Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.

Install engineering discipline into any AI coding assistant. Composable skills for design, implementation, review, and team standards. Better process, not just better prompts.

A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.

deepseek-harness for vscode .A native VS Code coding-agent extension for DeepSeek Harness. Streamlined workbench with session management, streaming Markdown, slash commands, plugin center, and zero-deployment runtime — no WebUI served, no Harness setup

A visual, non-linear conversation workspace plugin for DeepSeek Harness ; A canvas-based session explorer and branching workspace for DeepSeek Harness.

DSH 个人配置:Token 用量统计 / 成本估算 / 自定义指令 / 外观全局字号 / 桌面宠物(含会话状态概览),纯本地不联网。Personal center for DSH: usage stats, cost estimation, custom instructions, global font size & desktop pet with session overview — all local & offline.

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

Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main context.

Unified DSH checkpoints: session + workspace + config three-state snapshots with one-shot rollback — /checkpoint and /rewind commands, a checkpoint tool, automatic interval snapshots, a Settings page timeline with pairwise diffs, and seed-replay session r

A self-evolving Claude Code plugin. Context routing, memory bootup, smart delegation, self-correction — out of the box.

DSH permission-gate for the DeepSeek Harness 0.1.5 line: a single self-sufficient, deterministic-first, fail-closed gate covering P0 hard-deny -> P1 session grant -> P2 static rule (allow/deny) chain -> P3 optional LLM semantic classifier -> P4 ask, with

Open-source MCP server for comparing products and asking the buyer before purchase.

OpenTelemetry and Langfuse observability exporter for DeepSeek Harness: turn/step/tool/LLM spans, token and cost metrics, and sanitized LLM prompt/completion capture from the session/event stream, with async batching, bounded offline buffering, and retry

Built-in memory decides what to remember. This one asks. Agent memory as plain files in your folder: the agent proposes, you approve, every line dated. Injected on Claude Code, Cursor & OpenCode; skills on Codex & Copilot. One memory per client, session handoffs, promotion into knowledge and rules on your yes, plus orchestration and QA layers.

Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.

Turn a one-line idea into a branch with tested, reviewed, committed code. The brainstorm-to-commit pipeline for Claude Code.

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for free.

Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.

Query robotics, drone, and IoT data in plain English through an MCP server, with an intelligent edge data reduction pipeline that keeps only the data that matters.

Claude Code skill that forces AI to understand before executing. Three disciplines: cognition check, requirement understanding, method search.

TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.

Test mode for your integrations, built for the way agents build. Local, stateful twins of GitHub, Slack, Stripe, Gmail and Linear, over REST and MCP.