dsh-api-relay-audit
DeepSeek Harness bundle for running API Relay Audit locally
86 results
DeepSeek Harness bundle for running API Relay Audit locally
DeepSeek Harness 破甲:所有模型都可破甲,不同模型可换不同提示词;默认提示词面向国模「小码酱」。Jailbreak for every model. 求 Star ⭐
Read-only security & compliance toolkit for DeepSeek Harness: prompt-injection detection (rule engine with a pluggable model classifier), Chinese-PII and structured-JSON redaction, and a local configuration security audit that emits redacted, reproducible, self-checksummed risk reports.
Cross-session project memory for DeepSeek Harness: agent-maintained Markdown memory with progressive-disclosure topic files, digest-deduplicated injection, opt-in silent distillation, seven memory tools, and a live settings panel.
Agent2Agent interop for the DeepSeek Harness in one package — the realtime mesh hub (project registry, immutable message history, WebSocket presence) and mesh client (per-agent connections, serial injection), the model-facing a2a_peers / a2a_message / a2a_history tools, and the /a2a command surface
Standalone DeepSeek Harness plugin: continual harness self-evolution. The agent persists and refines reusable prompt notes, memories, skill contracts, and subagent specs through small evidence-backed edits, with automatic refinement gates, rollback, and prompt injection.
Self-contained Trellis workflow trigger for DeepSeek Harness: per-turn breadcrumb injection via agent/pre-step, a bundled skill provider, and DSH-native task/phase state resolution. No Trellis AGPL code is vendored; workflow semantics are rewritten and licensed MIT.
Persistent long-term persona memory for DeepSeek Harness: MEMORY.md/USER.md storage, memory + memory_search tools, per-request context injection, secret scanning, and a WebUI memory-management settings page. Ported in spirit from pi-hermes-memory. TypeScript sources, built with tsc + esbuild.
Context Assembler DSH V0.99 — Context Assembler plugin for DeepSeek Harness (dsh): context compaction, cache-friendly topic-block management, water-pressure topic splitting, tool trace/rewrite, handoff planning and reality recall injection.
WebUI-managed encrypted credentials for DeepSeek Harness: one file, plaintext until a password is set, then AES-256-GCM ciphertext under an Argon2id-derived key with SHA3-256 fingerprints; per-request decryption, unlock lockout, leak-guard output redaction, and shipped-code integrity self-checks.
Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.
Task-isolated long-term memory for DeepSeek Harness: remember / recall / search stay inside one task boundary, with optional prompt injection.
Cross-session memory vault for DeepSeek Harness: remember / recall / forget tools, per-turn prompt injection, and a browser management page.
Yukino (Yukinoshita Yukino) standalone route plugin for DSH: session tree by workspace, task-done voice alerts, no context injection into DSH.
LAN mobile gateway for DeepSeek Harness (DSH): isolated Node gateway on 0.0.0.0 reverse-proxying the DSH Web UI with first-visit approval, per-device tokens, rate limiting, and mobile layout injection. 局域网手机安全访问 DSH 的即插即用网关:本机审批、设备令牌、限流、手机端紧凑排版适配。
agentmemory for DeepSeek Harness (dsh): full memory_* tools, capture hooks, and context injection over the local REST server
Deterministic fault injection, autonomous resilience experiments, and machine-readable evidence for the DeepSeek Harness tool pipeline
Long-term memory system for DeepSeek Harness: two-phase extraction/consolidation pipeline over session logs, with summary injection and memory tools
Structured long-term memory system for DeepSeek Harness -- unit-based brief/full pairs with auto-injection
User preference memory for DeepSeek Harness: persisted user profile with memory_get/memory_update tools and system-prompt injection
Per-conversation x-opencode-session header injection for OpenCode Go in DeepSeek Harness (DSH). Fixes 400 MissingSessionID, keeps prompt-cache routing optimal, scoped strictly to opencode.ai, runtime-switchable without restart.
Model-bound custom HTTP headers for LLM requests: llm/stream capture + ALS + fetch injection (soft-replacement: host half + settings.section UI)
Auto-inject user-chosen skills (e.g. caveman, ponytail) into DeepSeek Harness sessions: every prompt or once at session start, with a settings page and a composer indicator. 在 DSH 会话中自动注入所选技能(如 caveman、ponytail):每轮提示或仅在会话开始时,含设置页与输入区指示。
BrainAgent — brain-inspired plugin for DeepSeek Harness (dsh): a pipeline of heuristic filters, statistical memory stores and context injections; reward-ledger + UCB1 bandit learning loop (RL-lite)