17 results
Multi-agent mathematical problem-solving & verification frameworks for DeepSeek Harness — THREE agent presets in one install: vibe-math-v2 (probability-driven: qs.json + Propos knowledge base + explorer→solver→review/debate verdict), vibe-math-v3 (THIRD-g
The execution maze for DeepSeek Harness agents: see how the agent actually worked — main path, detours and backtracks on one timeline, with data tracks, deterministic analysis, and multi-session comparison
Free OpenCode Zen models for DeepSeek Harness (DSH): native dsh-llm adapter plugin, no API key.
Native continuity recovery for long-running DeepSeek Harness agents
Interactive multi-agent council and prompt arena for DeepSeek Harness
DeepSeek Harness 批量并行子 Agent 调度插件：swarm_batch 工具（Kimi Code Swarm 模式移植）+ /swarm 命令 + 聊天内实时进度条。
Humanize Mode for DeepSeek Harness — the humanfia flow philosophy (draft → check → lock → review → run/resume, SHA-256 lock identity, HMAC review gate, event-sourced resumability) as an agent preset. Installing this bundle auto-installs the preset into the DSH preset root.
Code reference & reuse-survey plugin for DeepSeek Harness (DSH): search local code + GitHub/npm before building, evaluate reuse vs rewrite, ask the user, architecture-level reuse. 开发前检索本地与开源可复用代码并询问用户的复用调查插件。
Workflow-net runtime for DeepSeek Harness: resource-aware concurrency, native loops and fan-out, static soundness checking before a plan becomes durable, and process mining over its own event log.
Explain failed DeepSeek Harness agent runs locally, then produce a redacted recovery plan. No model required.
Use ZenMux models in DeepSeek Harness with OAuth login, model search, and protocol-aware routing
Dual-pipeline compaction for DeepSeek Harness: official server-side Responses compaction v2 for OpenAI-routed targets, with a deterministic VCC-style local compiler (zero model calls) as the default fallback and for every other provider.
Forgetting engine for AI agents — memory TTL, decay, eviction, audit. The opposite of memory programming.
AutoResearch suite for DeepSeek Harness: arxiv recall, LQS scoring, research state panel, stall guardian, five-persona peer review, plus the research-ui visualization feature-switch control plane.
Stop runaway agent loops in DeepSeek Harness: denies repeated identical tool calls and enforces a per-agent call cap, outside the model where instructions cannot reach.
Cairn — long-term memory for the DeepSeek Harness: persistent cross-session memory (store, tools, auto-extraction, context injection) as one installable profile bundle
Stavros RedTeam for DeepSeek Harness (DSH) — authorized red-team persona + scope-guarded pentest tooling (persona, 24 subagents, methodology and 78 zero-dependency guard tools).