244,363 packages matching “llm-tool-policy”
@deepseek-ai/dsh-sandbox-policy
v0.0.1-rc.1 · 1 month ago
Per-call sandbox policy resolver and current model context: deployment fallbacks plus each session's mode and workspace root, shared by every enforcing capability family
No known vulnerabilities
@deepseek-ai/dsh-http-proxy
v0.1.3-alpha.2 · 25 days ago
Process-wide outbound HTTP proxy policy for DeepSeek Harness: resolve it from the launch environment and install it as undici's global dispatcher
No known vulnerabilities
http-cache-semantics
v4.2.0 · 1 year ago
Parses Cache-Control and other headers. Helps building correct HTTP caches and proxies
1 high
@deepseek-ai/dsh-pwsh-sandbox
v0.0.1-rc.1 · 1 month ago
Sandbox-consuming implementation of the DeepSeek Harness PowerShell executor seam (confines every command via ctx.sandbox, reports denial/enforcement result facts)
No known vulnerabilities
csp_evaluator
v1.1.8 · 4 months ago
Evaluate Content Security Policies for a wide range of bypasses and weaknesses
No known vulnerabilities
@deepseek-ai/dsh-base
v0.0.1-rc.1 · 1 month ago
The shared dsh core as a profile bundle: every profile's first patch layer, inserting the base plugin rows over the empty profile root
No known vulnerabilities
llm-trust-guard
v4.32.7 · 2 months ago
Comprehensive security guards for LLM-powered and agentic AI applications - 35 guards covering OWASP Top 10 for LLMs 2025, Agentic Applications 2026, and MCP Security. All guards accessible via unified TrustGuard facade. Features prompt injection (PAP/per
No known vulnerabilities
@unieai/uad-llm
v0.1.21 · 1 month ago
Provider-neutral LLM service interface for the DeepSeek Harness
No known vulnerabilities
@deepseek-ai/dsh-deepseek-llm-api-extensions
v0.1.2-alpha.2 · 1 month ago
Additive request-field registry for the official DeepSeek LLM API adapter
No known vulnerabilities
@mastra/core
v1.74.0 · 1 day ago
Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.
No known vulnerabilities
@deepseek-ai/dsh-llm-deepseek-account
v0.1.7-rc.2 · 8 days ago
DeepSeek account provider authentication and discovery
No known vulnerabilities
@metaharness/darwin
v0.10.3 · 6 days ago
Freeze the model, evolve the harness. Two measured applications: (1) SWE-bench code-repair — conformant GLM->Opus empty-patch cascade resolves 51.3% Lite (n=300) and 55.6% Verified (278/500, Wilson 95% CI [51.2, 59.9], official swebench gold eval, no gold
No known vulnerabilities
@hutson/parse-repository-url
v5.0.0 · 6 years ago
Parse repository URLs to extract, SCM platform, domain, user, and project information.
No known vulnerabilities
@openclaw/ai
v2026.9.8 · 4 hours ago
Reusable model provider adapters and streaming runtime from OpenClaw
No known vulnerabilities
helmet
v8.3.0 · 2 months ago
help secure Express/Connect apps with various HTTP headers
No known vulnerabilities
@deepseek-ai/dsh-llm-deepseek-api-key
v0.1.7-rc.2 · 8 days ago
DeepSeek api-key provider authentication and discovery
No known vulnerabilities
@deepseek-ai/dsh-tool-ralph
v0.0.1-rc.1 · 1 month ago
Model-facing fresh-agent Ralph loop over the workflow and subagent seams
No known vulnerabilities
@deepseek-ai/dsh-subagent-in-process-driver
v0.0.1-rc.5 · 1 month ago
Shared in-process subagent run driver: drives a child agent on ctx.agents (used by the spawn and fork backends)
No known vulnerabilities
@deepseek-ai/dsh-terminal
v0.0.1-rc.3 · 1 month ago
Persistent PTY session seam for the DeepSeek Harness — owner-scoped ids, backend registry, interactive sends, reads, signals, and awaited cleanup
No known vulnerabilities
eslint-config-gulp
v7.0.0 · 8 days ago
Sharable eslint config for gulp projects
No known vulnerabilities