One config to rule them all — sync MCP servers, skills and AGENTS.md across 18 AI coding tools, and package them as Agent Plugins.

Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.

Fork of @deepseek-ai/dsh-agent-instructions that delivers the workspace instruction baseline as system-prompt sections, keeping the upstream mid-session reminder path.

Built-in memory decides what to remember. This one asks. Agent memory as plain files in your folder: the agent proposes, you approve, every line dated. Injected on Claude Code, Cursor & OpenCode; skills on Codex & Copilot. One memory per client, session handoffs, promotion into knowledge and rules on your yes, plus orchestration and QA layers.

Session memory for Claude Code. Auto-captures every session into a plain Obsidian markdown vault. Zero config. MIT. macOS + Linux.

Your team and your AI agents work from the same context: tasks, their full history and time as plain files in your git repository

Multi-account orchestration and secure token storage for OAuth-based MCP servers

A persistent, Git-versioned map of your whole codebase and database schema that coding agents read before they touch anything. Local-first MCP server + CLI in Go: a governed repository index of code knowledge that gives Claude Code, Codex, Cursor, and opencode long-term context, memory, and code intelligence.

Composable, view-based memory for DeepSeek Harness. Pluggable sources and strategies, with three-tier memory out of the box.

Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /caveman-compress.

Linter for AI agent configurations. Validates SKILL.md, CLAUDE.md, hooks, MCP, and more.

Automatic project memory for Claude Code: decisions, rules and dead ends saved to JEVMEM.md in your repo, brought back next session. In the Claude plugin directory and on the MCP Registry.

🗂️🤖 Airtable Model Context Protocol Server, for allowing AI systems to interact with your Airtable bases

💻 Give AI models complete control of your computer (probably a bad idea)

Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.

Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt. File-only, no external services.

Requires dsh >= 0.1.7 (session format 4); on dsh 0.1.5 use dsh-repeat-tool-breaker@0.7. Escalating repeat detection for dsh: a synchronous ctx.tools.guard gate that counts semantic fingerprints (exact/cmd/net/host/sink) over a per-agent sliding window, wa

Local dashboard auditing Claude Code's per-turn token context (skills, agents, commands, CLAUDE.md, MEMORY.md, hooks, MCP) with toggle-based disable and session analytics.

Open-source Claude Code plugin porting the internal /skillify skill: turn a finished session's repeatable workflow into a reusable SKILL.md you can rerun with a slash command.

Audit MCP servers, skills, and CLAUDE.md bloat eating your Claude Code context window.