brianwang2007xjtu/dsh-agent-teams
brianwang2007xjtu★ 1JavaScript最后同步: 2026-08-19
dsh plugin for multi-agent co-working.
README 摘要
dsh-agent-teams Agent teams for the DeepSeek Harness: parallel fan-out of one objective to role-specialized subagents, with an optional integration pass. What it adds One model-facing tool, team : - task — the complete, self-contained objective. - members — a list of { role, instructions } ; each member runs as an independent subagent that only sees the objective and its own role. Members run in parallel via the configured subagent provider. When synthesize is enabled (the default), a final "team lead" subagent integrates the members' output into a single report; otherwise the raw member outputs are returned. Configuration Installation Then mount it with the patch row above in the profile's cordis.patch.yml .
在 GitHub 查看完整 README →分类
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
★ 68,716
volcengine/OpenVikingSelf-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
★ 31,761
titanwings/colleague-skill将冰冷的离别化为温暖的 Skill,欢迎加入数字生命1.0!Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶
★ 23,757