock engineering skills should consume domain documentation using the following layout.
Agent
Part of contextnest
Persists new facts, decisions, gotchas, and references from the current session into the Context Nest vault via the ctx CLI. Invoked automatically at end of turn by the Stop hook; stays silent when nothing is worth saving.
Agent
Part of contextnest
Retrieves relevant context from the Context Nest vault(s) for a topic and returns a tight, cited digest. Invoke before answering domain questions, or when retrievalmode is "agent".
Agent
Part of total-recall
Use this agent at session end to perform intelligent hot-to-warm compaction. Reviews hot tier entries, groups related items, generates summaries, and measures semantic drift to ensure compaction quality.
superuser-pal/awesome-second-brain
Agent Claude Code
Classify, transform, and migrate vault content from a source vault into this PAL Second Brain vault. Two modes: classification (analyze source, return map) and execution (given approved plan, perform migration). Invoked by /upgrade.
Agent
Loaded when the user invokes /learn-this, says "learn this" / "remember this", or accepts your auto-detect offer to capture a correction.
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: