v0.1.0 · Apache-2.0
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.
v0.7.0 · MIT
白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。
v3.50.0 · MIT
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
v0.1.0 · MIT
Harness engineering beginner tutorial, from 0 to 1
v0.1.0 · MIT
The living DeepSeek Harness plugin directory — refreshed hourly, compat-tested daily, with an in-app plugin store and scaffolder. DSH 插件活目录：每小时刷新，每日兼容实测，内置插件商店与脚手架。
— · MIT
A reliable coding agent for complex software engineering tasks.
— · Apache-2.0
Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.
v0.50.0 · no license
Open-source alternative to Claude Cowork — a local-first AI agent desktop app · multi-model · self-evolving skills · privacy-first · multi-Harness roadmap · DeepSeek Harness integration in progress
— · no license
DeepSeek Harness (dsh) 从 0 到 1 深度手册：安装/插件开发/性能调优/实测案例/同模型多 Agent 实测对比（中文 + 英文 PDF）
v0.6.3 · Apache-2.0
Synchronize and Orchestrate agents from CLI to GUI, across desktop to phone.
v2.7.2 · MIT
Multi-agent mathematical problem-solving & verification frameworks for DeepSeek Harness — FOUR agent presets in one install: vibe-math-v2 (probability-driven, classic: qs.json + Propos knowledge base + explorer→solver→review/debate verdict), vibe-math-v3
— · MIT
AI agent 通用任务治理框架：对齐目标与事实，规划和调度能力，守住授权与风险边界，治理任务执行到真实验收与交付。Governance framework for evidence-driven planning, orchestration, and verified delivery.
— · Apache-2.0
An LLM-powered multi-agent framework for simulating interactive, evolving story worlds.
— · MIT
Multi-agent department framework for long-form complex tasks, fighting AI hallucination, validated on academic research. 共识管线：多智能体部门长线任务解决框架，对抗AI幻觉，以学术研究为验证场景。
— · MIT
【EMNLP 2026 Demo】A debugging framework for agentic AI systems: diagnose failures, attribute root causes, recover with evidence, and validate fixes through reruns.