v0.22.3 · MIT
Lightweight Codex/Claude loop harness with strict evidence gates.
— · MIT
Linked-Intent Development - a SDD methodology for agentic coding
v0.1.0 · Apache-2.0
System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics
v1.53.0 · MIT
Memory for AI agents that learns what is wrong and stops repeating it. Mark a memory wrong and it stops coming back; newer facts replace old ones. Local SQLite store and MCP server, persistent across sessions; hippo init wires it into Claude Code, Codex, Cursor, OpenClaw, OpenCode and Pi. Zero runtime deps, MIT, opt-in hosted TypeSafe Jev reranker.
v0.2.94 · MIT
Recent memories stay detailed. Older ones grow concise. Important ones live on.近期记忆保持详细,旧记忆逐渐精简,重要记忆长期存在。
v5.1.0 · MIT
You say it. AutoCode ships it. 48 skills. Code to deployment in one session. iLang v5.0 judgment + secret-safe deploys. Free forever.
v0.5.1 · MIT
A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context.
— · MIT
Bridge Deepseek-harness into Claude Code for review, critique, delegation, and session import.
v0.1.2 · MIT
把Claude Code的UltraCode模式带给DSH,把 DSH 的一次性多 Agent 调度,升级为可生成、可保存、可治理、可观察、可恢复的 Workflow 层
v1.11.1 · MIT
Local-first agent plan annotator
v1.7.38 · MIT
安装即自带mattpocock/skills v1.2.3的25个工程与效率技能,无需手动装技能。300亿token打造。本插件在原始技能之上提供10倍的开发效率。主力支持GitHub issue;Markdown为预览版;GitLab暂不支持。
— · MIT
Self-hosted mission control for AI coding agents: run Claude Code, OpenCode, Pi, Codex, and Antigravity & Gemini CLI 24/7, from any device, watch every subagent live
v0.2.10 · Apache-2.0
dsh-Openwrite:OpenWrite 的 DeepSeek Harness 小说创作插件,含统一创作 Agent、90 个小说工具、原生工作台与标准审稿 DAG
v0.5.18 · Apache-2.0
Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)
— · MIT
A Swift library for macOS automation — mouse, keyboard, screenshots, image recognition, and AI-powered agents.
v2.1.0 · MIT
Claude Code hooks that auto-switch model tier based on task complexity
v1.5.0 · no license
嘉立创EDA专业版(EasyEDA Pro)自动化:给 AI harness 装上画板的「手」—— 一套 typed 原理图/PCB 动作,CLI / Agent Skill / stdio MCP 三形态融合接入。承接嘉立创「不以卖板赚钱,以培养中国工程师为己任」 | EasyEDA Pro automation: the hands of your AI harness — typed schematic/PCB actions via CLI, Agent Skill and stdio MCP.
v2.40.0 · Apache-2.0
📚 A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging experience. | https://misakanet.org
v0.3.9 · BSD-3-Clause
deepseek harness对话和代码状态回退插件 | DSH — rewind conversation and workspace state, powered by a persistent Change Ledger
v0.10.1 · MIT
BrandDocs is a set of agent skills that learn your existing Word, PowerPoint and Excel templates and generate new on-brand documents from them. Unlike generic AI document generators, it preserves brand, structure, styles and formulas by construction. Built for Claude Code, Codex and compatible AI agents.
v0.23.2 · MIT
Import conversation history from 25+ AI coding agents into DeepSeek Harness as resumable sessions — tool calls, reasoning and results kept intact, with reverse export. | 把 25+ AI 编程 Agent 的聊天记录导入 DeepSeek Harness 继续对话,保留工具调用、推理与结果,支持反向导出。
v0.17.14 · MIT
Fix and diagnose DeepSeek Harness on native Windows. Official PowerShell, Workspace Write, shortcuts, and legacy preset repair. No WSL.
v0.10.0 · MIT
Shape rough requests into evidence-backed /goal completion contracts — an Agent Skill for Claude Code and Codex
— · MIT
Research-grade investment decision engine for AI agents: isolated multi-agent committee, auditable verdicts, backtests with lookahead protection, published negative results