The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Archcore
Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.
Install
$
git clone https://github.com/archcore-ai/archcoreInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →Archcore - Spec-driven development and git-native context engineering for AI coding agents
The agent stops guessing and starts following the system.
A coding agent can write the code. It does not know your project: what the feature must do, where the code belongs, which decisions and rules already apply. So it guesses, and you explain the same things again in the next session.
Archcore keeps specs, architecture, decisions, rules, and plans in Git, and makes the right project context available to AI coding agents as they work. It helps your coding agent make changes that fit your repo's architecture, rules, and past decisions.
/archcore:planbefore you build. The agent implements from a spec, examples, and tasks, sized to the change./archcore:documentas you go. One sentence from you becomes a finished, linked document./archcore:reviewbefore merge. Archcore compares the branch with the documents and names the side that is wrong.
Install
On macOS, Linux, or WSL:
curl -fsSL https://archcore.ai/install.sh | bash
On Windows (PowerShell 5.1+):
irm https://archcore.ai/install.ps1 | iex
Then, in your project:
archcore init
The installer adds the CLI and plugins for Claude Code, Codex CLI, and GitHub Copilot CLI when it finds them. archcore init connects the agents you choose to this project. It also supports Gemini CLI, OpenCode, Roo Code, and Cline. Cursor needs one extra setup step.
Already have a CLAUDE.md, AGENTS.md, or rule files? Say /archcore:init import in your agent to turn them into project documents.
The documents stay in your repo, in .archcore/. Details: privacy.
Plan: the agent builds from documents, not from a chat message
/archcore:plan [your feature]
/archcore:plan reads the repo and the existing documents first. Then it asks you only what it cannot find there. Your answers become documents in .archcore/: a spec with requirements, and a plan with tasks mapped to files. A user-facing change also gets examples in Given/When/Then form. Larger work can add a PRD, research, or a formal requirements chain.
Archcore weighs the change, computes the route, and reports its size from S to XL. You never choose a template or a size.
| The change | What plan prepares |
|---|---|
| A small fix | No documents |
| A settled choice | A decision record |
| A change to existing behavior | A check of the covering spec: update the spec, or fix the code |
| One new capability | A spec and a plan |
| Several capabilities | A PRD, one spec per capability, and a plan |
Risk raises the size. A security requirement adds a formal requirements chain. A data migration adds a migration runbook.
The agent then implements from the spec, the examples, and the tasks. The open questions are settled before the code, not after it.
Document: you say it once, Archcore writes the document
/archcore:document decision why we chose [X]
/archcore:document code [module]
Similar plugs
Reverse engineer anything with agents, from app behavior down to native binaries.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io