ruvnet81,2699,555Updated 3d ago
🌊 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
Practical score
97 / 100
Setup
Ready to use
License
MIT
Language
TypeScript
Copy the command, or hand the whole task to your harness agent.
git clone https://github.com/ruvnet/ruflo.gitPlease install the DeepSeek Harness plugin "ruflo" for me. - GitHub repository: ruvnet/ruflo (https://github.com/ruvnet/ruflo) - Type: a skill (installed into ~/.agents/skills) - This skill is primarily built for another AI host. Confirm it works in DSH before…
A cleaned excerpt from the project's own documentation.
An agent meta-harness for Claude Code and Codex.
Open on GitHubSimilar tools from the same corner of the ecosystem.
slow-stack
Cross-session memory for DeepSeek Harness: SQLite + human-editable Markdown mirror, autoDream consolidation, six memory tools, and fully-offline semantic search (local embedding / rerank / clustering), 198 tests.
titanwings
Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill（原同事 Skill）.
loopx-project
A control plane with a durable state kernel for long-horizon agents and teams. Keep work moving and improving across sessions, with less human attention.