Memory and context

12,529 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

awareness-memory

1081

everest-an/Awareness-Market

Skill Claude CodeCodex

Persistent memory for AI agents — recall past decisions and record new ones across sessions, search a public research knowledge graph, and read the Open Deal Board (awareness.market).

not rated 12 5d ago A 38 tokens original MIT

wormhole

1082

fatmali/wormhole

Plugin Claude Code

Bundles 1 MCP server

Collaborative AI memory layer - sync work between Claude Code, GitHub Copilot, and Cursor.

not rated 11 9mo ago A tokens not measured

calibrate

1083

mishahanin/heading-os

Skill Claude Code needs its repo

Reflective end-of-session self-improvement. Scans the current Claude Code session for corrections, preferences, repeated patterns, errors, success patterns, and voice violations, then proposes numbered concrete patches to memory, settings, ceo-only skills, and ceo-only rules. Corporate files route to a separate review…

not rated 11 changed 1mo ago A SkillSpector: warn 101 tokens original Apache-2.0

grape

1085

gael55x/Grape

Skill Claude CodeCodex

Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.

not rated 11 3mo ago A 48 tokens original MIT

gbrain-ingest

1086

imphillip/gbrain-openclaw

Skill Claude CodeCodex

Ingest meetings, articles, docs, and conversations into the brain. Updates existing pages with new info, creates pages for new entities, maintains cross-references.

not rated 11 7mo ago A 37 tokens original MIT

wiki

1087

flup-repo/skills

Skill Claude Code

Compile personal data (journals, notes, messages, whatever) into a personal knowledge wiki. Ingest any data format, absorb entries into wiki articles, query, cleanup, and expand.

not rated 11 3mo ago A 40 tokens

seeklink

1088

simonsysun/seeklink

MCP server Claude CodeCodexCursor +2

Local semantic search CLI and optional MCP stdio server for Markdown vaults. BM25 + vector + wikilink graph + metadata via RRF. Native CJK. Runs locally from the seeklink Python package.

not rated 11 5mo ago A tokens not measured original MIT archived

cortex-init

1089

brendenclerget/dotcortex

Command Claude Code

Bootstrap Claude Code context management for any project. Scans codebase, interviews user, generates skills/knowledge/memory.

not rated 11 changed 1mo ago A 28 tokens

lethe

1091

teimurjan/lethe

Plugin Claude Code

Bundles 2 skills, 1 hook · 118 tokens together

Persistent memory across Claude Code sessions. Markdown-first storage, hybrid BM25 + dense retrieval, clustered retrieval-induced forgetting, optional Haiku enrichment.

not rated 11 3mo ago A tokens not measured original MIT

brain-cache

1092

j4ckwinter/brain-cache

MCP server Claude CodeCodexCursor +2

MCP server "brain-cache" as configured in j4ckwinter/brain-cache. Runs ./dist/mcp.js with node.

not rated 11 7d ago A tokens not measured

synapse-graph-memory

1093

LameGz/synapse-graph-skills

Skill Claude Code

A memory system that stores project knowledge in linked Markdown files and loads only the notes relevant to a task and its nearby dependencies.

not rated 11 22d ago A 175 tokens original MIT

cognis-skills

1094

Lyzr-Cognis/cognis-skills

Skill Claude CodeCodex

Persistent memory and context for AI agents using Cognis by Lyzr. Use this skill when the user mentions "remember this", "what did I work on", "save this for later", "team knowledge", "project context", "recall", "memory", or needs long-term memory across sessions. Also use when the user asks about past decisions…

not rated 11 7mo ago A 107 tokens original MIT

vbm

1095

dengyuwu/vibe-memory

Skill Codex

A project-memory system called Vibe Memory, or VBM, for Codex and Claude Code. It initializes project guidance, stores controlled rules, enables global instructions, and reads or writes verified memories during development.

not rated 11 7mo ago A 50 tokens

Chub Workflow

1097

nrl-ai/chub

Skill Claude CodeCodex

Complete workflow for AI agents using Chub: how to query docs efficiently and how to write structured annotations back to build persistent team knowledge.

not rated 11 7mo ago A 30 tokens original MIT

david-skills

1098

thedavidweng/skills

Plugin Claude Code

Bundles 18 skills · 726 tokens together

david-skills. AI agent skills for content operations, knowledge management, and developer workflows. Compatible with Hermes Agent and OpenClaw.

not rated 11 changed 10d ago A tokens not measured original MIT

wiki

1099

Illuminated2020/agentic-wiki

Skill Claude Code

Instructions for operating a personal Obsidian wiki with help from a language model. Obsidian is a note-taking app that stores linked notes as files; these instructions cover adding, finding, checking, updating, and reorganising those notes.

not rated 11 3mo ago A 72 tokens original MIT

synapse-mcp

1101

susheel/synapse-mcp

MCP server Claude CodeCodexCursor +2

Persistent MCP server — session memory, engineering pipeline, and living knowledge base for AI agents. Runs locally from the synapse-mcp Python package.

not rated 11 1y ago A tokens not measured original MIT archived

memory-bank

1102

t3ta/memory-bank-mcp-server

MCP server Claude CodeCodexCursor +2

MCP server "memory-bank" as configured in t3ta/memory-bank-mcp-server. Runs locally from the memory-bank npm package.

not rated 11 1y ago A tokens not measured original MIT archived

claude-code-memory

1103

ViralV00d00/claude-code-memory

MCP server Claude CodeCodexCursor +2

MCP server "claude-code-memory" as configured in ViralV00d00/claude-code-memory. Runs locally from the claude-code-memory Python package.

not rated 11 1y ago A tokens not measured

nauro-adopt

1104

Nauro-AI/nauro

Cursor rule Cursor

Seeds Nauro's project store from an existing repo. Use after nauro adopt has run locally. On filesystem-capable surfaces, reads docs (README, manifests, ADRs, Memory-Bank) for rationale and inspects code, config, tests, lockfiles, and recent git history for evidence, then surfaces targeted probes that turn evidence…

not rated 11 changed 9d ago A 89 tokens original Apache-2.0

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: