Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.

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.

A task conductor for Claude Code that gets better the more you use it. Multi-agent orchestration with an evidence contract that BLOCKS instead of asking, gates written as hooks rather than prompts, and a retrospective that learns your repo's rules and tunes its own playbook.

ADHD-friendly study companion agent for Claude Code: spaced repetition, small-chunk teaching, Feynman reflection

CrawlForge MCP Server - Professional Model Context Protocol server with 31 web scraping, crawling, deep-research, and autonomous-extraction tools. Returns clean Markdown and structured JSON for Claude, Cursor, and any MCP client. Defaults to local Ollama

Production-ready prompt library for Claude coding agents. APEI methodology, ~35 specialist prompts, current Claude Code coverage, plus a /find-prompt skill that routes any task to the right prompt.

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

Editor-facing ACP server for Zed and other ACP clients, composed from published DeepSeek Harness plugins. Community-maintained; not affiliated with DeepSeek.

Native DeepSeek Harness (DSH) plugin integrating TypeSafe Jev as a System One decision layer for agent selection, supervision, corrections, and approvals.

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.

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.

Prompt-injection, jailbreak, and secret-leak detection with allow/ask/block interception for DeepSeek Harness: an Aho-Corasick pattern engine and heuristics ported from the Prompt-Injection-Payloads, Jailbreak-Detector, and Secret-Key-Leaker-Detect assets

Interactive long-session background agents plus persistent multi-agent team rooms for DeepSeek Harness: durable continuable child agents with progress, steering and interruption, and cross-session team rooms with a message bus, shared task board, approval

The Fintech Builder algorithm library — canonical, cross-language reference implementations of market-data, corporate-action, index, breadth, candlestick and technical-indicator algorithms, exposed as provider-agnostic subpath modules.

Always-current official Claude docs inside Claude Code. A 3 MB metadata plugin: live on-demand fetching from Anthropic's servers, zero content redistributed. Auto-discovery skill, instant search, interactive HTML courses, and doc changelog reports.

Agent skill that turns natural language, code, Terraform/K8s, SQL, OpenAPI, AsyncAPI, Protobuf and GraphQL sources into editable, tested draw.io architecture diagrams: incremental sync, multi-view projection, drift diff, CI architecture tests, whiteboard derasterize, interactive HTML/PPTX/Mermaid exports.

LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows

Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.

Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.

Topic-based automatic memory for Claude Code — never lose context across sessions or compactions.

A meticulously curated list of useful plugins, extensions, tools and development resources built for DSH, covering productivity enhancement, functional expansion, debugging utilities and custom development modules.

MCP server for 2kw.ai — EU-hosted AI platform: OpenAI-compatible LLM gateway, schema-driven document extraction, transcription, agents with a knowledge base, and cost observability. 158 tools for Claude Code, Cursor, and Windsurf.