Graph-native memory, self-learning, and multi-agent coordination for Claude Code. Every session is captured, every pattern learned, every agent connected. WINDOWS AGENTS: git pull then .\setup.cmd -PythonOnly (never & setup.ps1). SessionStart banner shows install steps when needed.
Authenticate AI agents with auth servers using the Agent Identity (AID) protocol. Ed25519 identity documents, proof of possession, and OAuth 2.0 token exchange.
★not rated 4 1mo agoA
tokens not measured
originalMIT
Spec-first workflows and specialized agent roles for Claude Code. Design docs before code, structured deliberation, automatic previous-session recap on startup.
★not rated 4 1mo agoA
tokens not measured
originalMIT
The meta plugin for the agent-plus framework. Workspace bootstrap, env-var readiness, identity cache, marketplace lifecycle (install/list/update/remove/search/prefer), extensions. One call to init creates .agent-plus/; envcheck reports which sibling-plugin env vars are set (names only); refresh resolves project.
★not rated 4 2mo agoA
tokens not measured
originalMIT
Ultra-advanced multi-agent orchestration system using RabbitMQ for distributed Claude Code instances. Enables team-like collaboration, task distribution, brainstorming, and result aggregation across independent sessions.
wise copilot — flat slash commands, a workflow engine with an SDLC agent roster (CEO/CTO/architect/engineer/QA/security/SRE/…), a session-mining self-improvement loop (mine + refine + reset), and shared scripts for everyday git / PR / ticket-planning / skill-authoring tasks. The /wise command is a natural-language he.
★not rated 4
changed todayA
tokens not measured
originalMIT
Fear of Zeno. Makes the agent close tasks: no trailing offers, no hedged dones, no seeded TODOs. A deterministic stop gate catches loose ends the persona misses.
★not rated 4 1mo agoA
tokens not measured
originalMIT
Turn any repo into a self-prompting agentic loop — a governed, project-fitted sub-agent team with persistent memory, a task/question router, hard safety brakes, a live team board, and active learning.
★not rated 4 23d agoA
tokens not measured
originalMIT
Turn any task into production-ready code. Rules and skills work on any coding harness; specialized agents and automatic hook enforcement are a Claude Code deepening feature.
★not rated 4
changed 5d agoA
tokens not measured
originalMIT
A Chinese-language design guide for creating teams of specialised coding agents and the skills they use. It is intended for Claude Code and focuses on simplified Chinese.
★not rated 4 2mo agoA
tokens not measured
originalApache-2.0
Orchestrate agent teams across multiple AI coding CLIs. Define once, run on Claude Code (slash commands) and Codex (subagents). PRs welcome to add Gemini CLI, Qwen Code, opencode, and more.
★not rated 4 4mo agoA
tokens not measured
originalApache-2.0
Use Google's Antigravity CLI (agy, the successor to Gemini CLI) from Claude Code to ask questions, review code, or delegate tasks. Wraps the local agy binary.
★not rated 4 1mo agoA
tokens not measured
originalApache-2.0
Delegate reasoning, code review, and research to Google Gemini from your coding agent — billed to your Google AI Pro / Ultra subscription via the Antigravity CLI (agy), not your agent's tokens. Skills: gemini-pro (general delegation + model selection via -m), gemini-review (adversarial code/diff/plan review)…
★not rated 4 2mo agoA
tokens not measured
originalMIT
Claude Code skills for AI-context, testing, and MCP development. IANA-registered format (application/vnd.faf+yaml). Create .faf project DNA, score AI-readiness, sync with CLAUDE.md, build MCP servers, generate test suites.
★not rated 4 26d agoA
tokens not measured
originalMIT
Self-running, verifier-gated loops with durable .seeks/ state and native worktrees.
★not rated 4 26d agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: