Semantic code intelligence MCP server for Claude Code - project maps, symbol search, impact analysis, and more

Installable agent skills for browser automation, local knowledge, skill management, external CLI workflows, and session handoffs.

Resource-aware multi-agent orchestration for Codex and DeepSeek Harness (All in Flash DSH plugin)

See how you really use AI — X-ray your AI coding sessions locally

Agent coordination protocol — declare intents, lock symbols, detect conflicts before code is written

The semantic layer for software engineering: Connect code to meaning, build on understanding

Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.

Universal skill installer and package manager for AI coding agents. One command, 12+ runtimes. npx ai-agent-skills

Structured skill framework for Claude Code. 130 skills, persistent memory, TokenStack compression, localhost dashboard with 3-agent runner, real-time streaming, MCP tools.

A Claude Code skill that 10x's your effective context window by dispatching tasks to background AI workers.

A dashboard for running and coordinating multiple AI CLI agents at once.

Agent skills for Spec Kit

Local, read-only audit for stale AGENTS.md, CLAUDE.md, and generic SKILL.md instructions.

Claude Code skill for session handoffs — survives context compaction, chain-links across sessions.

Turn a repository into a slide deck that tells you when it stops matching the code

Shared config, skills, and update scripts for Claude Code, Codex, and Gemini CLI

MCP server for Git with local Ollama — zero tokens for git operations

A management layer for AI agent skills — discover, install, scope, rate, and update skills across Cursor, Codex, and Claude Code.

Like htop, but for AI coding agents. Monitor Claude Code & Codex CLI sessions, tokens, context window, rate limits, and ports in real-time.

The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.

An agent-first task board, Take human out of the loop.

AI-native, markdown-first project management. Your repo is the project manager.

Containment for AI agents - user isolation, sandboxed execution, network controls, backup/rollback. TLA+ verified.

Local-only web GUI for inspecting agent skills (SKILL.md) across user, project, plugin, cache, and marketplace sources