Model-driven context management (Active Context Pruning / ACP) for the DeepSeek Harness — the model decides when and what to compress. Ported from billion-context-pi (ranxianglei); acp-kernel reused verbatim. CompactionEngine backend with compress/decompress/search_context/acp_status tools.

Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "imp

Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions, shared thread context, and cross-model review.

Persistent session memory for AI coding agents that never leaves your machine — including the on-device model that reasons over it. Restores your prior decisions, open TODOs, and changed files across sessions; adds associative recall of related past work,

OpenClaude opens coding-agent workflows to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models

Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.

You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/OpenCode/Cursor/Grok/GitHub/Kiro/Z.AI/Xiaomi/MiniMax/Kimi(300+ models, 200+ LLM providers, free models no auth) Build your AI company with multiple teams

Claude Code skill for handling long-context tasks through recursive decomposition

You already have the agent. This is everything around it. great_cto runs Claude Code as a pipeline of 70 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and three decisions stay yours: what gets built, how, and whether it ships.

Third-party provider reasoning-effort AND input-modality settings for DeepSeek Harness: thinking levels and image-input support declared per model, auto-adapted from a model knowledge base + wire-protocol inference, edited right inside the official Models

DeepSeek Harness companion for ClineBot / ClinePass: dynamic subscription models sync, quota exhaustion warnings, session metrics, dedicated settings page, live usage limits, and /cline slash-command.

Custom modes and custom prompts for DeepSeek Harness (dsh): edit a mode's system prompt on the settings page (it takes effect on the next model step), pick its base mode, switch plugin rows one by one, and keep several assistants side by side — coding, ch

Role-based AI swarm orchestration for DeepSeek Harness: duty-table model pinning per role, parallel task DAG with review loops, and a live Swarm dashboard tab in the web GUI.

Compound V — a multi-model orchestrator for Claude Code, layered on Superpowers: a deterministic router (Opus for risky work, Sonnet for the mechanical), cross-model review (Claude + Codex), 3 scouts (code · docs · domain), semantic memory, and Epic/Marathon autonomous loop mode. The pill that turns one freelancer into a squad.

23 practical agent skills: TeamWorkflow, multi-model review, media ingestion, and writing. Original Claude Code packages plus a Codex desktop edition tuned for Astra. Source for clickai.dev.

Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.

Automatic provider/model fallback chains for DeepSeek Harness agents when LLM requests keep failing (retry exhausted, auth, quota, rate limit)

Use Cursor CLI from Claude Code to delegate coding tasks to Composer 2.5+ and other Cursor models.

Claude-Code-style dynamic workflows for Pi — fan a task out across 100s of subagents with real model routing, token/cost accounting, resume, git-worktree isolation, an interactive /workflows TUI, and a real /deep-research.

Use a Kimi Code membership in DeepSeek Harness through a dedicated Kimi subscription model route

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until all models reach consensus.

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

Browser transport implementations for Model Context Protocol (MCP) - postMessage, Chrome extension messaging, and iframe communication for AI agents and LLMs