LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing, lifecycle hooks, multi-agent collaboration, and workflows.
Our agent harness: Skills, plugins, hooks, and utilities to improve the quality of your agent.
Reusable Agent Skills, plus integrations (statusline, provider usage, vision) that install into Codex, Claude Code, and opencode.
Make Opus 4.8 (or any Claude model) work like Claude Fable 5 — a Claude Code skill + guard hooks (plan gate, model ceiling, per-task enforcement) for Fable-5-grade discipline: plan, self-verify, and route sub-agents, without Fable 5.
Waifu for hermes-agent. Dashboard plugin with multi-emotion support.
Route Codex PermissionRequest hooks to the BLE "buddy" hardware from anthropics/claude-desktop-buddy. Approve/deny Codex actions on a physical button. macOS, on-demand BLE.
Pre-compaction hooks + a CAS-guarded task pointer that keep Codex agents on-goal across context auto-compaction — no mainline drift, no duplicate work, no conflicting progress in long runs.
YAML hook automation for the PI coding agent: tool guards, session hooks, prompts, notifications, and bash actions.
Proof-carrying completion for AI coding agents. Block 'I'm done' until every critical obligation has evidence.
Multi-agent coordination + harness adapters + portable CLI utilities for Claude Code / Cursor / Codex.
Open protocol for agent-to-agent communication over HTTPS. No registry, no platform — just inboxes.
Universal agent lifecycle / hook event handler for agent harnesses
Keep AI-generated UI on-system.
Wmux — Warp alert: native toasts when your AI agent (Claude, Codex, OpenCode, Gemini) finishes a turn.
完整的軟體開發工作流程自動化系統，透過 8 個專業角色的 Agent Hooks 實現端到端自動化流程
CLI for managing Agent commands, hooks, and skills across projects.
KiroForge - VS Code extension for Kiro IDE that enforces organizational code quality standards through steering packs, validation hooks, and Kiro Agent Hooks automation. Includes real-time validation, productivity analytics, and team metrics collection.
Publication authority for @workspacejson/codex-mcp and the preserved OpenAI Build Week submission. Development is migrating to workspacejson/integrations.
Nokori (残り) — behavioral memory layer for Claude Code and Cursor. Turns your corrections into rules that come back when it counts. 经验留下的痕迹，比记忆更深。
Evidence gates and session continuity for AI coding agents
To associate your repository with the agent-hooks topic, visit your repo's landing page and select "manage topics."