orbital-agents
Persistent Endeavour and Challenger peer sessions for DeepSeek Harness that plan, execute sequential tasks, and verify reported results.
How to install
dsh plugin add dsh-orbital-agents About
Orbital Agents Two coordinated DSH agents that plan and execute as one pair. **Orbital Agents** is the project and repository identity; the published package is **dsh-orbital-agents** (the predecessor name dsh-endeavour is superseded and deprecated on npm). The **Endeavour** agent investigates, writes the plan, and verifies results. Its persistent **Challenger** peer is a second ordinary chat that executes the plan and reports back through a durable protocol. The pair is created once and reused for every later plan, so the two agents stay in the same orbit instead of being re-spawned per task.…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 0
- mo. downloads
- 773
- Last push
- 2026-09-20
- Created
- 2026-09-18
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- ai-agents, cordis, deepseek-harness, dsh, dsh-plugin, dsh-plugins, multi-agent
Related plugins
dsh-memory
FuRongJun-1999/dsh-memory
White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.
dsh-engram
kenz1117/dsh-engram
Cross-session long-term memory under the "memory palace" metaphor: dual-scope SQLite stores (user + per-git-origin project), hybrid FTS5 + local-vector retrieval with RRF fusion and recency/proof ranking boost, automatic capture from the session log (including the final turn), provenance audit chains, consolidation distillation and decay forgetting, and a settings-page Memory Library panel with corridor topology, tour butler, and refurb list.
dsh-pua
MichengAI/dsh-pua
Adds /pua to steer the agent to try another approach and verify results before claiming completion, with 15 company styles, persona modes, global and per-conversation settings, and an optional loop that continues until a verification command passes, the iteration limit is reached, or the user cancels.
dsh-answer-reviewer
bycall/dsh-answer-reviewer
Agentic answer reviewer for DeepSeek Harness: each final assistant turn is re-reviewed by a separate LLM graded 1-100; below-threshold scores steer the agent back with concrete feedback. The score is shown as a chip on the answer's action row (green pass / red needs-work, with retry count and reason on hover). Live gate config over a 127.0.0.1 HTTP server, plus a collapsed dock above the composer and an optional right-sidebar tab via dsh-better-sidebar.