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.

neuromemory-ai

577

tonitangpotato/engram-ai

Skill Claude CodeCodex

Neuroscience-grounded memory for AI agents. Add, recall, and manage memories with ACT-R activation, Hebbian learning, and cognitive consolidation.

not rated 46 4mo ago A 35 tokens AGPL-3.0

doc-cleanup

578

aka-luan/doc-cleanup

Skill Claude CodeCodex

Audit and clean Markdown documentation for context rot. Use when docs may contain completed-work logs, executed plans, stale claims, contradictions, dead paths, or drifted authorities, especially in agent-required reading.

not rated 46 3mo ago A 44 tokens original MIT

yesloop

579

carsteneu/yesmem

Skill Claude Code needs its repo

Autonomous task loop — analyze, plan, execute, verify, review, finish. Runs as visible TUI agent in git worktree. Use when user says "yesloop", "loop", "run it autonomously".

not rated 46 +1 changed 9d ago A SkillSpector: warn 48 tokens original Apache-2.0

recall

580

BetaBots-LLC/callimachus

Skill Claude Code

Recall the user's past AI coding sessions (Claude Code, Codex, Cursor and more) before redoing work, or when they mention something decided or solved before.

not rated 46 changed 5d ago A 36 tokens AGPL-3.0

sessions

581

nicknisi/sessions

Plugin Claude Code

Bundles 8 skills, 1 MCP server · 695 tokens together

Skills for summarizing and recalling AI coding sessions across Claude Code, Codex, Pi, and OpenCode.

not rated 46 +1 changed 14d ago A tokens not measured original MIT

palinode-memory

582

phasespace-labs/palinode

Skill Claude CodeCodex

Search, save, and manage persistent agent memory using Palinode (git-versioned markdown + vector search). Use when user says 'remember this', 'save to memory', 'what do you know about X', 'search memory for context', 'what was decided about', 'register a trigger', 'show memory diff', 'run consolidation'. Also fires…

not rated 46 17d ago A SkillSpector: pass 141 tokens original MIT

adam-framework

583

strangeadvancedmarketing/Adam

Skill Claude CodeCodex

5-layer persistent memory and coherence architecture for OpenClaw agents. Solves AI amnesia and within-session drift. Built and validated over 353 sessions on a live business. No CS degree required.

not rated 45 3mo ago A 43 tokens original MIT

memory-system

584

criterium/opencode-lab

Skill Claude CodeCodex

Loaded by custom.md upon receiving >> or <<. Single file per scope (memory.md) that accumulates relevant project information. In effect until the skill is loaded again. Apply the certainty rule without asking.

not rated 45 2mo ago A SkillSpector: warn 0 tokens original MIT

ontology-inference

585

robotaitai/project-bedrock

Skill Claude CodeCodex

Infer a project's natural ontology from the actual repo. Use when determining what memory branches to create, how to name them, and how to decompose the project into focused domains.

not rated 45 2mo ago A SkillSpector: pass 39 tokens original MIT

NovasPlace/CSM

Skill Codex

Coordinate Git and Cross-Session Memory as version control for agent work. Use when Codex needs AgentBook status, checkpoints, history, resume or handoff, provenance, isolated agent approaches, semantic comparison, or an evidence-backed game-development tuning and playtest iteration with an explicit keep or revert…

not rated 45 +1 4d ago A SkillSpector: pass 65 tokens original MIT

agent-memory

587

ipiton/agent-memory-mcp

Skill Claude CodeCodex

A system for keeping useful project information between agent sessions through persistent memory. It stores decisions, procedures, incidents, postmortems, and current work context.

not rated 45 +2 2d ago A 30 tokens original MIT

katok

588

changeroa/lazykatok

Skill Claude CodeCodex

Search local KakaoTalk keyword, BM25, and EmbeddingGemma vector indexes through the katok CLI, list rooms, export chunks or transcripts, extract attachments, and prepare guarded message sends only after explicit user confirmation.

not rated 45 +1 changed 17d ago A 48 tokens copy · 100% MIT

contextstream-coach

589

contextstream/mcp-server

Skill Claude CodeCodex

Coach this agent on work the person needs again and again, such as a weekly note, an article, a recap or an image series. Use it when the person starts a job for one of their workflows, reacts to a draft, or asks what was learned from earlier jobs. Goals, drafts and the person's own words are saved in their…

not rated 45 +1 changed 21d ago A 103 tokens original MIT

hyxnj666-creator/ai-memory

Skill Claude Code

Project coding conventions extracted from chat history. Load when writing new code, naming things, designing APIs, or reviewing PRs. Topics: Cursor pagination is mandatory for all paged GraphQL endpoints.

not rated 44 6mo ago A 46 tokens original MIT

research-git

591

StepzeroLab/research-git

Plugin Claude Code

Bundles 3 skills, 3 agents · 435 tokens together

A memory system for the code you're exploring: capture each idea as a semantic Feature Capsule, recall it, and regenerate it onto today's codebase. Segmentation/regeneration run on natively-dispatched subagents (your subscription) — no pay-per-use API. MCP serves the graph read-only for sharing.

not rated 44 3mo ago A tokens not measured original MIT

docflow

592

MedAdemBHA/docflow

Plugin Claude Code

Bundles 9 skills, 3 commands · 492 tokens together

Adoption-aware documentation memory for AI coding agents. Scaffolds or adopts living docs, validates native and established structures with appropriate severity, upgrades managed helpers, and loads bounded recent context.

not rated 44 +1 2mo ago A tokens not measured original MIT

ldm-memory-system

593

Holden323/ldm-skill

Skill Claude CodeCodex

A system for organizing an AI project's memories, documents, skills, and reference links. It assigns each kind of information a proper place and keeps one file as the authoritative source.

not rated 44 +1 changed 1mo ago A SkillSpector: pass 175 tokens original MIT

lean-memory

594

Wuesteon/lean-memory

Plugin Claude Code

Bundles 5 commands, 1 MCP server · 82 tokens together

Local-first agent memory for Claude Code: an observing MCP that stores and searches memories, plus a read-only console to verify the supersession spine, score breakdown, and provenance episodes.

not rated 43 3mo ago A tokens not measured original Apache-2.0

ontomics

595

EtienneChollet/ontomics

MCP server Claude CodeCodexCursor +2

Index your codebase's domain knowledge. 20x fewer tokens, 10x faster. Runs locally from the @ontomics/ontomics npm package.

not rated 43 6mo ago A tokens not measured original MIT

memclaw

596

Felo-Inc/memclaw

Plugin Claude Code

Bundles 1 skill · 226 tokens together

Persistent project workspaces for AI agents — task tracking, artifact storage, and semantic retrieval.

not rated 43 6mo ago A tokens not measured original MIT

inite-brain

597

inite-ai/inite-brain-service

Plugin Claude Code

Bundles 6 skills, 3 hooks · 520 tokens together

Persistent, bitemporal memory for Claude Code: the MCP tool surface, six skills that teach the model to use it, recall injected at session start, and capture before compaction.

not rated 43 changed 21d ago A tokens not measured AGPL-3.0

mnemo

598

omermaksutii/mnemo

Skill Claude CodeCodex

Persistent memory for the current session. Use this skill whenever the user asks you to remember a fact, recall something they told you before, or when starting work where prior context might exist (conventions, decisions, file purposes, preferences).

not rated 42 +1 4mo ago A 50 tokens original MIT

knowledge-compiler

600

sonpiaz/hidrix-tools

Skill Claude Code

Collect knowledge from internet → compile into Obsidian wiki. Personal knowledge base builder.

not rated 42 1mo ago A 21 tokens original MIT

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: