🧠
AI EngineeringPython

Working Memory

by nowledge-co

Working Memory is an AI Engineering skill for Claude Code, published by nowledge-co in community.

166 stars35 forkson nowledge-co/communityAdded 2026/09/08+2% in starsRepository updated 2026/09/08
agent-memoryalmaclaude-codecursor-plugingemini-cli-extensionmemorynowledge-labsnowledge-memopenclawopenclaw-memory
Install in seconds
Install Working Memory
Copy Working Memory into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/nowledge-co/community/tree/main/nowledge-mem-codex-plugin/skills/working-memory ~/.claude/skills/working-memory

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/nowledge-co/community.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
nowledge-mem-codex-plugin/skills/working-memory/SKILL.md in nowledge-co/community
Installs to
~/.claude/skills/working-memory
Collection
One of 25 skills cataloged from this repository
Category
AI Engineering3670 skills

What Working Memory does

Working Memory loads current cross-tool context at session start, including active work, priorities, and unresolved flags. Use it when resuming work or asking what you are working on.

Working Memory is cataloged under AI Engineering on DirSkills. Working Memory comes from a repository tagged agent-memory, alma, claude-code, cursor-plugin and gemini-cli-extension.

Documentation

README

Start with what matters. For full startup context, use Context Bundle: it resolves owner identity, the resolved AI Identity, active scope, active rules, Working Memory, and KFS paths. Working Memory is the lighter daily briefing of active focus areas, priorities, and recent knowledge changes.

Codex local Memory is a separate, local recall layer. Even when it is enabled, use Nowledge Mem for current cross-tool context, exact prior conversations, sourced decisions, and continuity with other agents.

Preferred path

If this session exposes the Nowledge Mem MCP server and you need the full startup contract, prefer read_context_bundle.

Otherwise use read_working_memory for a lightweight daily briefing, or the CLI Context Bundle fallback:

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Working Memory

  • What else does nowledge-co publish alongside Working Memory?

    Working Memory is one of 25 skills that DirSkills catalogs from nowledge-co/community, the repository it ships in. Its siblings there include Browse Now, Check Connector and Distill Memory. Each one is a separate skill with its own page in this directory, installs the same way Working Memory does, and is maintained by nowledge-co in that same repository. The rest of the collection is listed on the nowledge-co/community page.

  • How does Working Memory compare to other AI Engineering skills?

    Working Memory ranks #3355 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Working Memory against them. Open each page to compare what they document and how they install.

More from nowledge-co/community

Working Memory is one of 25 skills cataloged on DirSkills from nowledge-co/community.

See all 25 skills
🌐
1h ago

Browse Now

Browse Now controls the user's real browser for authenticated pages, dynamic UI interaction, form filling, screenshots, and content extraction. Use it when web search or plain fetches cannot access the live page state.
Automation
16635
🔌
1h ago

Check Connector

Check Connector verifies whether Nowledge Mem is running, detects the current agent, and guides the best connector setup. Use it when setup, configuration, or memory access is failing.
AI Engineering
16635
🧠
1h ago

Distill Memory

Distill Memory saves durable facts, decisions, preferences, and procedures from a conversation into searchable memories. Use it when a session produces insight that should be reused later.
AI Engineering
16635
🧠
1h ago

Distill Memory

Distill Memory captures durable facts, decisions, preferences, and lessons from a conversation when they are likely to save time later. It suggests saving insights after breakthroughs, resolutions, or other high-value moments.
AI Engineering
16635
🧠
1h ago

Distill Memory

Distill Memory saves key decisions, procedures, learnings, preferences, and plans as durable memories. Use it when something non-obvious is discovered or a significant choice is made so future sessions can find it again.
AI Engineering
16635
🧠
1h ago

Distill Memory

Distill Memory recognizes durable decisions, lessons, and breakthrough insights during conversations and suggests saving them at the right moment. Use it when a resolution, preference, or procedure is worth preserving for future reference.
AI Engineering
16635