treg-dsh
OpenRouter for tools - 2,896 agent-friendly tools, pay for the usage, not subscription
168 results
OpenRouter for tools - 2,896 agent-friendly tools, pay for the usage, not subscription
DeepSeek Harness bundle for running API Relay Audit locally
Local-first, self-hosted AI agent runtime with Claude Managed Agents-style APIs, sandboxed sessions, memory, tools, audit, replay, and a local Console.
DSH redteam security research modes and runtime plugins, managed from one settings page: deploy the nine presets, install, update and uninstall the seventeen runtime plugins for the current profile.
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent decides allow/deny on the approval answerer chain, with fail-closed fallback and full session-log audit.
Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness — a capability seam (ctx.memory service + local SQLite provider + memory tool + frozen snapshot injection), not another memory warehouse
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.
Role-based Codex / Claude Code / ACP subagent providers for the DeepSeek Harness: continuable children, durable session recovery, per-role product permissions, delegation with a permission ceiling, and a declarative role library.
FormatForge for DeepSeek Harness: forge any file format (pdf/docx/xlsx/pptx/eml/toml/...) into AI-readable structured data. v1.0.0 (PRODUCTION-READY, protocol frozen): 协议冻结(v1.x 向后兼容)+ v0.14.0 全部 7 项 P0+P1 + 5 项 audit 修复(4 bug + 1 性能)。测试基线 567 passed。Thin
Project-scoped one-shot users for DSH: project/user dual workspaces with symlink isolation, cwd session bucketing, soft guard, and a built-in admin UI. Best-effort isolation (honnet gens) — not a hard security boundary.
Fail-closed LLM-assisted approval reviewer for DeepSeek Harness
Rule-gated automatic approval for DeepSeek Harness sandbox escalations with an optional LLM reviewer and native human fallback.
Normalize redundant sandbox requests and malformed justifications in DeepSeek Harness tools
DSH local security audit tool: read-only scans of config, credential metadata, plugin provenance, session structure and network exposure; redacted, reproducible, locatable risk reports
为 DeepSeek Harness 增加介于 Workspace Write 与 Full access 之间的自动批准权限档:例行沙箱升级由分类模型一次性放行,危险或不确定的操作仍转人工审批。An auto-approval permission preset for DeepSeek Harness between workspace-write and full access: routine sandbox escalations are granted once by a classifier, while dangerous or uncertain requests still go to a human.
MCP bridge: lets ChatGPT Web create, view, continue and control DeepSeek Harness (DSH) agent sessions through the official MCP protocol. The bridge only connects; DSH keeps its session, agent, tool, approval and workspace security model.
Private, zero-trust gateway for DeepSeek Harness Web: loopback-only proxy, exact principal allowlists, and provider-agnostic onboarding
DeepSeek Harness plugin: secondary working directories for a project. The agent keeps the primary workspace as cwd, gains equal write/exec permissions on configured secondary directories under workspace-write mode, and is notified of configuration changes at the next message boundary. Configurable from the session header AND from the session-creation page (before the first message) through a sessionless multiFolder remote API.
Model-based permission approval (approve-for-me) for DeepSeek Harness: an approval/request answerer backed by a separate reviewer model
See what your AI agent protected: session security receipts, visible data provenance, task boundaries, and tool identity checks for DeepSeek Harness.
Tensorlake sandbox execution providers for DeepSeek Harness
Model-reviewed Auto Approve permission preset for the DeepSeek Harness Web UI
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.
Enhanced ACP server for DeepSeek Harness: block-level streaming, usage/stat telemetry (cache hit rate, token speed, input/output tokens, context length, turns, tool timing), model & reasoning-effort switching, and permission-preset control over the ACP wire (Zed-friendly)