1. Conduid
  2. Agents
  3. Agent Workspace Architecture
MCP server · Agents

Agent Workspace Architecture

Agent-ready knowledge architecture, run daily in Claude Code: turn a coding agent into a system you can hand work to and trust while you're away. 18 load-bearing patterns, one-page workspace map, interactive tour, guided learn track, teardowns of real systems, roles, typed memory, hooks, delegation queue, self-audits. Fork-ready samples.

39Low

Scored a month ago · breakdown

About Agent Workspace Architecture

Agent Workspace Architecture is an MCP server published by jimy-r in the Agents category: agent-ready knowledge architecture, run daily in Claude Code: turn a coding agent into a system you can hand work to and trust while you're away. 18 load-bearing patterns, one-page workspace map, interactive tour, guided learn track, teardowns of real systems, roles, typed memory, hooks, delegation queue, self-audits. Fork-ready samples.

The repository has 12 stars and 0 forks, with the last commit 7 days ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/jimy-r/agent-workspace-architecture

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Agent Workspace Architecture

Powered by Claude · Grounded in docs

I know everything about Agent Workspace Architecture. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

v1.21.0v1.21.0 — the board sorts by attention · 10 Oct 2026The board module now sorts cards by what each one asks of the operator. Attention sections.** The card grid is five sections laid over the category columns: Decide, Review, Do, Monitor and Backlog. One optional field (`attn: decide |…
v1.20.0v1.20.0 — memory-layer lifts, credited at the commit read · 8 Oct 2026Six memory-layer lifts.** Eight open-source memory projects were read at pinned commits, and six patterns were rebuilt here. They are a source-drift stamp on the review clock, a read ledger, a credential-shape screen at the memory write,…
v1.19.0v1.19.0 — experiments, and teardown lifts with owners · 4 Oct 2026Experiments.** A new `experiments/` section publishes six experiments the workspace ran on itself. Each protocol was fixed before its data was read, each page links a redacted copy of it, and a failed hypothesis is reported the same way as…
v1.18.0v1.18.0 — teardowns: OpenHarness and Zenith · 4 Oct 2026Sixth and seventh teardowns, each read at one pinned commit. OpenHarness** (`autonomous-ai/openharness` at 4dfcea3af13b). The page reads the repository's own agent-operations record more than the product. It credits validation receipts…
v1.17.0v1.17.0 — CI gates for the claims the docs make · 13 Sep 2026Three claims the docs used to make by hand now fail CI when they stop being true: every pattern sits in exactly one learn module, every teardown and learn page is listed in `llms.txt`, and every workflow is named in `SECURITY.md`.…
Questions

About Agent Workspace Architecture

How do I install Agent Workspace Architecture?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Agent Workspace Architecture safe to use with an AI agent?

Its trust score is 39 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Agent Workspace Architecture still maintained?

Yes — the latest release is v1.21.0 (10 Oct 2026), and the last commit was 7 days ago. The repository has 12 stars.