v2.4.0 · AGPL-3.0
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.
v0.4.1 · Apache-2.0
DeepSeek Harness auth插件
v0.2.0 · MIT
DeepSec — AI Security Offense & Defense Platform. Shield audits AI-generated code for hallucinated packages, missing safeguards & AI pattern errors in real time. Spear automates authorized penetration testing with 40+ skill packs, from recon to PoC.
— · Apache-2.0
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
v0.5.2 · MIT
Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys
v0.2.0-alpha.4 · MIT
Self-contained DeepSeek Harness (DSH) plugin for Provider/Auth login, model switching, image fallback, token/cost analytics, and same-port Web restart. Useful? A star helps.
v0.43.5 · Apache-2.0
Always-on dependency and compatibility monitoring for DeepSeek Harness plugins, including exact paths, upstream changes, and isolated install/load evidence.
v0.3.4 · MIT
Automatic provider/model fallback chains for DeepSeek Harness agents when LLM requests keep failing (retry exhausted, auth, quota, rate limit)
v0.3.8 · MIT
Auditable, token-gated DeepSeek Harness remote gateway: mobile QR access, per-device sessions, Host/Origin rewrite, settings/credentials/directory support.
v0.1.0-rc.9 · MIT
Fail-closed LLM-assisted approval reviewer for DeepSeek Harness
v2.0.0 · Apache-2.0
Deterministic Runtime Execution Governance & Security Circuit-Breaker for DSH & Multi-Agent Workstations
v0.2.19 · MIT
General-purpose MCP connector, connection manager, plugin extension, and integration marketplace for DeepSeek Harness, initiated and maintained by Qichacha/QCC.
v2.4.13 · SEE LICENSE IN LICENSE
AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.
— · Apache-2.0
The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.